LLM blueprints¶
The following endpoints outline how to manage LLM generation.
GET /api/v2/genai/customModelLLMValidations/¶
List custom model LLM validations.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| useCaseId | query | any | false | Only retrieve the custom model LLM validations associated with these use case IDs. |
| playgroundId | query | any | false | Only retrieve the custom model LLM validations associated with this playground ID. |
| offset | query | integer | false | Skip the specified number of values. |
| limit | query | integer | false | Retrieve only the specified number of values. |
| search | query | any | false | Only retrieve the custom model LLM validations matching the search query. |
| sort | query | any | false | Apply this sort order to the results. Valid options are "name", "deploymentName", "userName", "creationDate". Prefix the attribute name with a dash to sort in descending order, e.g., sort=-creationDate. |
| completedOnly | query | boolean | false | If true, only retrieve the completed custom model LLM validations. The default is false. |
| deploymentId | query | any | false | Only retrieve the custom model LLM validations associated with this deployment ID. |
| modelId | query | any | false | Only retrieve the custom model LLM validations associated with this model ID. |
| promptColumnName | query | any | false | Only retrieve the custom model LLM validations where the custom model uses this column name for prompt input. |
| targetColumnName | query | any | false | Only retrieve the custom model LLM validations where the custom model uses this column name for prediction output. |
Example responses¶
200 Response
{
"description": "Paginated list of custom model LLM validations.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "API response object for a single custom model LLM validation.",
"properties": {
"chatModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The model ID to specify when calling the OpenAI chat completion API of the deployment.",
"title": "chatModelId"
},
"creationDate": {
"description": "The creation date of the custom model validation (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"deploymentAccessData": {
"anyOf": [
{
"description": "Add authorization_header to avoid breaking change to API.",
"properties": {
"authorizationHeader": {
"default": "[REDACTED]",
"description": "The `Authorization` header to use for the deployment.",
"title": "authorizationHeader",
"type": "string"
},
"chatApiUrl": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the deployment's chat API.",
"title": "chatApiUrl"
},
"datarobotKey": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The server key associated with the prediction API.",
"title": "datarobotKey"
},
"inputType": {
"description": "The format of the input data submitted to a DataRobot deployment.",
"enum": [
"CSV",
"JSON"
],
"title": "DeploymentInputType",
"type": "string"
},
"modelType": {
"description": "The type of the target output a DataRobot deployment produces.",
"enum": [
"TEXT_GENERATION",
"VECTOR_DATABASE",
"UNSTRUCTURED",
"REGRESSION",
"MULTICLASS",
"BINARY",
"NOT_SUPPORTED"
],
"title": "SupportedDeploymentType",
"type": "string"
},
"predictionApiUrl": {
"description": "The URL of the deployment's prediction API.",
"title": "predictionApiUrl",
"type": "string"
}
},
"required": [
"predictionApiUrl",
"datarobotKey",
"inputType",
"modelType"
],
"title": "DeploymentAccessData",
"type": "object"
},
{
"type": "null"
}
],
"description": "The parameters used for accessing the deployment."
},
"deploymentId": {
"description": "The ID of the custom model deployment.",
"title": "deploymentId",
"type": "string"
},
"deploymentName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the custom model deployment.",
"title": "deploymentName"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the validation error (if the validation failed).",
"title": "errorMessage"
},
"id": {
"description": "The ID of the custom model validation.",
"title": "id",
"type": "string"
},
"modelId": {
"description": "The ID of the model used in the deployment.",
"title": "modelId",
"type": "string"
},
"name": {
"description": "The name of the validated custom model.",
"title": "name",
"type": "string"
},
"predictionTimeout": {
"description": "The timeout in seconds for the prediction API used in this custom model validation.",
"title": "predictionTimeout",
"type": "integer"
},
"promptColumnName": {
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName",
"type": "string"
},
"tenantId": {
"description": "The ID of the tenant the custom model validation belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case associated with the validated custom model.",
"title": "useCaseId"
},
"userId": {
"description": "The ID of the user that created this custom model validation.",
"title": "userId",
"type": "string"
},
"userName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the user that created this custom model validation.",
"title": "userName"
},
"validationStatus": {
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
}
},
"required": [
"id",
"deploymentId",
"targetColumnName",
"validationStatus",
"modelId",
"deploymentAccessData",
"tenantId",
"name",
"useCaseId",
"creationDate",
"userId",
"predictionTimeout",
"promptColumnName"
],
"title": "CustomModelLLMValidationResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListCustomModelLLMValidationsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model LLM validations successfully retrieved. | ListCustomModelLLMValidationsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/customModelLLMValidations/¶
Validate an LLM hosted in a custom model deployment for use in the playground.
Body parameter¶
{
"description": "The body of the \"Validate custom model\" request.",
"properties": {
"chatModelId": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The model ID to specify when calling the OpenAI chat completion API of the deployment. If this parameter is specified, the deployment must support the OpenAI chat completion API.",
"title": "chatModelId"
},
"deploymentId": {
"description": "The ID of the custom model deployment.",
"title": "deploymentId",
"type": "string"
},
"modelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the model used in the deployment.",
"title": "modelId"
},
"name": {
"default": "Untitled",
"description": "The name to use for the validated custom model.",
"maxLength": 5000,
"title": "name",
"type": "string"
},
"predictionTimeout": {
"default": 300,
"description": "The timeout in seconds for the prediction when validating a custom model. Defaults to 300.",
"maximum": 600,
"minimum": 1,
"title": "predictionTimeout",
"type": "integer"
},
"promptColumnName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prompt text input. This value is used to call the Prediction API of the deployment. For LLM deployments that support the OpenAI chat completion API, it is recommended to specify `chatModelId` instead.",
"title": "promptColumnName"
},
"targetColumnName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prediction output. This value is used to call the Prediction API of the deployment. For LLM deployments that support the OpenAI chat completion API, it is recommended to specify `chatModelId` instead.",
"title": "targetColumnName"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case to associate with the validated custom model.",
"title": "useCaseId"
}
},
"required": [
"deploymentId"
],
"title": "CreateCustomModelLLMValidationRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateCustomModelLLMValidationRequest | true | none |
Example responses¶
202 Response
{
"description": "API response object for a single custom model LLM validation.",
"properties": {
"chatModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The model ID to specify when calling the OpenAI chat completion API of the deployment.",
"title": "chatModelId"
},
"creationDate": {
"description": "The creation date of the custom model validation (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"deploymentAccessData": {
"anyOf": [
{
"description": "Add authorization_header to avoid breaking change to API.",
"properties": {
"authorizationHeader": {
"default": "[REDACTED]",
"description": "The `Authorization` header to use for the deployment.",
"title": "authorizationHeader",
"type": "string"
},
"chatApiUrl": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the deployment's chat API.",
"title": "chatApiUrl"
},
"datarobotKey": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The server key associated with the prediction API.",
"title": "datarobotKey"
},
"inputType": {
"description": "The format of the input data submitted to a DataRobot deployment.",
"enum": [
"CSV",
"JSON"
],
"title": "DeploymentInputType",
"type": "string"
},
"modelType": {
"description": "The type of the target output a DataRobot deployment produces.",
"enum": [
"TEXT_GENERATION",
"VECTOR_DATABASE",
"UNSTRUCTURED",
"REGRESSION",
"MULTICLASS",
"BINARY",
"NOT_SUPPORTED"
],
"title": "SupportedDeploymentType",
"type": "string"
},
"predictionApiUrl": {
"description": "The URL of the deployment's prediction API.",
"title": "predictionApiUrl",
"type": "string"
}
},
"required": [
"predictionApiUrl",
"datarobotKey",
"inputType",
"modelType"
],
"title": "DeploymentAccessData",
"type": "object"
},
{
"type": "null"
}
],
"description": "The parameters used for accessing the deployment."
},
"deploymentId": {
"description": "The ID of the custom model deployment.",
"title": "deploymentId",
"type": "string"
},
"deploymentName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the custom model deployment.",
"title": "deploymentName"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the validation error (if the validation failed).",
"title": "errorMessage"
},
"id": {
"description": "The ID of the custom model validation.",
"title": "id",
"type": "string"
},
"modelId": {
"description": "The ID of the model used in the deployment.",
"title": "modelId",
"type": "string"
},
"name": {
"description": "The name of the validated custom model.",
"title": "name",
"type": "string"
},
"predictionTimeout": {
"description": "The timeout in seconds for the prediction API used in this custom model validation.",
"title": "predictionTimeout",
"type": "integer"
},
"promptColumnName": {
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName",
"type": "string"
},
"tenantId": {
"description": "The ID of the tenant the custom model validation belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case associated with the validated custom model.",
"title": "useCaseId"
},
"userId": {
"description": "The ID of the user that created this custom model validation.",
"title": "userId",
"type": "string"
},
"userName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the user that created this custom model validation.",
"title": "userName"
},
"validationStatus": {
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
}
},
"required": [
"id",
"deploymentId",
"targetColumnName",
"validationStatus",
"modelId",
"deploymentAccessData",
"tenantId",
"name",
"useCaseId",
"creationDate",
"userId",
"predictionTimeout",
"promptColumnName"
],
"title": "CustomModelLLMValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Custom model LLM validation job successfully accepted. Follow the Location header to poll for job execution status. |
CustomModelLLMValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
DELETE /api/v2/genai/customModelLLMValidations/{validationId}/¶
Delete an existing custom model LLM validation.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| validationId | path | string | true | The ID of the custom model LLM validation to delete. |
Example responses¶
422 Response
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 204 | No Content | Custom model LLM validation successfully deleted. | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/customModelLLMValidations/{validationId}/¶
Retrieve the status of validating a custom model LLM.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| validationId | path | string | true | The ID of the custom model LLM validation to retrieve. |
Example responses¶
200 Response
{
"description": "API response object for a single custom model LLM validation.",
"properties": {
"chatModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The model ID to specify when calling the OpenAI chat completion API of the deployment.",
"title": "chatModelId"
},
"creationDate": {
"description": "The creation date of the custom model validation (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"deploymentAccessData": {
"anyOf": [
{
"description": "Add authorization_header to avoid breaking change to API.",
"properties": {
"authorizationHeader": {
"default": "[REDACTED]",
"description": "The `Authorization` header to use for the deployment.",
"title": "authorizationHeader",
"type": "string"
},
"chatApiUrl": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the deployment's chat API.",
"title": "chatApiUrl"
},
"datarobotKey": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The server key associated with the prediction API.",
"title": "datarobotKey"
},
"inputType": {
"description": "The format of the input data submitted to a DataRobot deployment.",
"enum": [
"CSV",
"JSON"
],
"title": "DeploymentInputType",
"type": "string"
},
"modelType": {
"description": "The type of the target output a DataRobot deployment produces.",
"enum": [
"TEXT_GENERATION",
"VECTOR_DATABASE",
"UNSTRUCTURED",
"REGRESSION",
"MULTICLASS",
"BINARY",
"NOT_SUPPORTED"
],
"title": "SupportedDeploymentType",
"type": "string"
},
"predictionApiUrl": {
"description": "The URL of the deployment's prediction API.",
"title": "predictionApiUrl",
"type": "string"
}
},
"required": [
"predictionApiUrl",
"datarobotKey",
"inputType",
"modelType"
],
"title": "DeploymentAccessData",
"type": "object"
},
{
"type": "null"
}
],
"description": "The parameters used for accessing the deployment."
},
"deploymentId": {
"description": "The ID of the custom model deployment.",
"title": "deploymentId",
"type": "string"
},
"deploymentName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the custom model deployment.",
"title": "deploymentName"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the validation error (if the validation failed).",
"title": "errorMessage"
},
"id": {
"description": "The ID of the custom model validation.",
"title": "id",
"type": "string"
},
"modelId": {
"description": "The ID of the model used in the deployment.",
"title": "modelId",
"type": "string"
},
"name": {
"description": "The name of the validated custom model.",
"title": "name",
"type": "string"
},
"predictionTimeout": {
"description": "The timeout in seconds for the prediction API used in this custom model validation.",
"title": "predictionTimeout",
"type": "integer"
},
"promptColumnName": {
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName",
"type": "string"
},
"tenantId": {
"description": "The ID of the tenant the custom model validation belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case associated with the validated custom model.",
"title": "useCaseId"
},
"userId": {
"description": "The ID of the user that created this custom model validation.",
"title": "userId",
"type": "string"
},
"userName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the user that created this custom model validation.",
"title": "userName"
},
"validationStatus": {
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
}
},
"required": [
"id",
"deploymentId",
"targetColumnName",
"validationStatus",
"modelId",
"deploymentAccessData",
"tenantId",
"name",
"useCaseId",
"creationDate",
"userId",
"predictionTimeout",
"promptColumnName"
],
"title": "CustomModelLLMValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model LLM validation status successfully retrieved. | CustomModelLLMValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
PATCH /api/v2/genai/customModelLLMValidations/{validationId}/¶
Edit an existing custom model LLM validation.
Body parameter¶
{
"description": "The body of the \"Edit custom model validation\" request.",
"properties": {
"chatModelId": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The model ID to specify when calling the OpenAI chat completion API of the deployment. If this parameter is specified, the deployment must support the OpenAI chat completion API.",
"title": "chatModelId"
},
"deploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the ID of the deployment associated with this custom model validation.",
"title": "deploymentId"
},
"modelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the ID of the model associated with this custom model validation.",
"title": "modelId"
},
"name": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, renames the custom model validation to this value.",
"title": "name"
},
"predictionTimeout": {
"anyOf": [
{
"maximum": 600,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "If specified, sets the timeout in seconds for the prediction when validating a custom model.",
"title": "predictionTimeout"
},
"promptColumnName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the name of the column that will be used to format the prompt text input for the custom model deployment.",
"title": "promptColumnName"
},
"targetColumnName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the name of the column that will be used to extract the prediction response from the custom model deployment.",
"title": "targetColumnName"
}
},
"title": "EditCustomModelValidationRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| validationId | path | string | true | The ID of the custom model LLM validation to edit. |
| body | body | EditCustomModelValidationRequest | true | none |
Example responses¶
200 Response
{
"description": "API response object for a single custom model LLM validation.",
"properties": {
"chatModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The model ID to specify when calling the OpenAI chat completion API of the deployment.",
"title": "chatModelId"
},
"creationDate": {
"description": "The creation date of the custom model validation (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"deploymentAccessData": {
"anyOf": [
{
"description": "Add authorization_header to avoid breaking change to API.",
"properties": {
"authorizationHeader": {
"default": "[REDACTED]",
"description": "The `Authorization` header to use for the deployment.",
"title": "authorizationHeader",
"type": "string"
},
"chatApiUrl": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the deployment's chat API.",
"title": "chatApiUrl"
},
"datarobotKey": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The server key associated with the prediction API.",
"title": "datarobotKey"
},
"inputType": {
"description": "The format of the input data submitted to a DataRobot deployment.",
"enum": [
"CSV",
"JSON"
],
"title": "DeploymentInputType",
"type": "string"
},
"modelType": {
"description": "The type of the target output a DataRobot deployment produces.",
"enum": [
"TEXT_GENERATION",
"VECTOR_DATABASE",
"UNSTRUCTURED",
"REGRESSION",
"MULTICLASS",
"BINARY",
"NOT_SUPPORTED"
],
"title": "SupportedDeploymentType",
"type": "string"
},
"predictionApiUrl": {
"description": "The URL of the deployment's prediction API.",
"title": "predictionApiUrl",
"type": "string"
}
},
"required": [
"predictionApiUrl",
"datarobotKey",
"inputType",
"modelType"
],
"title": "DeploymentAccessData",
"type": "object"
},
{
"type": "null"
}
],
"description": "The parameters used for accessing the deployment."
},
"deploymentId": {
"description": "The ID of the custom model deployment.",
"title": "deploymentId",
"type": "string"
},
"deploymentName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the custom model deployment.",
"title": "deploymentName"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the validation error (if the validation failed).",
"title": "errorMessage"
},
"id": {
"description": "The ID of the custom model validation.",
"title": "id",
"type": "string"
},
"modelId": {
"description": "The ID of the model used in the deployment.",
"title": "modelId",
"type": "string"
},
"name": {
"description": "The name of the validated custom model.",
"title": "name",
"type": "string"
},
"predictionTimeout": {
"description": "The timeout in seconds for the prediction API used in this custom model validation.",
"title": "predictionTimeout",
"type": "integer"
},
"promptColumnName": {
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName",
"type": "string"
},
"tenantId": {
"description": "The ID of the tenant the custom model validation belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case associated with the validated custom model.",
"title": "useCaseId"
},
"userId": {
"description": "The ID of the user that created this custom model validation.",
"title": "userId",
"type": "string"
},
"userName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the user that created this custom model validation.",
"title": "userName"
},
"validationStatus": {
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
}
},
"required": [
"id",
"deploymentId",
"targetColumnName",
"validationStatus",
"modelId",
"deploymentAccessData",
"tenantId",
"name",
"useCaseId",
"creationDate",
"userId",
"predictionTimeout",
"promptColumnName"
],
"title": "CustomModelLLMValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model LLM validation successfully updated. | CustomModelLLMValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/customModelLLMValidations/{validationId}/revalidate/¶
Revalidate an existing custom model LLM validation.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| validationId | path | string | true | The ID of the custom model LLM validation to revalidate. |
Example responses¶
200 Response
{
"description": "API response object for a single custom model LLM validation.",
"properties": {
"chatModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The model ID to specify when calling the OpenAI chat completion API of the deployment.",
"title": "chatModelId"
},
"creationDate": {
"description": "The creation date of the custom model validation (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"deploymentAccessData": {
"anyOf": [
{
"description": "Add authorization_header to avoid breaking change to API.",
"properties": {
"authorizationHeader": {
"default": "[REDACTED]",
"description": "The `Authorization` header to use for the deployment.",
"title": "authorizationHeader",
"type": "string"
},
"chatApiUrl": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the deployment's chat API.",
"title": "chatApiUrl"
},
"datarobotKey": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The server key associated with the prediction API.",
"title": "datarobotKey"
},
"inputType": {
"description": "The format of the input data submitted to a DataRobot deployment.",
"enum": [
"CSV",
"JSON"
],
"title": "DeploymentInputType",
"type": "string"
},
"modelType": {
"description": "The type of the target output a DataRobot deployment produces.",
"enum": [
"TEXT_GENERATION",
"VECTOR_DATABASE",
"UNSTRUCTURED",
"REGRESSION",
"MULTICLASS",
"BINARY",
"NOT_SUPPORTED"
],
"title": "SupportedDeploymentType",
"type": "string"
},
"predictionApiUrl": {
"description": "The URL of the deployment's prediction API.",
"title": "predictionApiUrl",
"type": "string"
}
},
"required": [
"predictionApiUrl",
"datarobotKey",
"inputType",
"modelType"
],
"title": "DeploymentAccessData",
"type": "object"
},
{
"type": "null"
}
],
"description": "The parameters used for accessing the deployment."
},
"deploymentId": {
"description": "The ID of the custom model deployment.",
"title": "deploymentId",
"type": "string"
},
"deploymentName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the custom model deployment.",
"title": "deploymentName"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the validation error (if the validation failed).",
"title": "errorMessage"
},
"id": {
"description": "The ID of the custom model validation.",
"title": "id",
"type": "string"
},
"modelId": {
"description": "The ID of the model used in the deployment.",
"title": "modelId",
"type": "string"
},
"name": {
"description": "The name of the validated custom model.",
"title": "name",
"type": "string"
},
"predictionTimeout": {
"description": "The timeout in seconds for the prediction API used in this custom model validation.",
"title": "predictionTimeout",
"type": "integer"
},
"promptColumnName": {
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName",
"type": "string"
},
"tenantId": {
"description": "The ID of the tenant the custom model validation belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case associated with the validated custom model.",
"title": "useCaseId"
},
"userId": {
"description": "The ID of the user that created this custom model validation.",
"title": "userId",
"type": "string"
},
"userName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the user that created this custom model validation.",
"title": "userName"
},
"validationStatus": {
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
}
},
"required": [
"id",
"deploymentId",
"targetColumnName",
"validationStatus",
"modelId",
"deploymentAccessData",
"tenantId",
"name",
"useCaseId",
"creationDate",
"userId",
"predictionTimeout",
"promptColumnName"
],
"title": "CustomModelLLMValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model LLM successfully revalidated. | CustomModelLLMValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/customModelVersions/¶
Export the specified LLM blueprint as a custom model version in Model Registry.
Body parameter¶
{
"description": "The body of the \"Create custom model version\" request.",
"properties": {
"insightsConfiguration": {
"default": [],
"description": "The configuration of insights to transfer to production.",
"items": {
"description": "The configuration of insights with extra data.",
"properties": {
"aggregationTypes": {
"anyOf": [
{
"items": {
"description": "The type of the metric aggregation.",
"enum": [
"average",
"percentYes",
"classPercentCoverage",
"ngramImportance",
"guardConditionPercentYes"
],
"title": "AggregationType",
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The aggregation types used in the insights configuration.",
"title": "aggregationTypes"
},
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom metric (if using a custom metric).",
"title": "customMetricId"
},
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation if using a custom model LLM for OOTB metrics.",
"title": "customModelLLMValidationId"
},
"deploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model deployment associated with the insight.",
"title": "deploymentId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the evaluation dataset configuration or sidecar model metric validation or OOTB metric.",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The error type associated with the insight error status and error message as an indicator of what fields needs to be edited if any.",
"title": "errorResolution"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The execution status of the evaluation dataset configuration."
},
"insightName": {
"description": "The name of the insight.",
"maxLength": 5000,
"minLength": 1,
"title": "insightName",
"type": "string"
},
"insightType": {
"anyOf": [
{
"description": "The type of insight.",
"enum": [
"Reference",
"Quality metric",
"Operational metric",
"Evaluation deployment",
"Custom metric",
"Nemo"
],
"title": "InsightTypes",
"type": "string"
},
{
"type": "null"
}
],
"description": "The type of the insight."
},
"isTransferable": {
"default": false,
"description": "Indicates if insight can be transferred to production.",
"title": "isTransferable",
"type": "boolean"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The LLM ID for OOTB metrics that use LLMs."
},
"llmIsActive": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is active.",
"title": "llmIsActive"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"modelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the model associated with `deploymentId`.",
"title": "modelId"
},
"modelPackageRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the registered model package associated with `deploymentId`.",
"title": "modelPackageRegisteredModelId"
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithID",
"type": "object"
},
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration associated with the insight configuration.",
"title": "moderationConfiguration"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the Nemo configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the ootb metric (if using an ootb metric).",
"title": "ootbMetricId"
},
"ootbMetricName": {
"anyOf": [
{
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The OOTB metric name."
},
"resultUnit": {
"anyOf": [
{
"description": "The unit of measurement associated with a metric.",
"enum": [
"s",
"ms",
"%"
],
"title": "MetricUnit",
"type": "string"
},
{
"type": "null"
}
],
"description": "The unit of measurement associated with the insight result."
},
"sidecarModelMetricMetadata": {
"anyOf": [
{
"description": "The metadata of a sidecar model metric.",
"properties": {
"expectedResponseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for expected response text input.",
"title": "expectedResponseColumnName"
},
"promptColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName"
},
"responseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for response text input.",
"title": "responseColumnName"
},
"targetColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName"
}
},
"required": [
"targetColumnName"
],
"title": "SidecarModelMetricMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata of the sidecar model metric (if using a sidecar model metric)."
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the sidecar model metric validation (if using a sidecar model metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) where insight is calculated at."
}
},
"required": [
"insightName",
"aggregationTypes"
],
"title": "InsightsConfigurationWithAdditionalData",
"type": "object"
},
"minItems": 0,
"title": "insightsConfiguration",
"type": "array"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint to use for the custom model version.",
"title": "llmBlueprintId",
"type": "string"
},
"llmTestConfigurationIds": {
"default": [],
"description": "The IDs of the LLM test configurations to execute.",
"items": {
"type": "string"
},
"maxItems": 100,
"title": "llmTestConfigurationIds",
"type": "array"
},
"promptColumnName": {
"default": "promptText",
"description": "The name of the column to use for prompt text input in the custom model.",
"maxLength": 5000,
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"default": "resultText",
"description": "The name of the column to use for prediction output in the custom model.",
"maxLength": 5000,
"title": "targetColumnName",
"type": "string"
}
},
"required": [
"llmBlueprintId"
],
"title": "CreateCustomModelVersionRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateCustomModelVersionRequest | true | none |
Example responses¶
202 Response
{
"description": "API response object for the \"Create custom model version\" request.",
"properties": {
"customModelId": {
"description": "The ID of the created custom model.",
"title": "customModelId",
"type": "string"
}
},
"required": [
"customModelId"
],
"title": "CreateCustomModelVersionResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Successful Response | CreateCustomModelVersionResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/llmBlueprints/¶
List LLM blueprints.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | query | any | false | Playground ID. |
| llmIds | query | any | false | Retrieve only the LLM blueprints that use the specified LLM IDs. |
| vectorDatabaseIds | query | any | false | Retrieve only the LLM blueprints linked to the specified vector database IDs. |
| isSaved | query | any | false | Retrieve only the LLM blueprints that have the specified draft/saved status. |
| isStarred | query | any | false | Retrieve only the LLM blueprints that have the specified starred status. |
| offset | query | integer | false | Skip the specified number of values. |
| limit | query | integer | false | Retrieve only the specified number of values. |
| sort | query | any | false | Apply this sort order to the results. Valid options are "name", "description", "creationDate", "lastUpdateDate", "llmId", "vectorDatabaseId". Prefix the attribute name with a dash to sort in descending order, e.g., sort=-creationDate. |
| creationUserIds | query | any | false | Retrieve only the LLM blueprints created by these users. |
Example responses¶
200 Response
{
"description": "Paginated list of LLM blueprints.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "API response object for a single LLM blueprint.",
"properties": {
"creationDate": {
"description": "The creation date of the LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this LLM blueprint.",
"title": "creationUserId",
"type": "string"
},
"creationUserName": {
"description": "The name of the user who created this LLM blueprint.",
"title": "creationUserName",
"type": "string"
},
"customModelLLMErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorMessage"
},
"customModelLLMErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorResolution"
},
"customModelLLMValidationStatus": {
"anyOf": [
{
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation status of the custom model LLM (if using a custom model LLM)."
},
"description": {
"description": "The description of the LLM blueprint.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the LLM blueprint.",
"title": "id",
"type": "string"
},
"isActive": {
"description": "Whether the LLM specified in this blueprint is active in the current environment.",
"title": "isActive",
"type": "boolean"
},
"isDeprecated": {
"description": "Whether the LLM specified in this blueprint is deprecated.",
"title": "isDeprecated",
"type": "boolean"
},
"isSaved": {
"description": "If false, then this LLM blueprint is a draft and its settings can be changed. If true, then its settings are frozen and cannot be changed anymore.",
"title": "isSaved",
"type": "boolean"
},
"isStarred": {
"description": "Specifies whether this LLM blueprint is starred.",
"title": "isStarred",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this LLM blueprint.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM selected for this LLM blueprint."
},
"llmName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the LLM used by this LLM blueprint.",
"title": "llmName"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"name": {
"description": "The name of the LLM blueprint.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground this LLM blueprint belongs to.",
"title": "playgroundId",
"type": "string"
},
"promptType": {
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
"retirementDate": {
"anyOf": [
{
"format": "date",
"type": "string"
},
{
"type": "null"
}
],
"description": "When the LLM is expected to be retired and no longer available for submitting new prompts.",
"title": "retirementDate"
},
"vectorDatabaseErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the vector database associated with this LLM.",
"title": "vectorDatabaseErrorMessage"
},
"vectorDatabaseErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseErrorResolution"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family associated with this LLM blueprint.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseName"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
},
"vectorDatabaseStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database associated with this LLM blueprint."
}
},
"required": [
"id",
"name",
"description",
"isSaved",
"isStarred",
"promptType",
"playgroundId",
"llmName",
"creationDate",
"creationUserId",
"creationUserName",
"lastUpdateDate",
"lastUpdateUserId",
"vectorDatabaseName",
"vectorDatabaseStatus",
"vectorDatabaseErrorMessage",
"vectorDatabaseErrorResolution",
"customModelLLMValidationStatus",
"customModelLLMErrorMessage",
"customModelLLMErrorResolution",
"vectorDatabaseFamilyId",
"isActive",
"isDeprecated"
],
"title": "LLMBlueprintResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListLLMBlueprintsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ListLLMBlueprintsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/llmBlueprints/¶
Create a new LLM blueprint.
Body parameter¶
{
"description": "The body of the Create LLM Blueprint request.",
"properties": {
"description": {
"default": "",
"description": "The description of the LLM blueprint.",
"maxLength": 5000,
"title": "description",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM selected for this LLM blueprint."
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"name": {
"description": "The name of the LLM blueprint.",
"maxLength": 5000,
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground to link this LLM blueprint to.",
"title": "playgroundId",
"type": "string"
},
"promptType": {
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Specifies the vector database retrieval settings in LLM blueprint API requests.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettingsRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
}
},
"required": [
"playgroundId",
"name"
],
"title": "CreateLLMBlueprintRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateLLMBlueprintRequest | true | none |
Example responses¶
201 Response
{
"description": "API response object for a single LLM blueprint.",
"properties": {
"creationDate": {
"description": "The creation date of the LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this LLM blueprint.",
"title": "creationUserId",
"type": "string"
},
"creationUserName": {
"description": "The name of the user who created this LLM blueprint.",
"title": "creationUserName",
"type": "string"
},
"customModelLLMErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorMessage"
},
"customModelLLMErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorResolution"
},
"customModelLLMValidationStatus": {
"anyOf": [
{
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation status of the custom model LLM (if using a custom model LLM)."
},
"description": {
"description": "The description of the LLM blueprint.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the LLM blueprint.",
"title": "id",
"type": "string"
},
"isActive": {
"description": "Whether the LLM specified in this blueprint is active in the current environment.",
"title": "isActive",
"type": "boolean"
},
"isDeprecated": {
"description": "Whether the LLM specified in this blueprint is deprecated.",
"title": "isDeprecated",
"type": "boolean"
},
"isSaved": {
"description": "If false, then this LLM blueprint is a draft and its settings can be changed. If true, then its settings are frozen and cannot be changed anymore.",
"title": "isSaved",
"type": "boolean"
},
"isStarred": {
"description": "Specifies whether this LLM blueprint is starred.",
"title": "isStarred",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this LLM blueprint.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM selected for this LLM blueprint."
},
"llmName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the LLM used by this LLM blueprint.",
"title": "llmName"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"name": {
"description": "The name of the LLM blueprint.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground this LLM blueprint belongs to.",
"title": "playgroundId",
"type": "string"
},
"promptType": {
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
"retirementDate": {
"anyOf": [
{
"format": "date",
"type": "string"
},
{
"type": "null"
}
],
"description": "When the LLM is expected to be retired and no longer available for submitting new prompts.",
"title": "retirementDate"
},
"vectorDatabaseErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the vector database associated with this LLM.",
"title": "vectorDatabaseErrorMessage"
},
"vectorDatabaseErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseErrorResolution"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family associated with this LLM blueprint.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseName"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
},
"vectorDatabaseStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database associated with this LLM blueprint."
}
},
"required": [
"id",
"name",
"description",
"isSaved",
"isStarred",
"promptType",
"playgroundId",
"llmName",
"creationDate",
"creationUserId",
"creationUserName",
"lastUpdateDate",
"lastUpdateUserId",
"vectorDatabaseName",
"vectorDatabaseStatus",
"vectorDatabaseErrorMessage",
"vectorDatabaseErrorResolution",
"customModelLLMValidationStatus",
"customModelLLMErrorMessage",
"customModelLLMErrorResolution",
"vectorDatabaseFamilyId",
"isActive",
"isDeprecated"
],
"title": "LLMBlueprintResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 201 | Created | Successful Response | LLMBlueprintResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/llmBlueprints/fromChatPrompt/¶
Create a new LLM blueprint using the LLM and vector database settings currently used by the specified existing chat prompt.
Body parameter¶
{
"description": "The body of the Create LLM Blueprint from a ChatPrompt request.",
"properties": {
"chatPromptId": {
"description": "The ID of an existing chat prompt to copy the LLM and vector database settings from.",
"title": "chatPromptId",
"type": "string"
},
"description": {
"default": "",
"description": "The description of the new LLM blueprint.",
"maxLength": 5000,
"title": "description",
"type": "string"
},
"name": {
"description": "The name of the new LLM blueprint.",
"maxLength": 5000,
"title": "name",
"type": "string"
}
},
"required": [
"name",
"chatPromptId"
],
"title": "CreateFromChatPromptRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateFromChatPromptRequest | true | none |
Example responses¶
201 Response
{
"description": "API response object for a single LLM blueprint.",
"properties": {
"creationDate": {
"description": "The creation date of the LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this LLM blueprint.",
"title": "creationUserId",
"type": "string"
},
"creationUserName": {
"description": "The name of the user who created this LLM blueprint.",
"title": "creationUserName",
"type": "string"
},
"customModelLLMErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorMessage"
},
"customModelLLMErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorResolution"
},
"customModelLLMValidationStatus": {
"anyOf": [
{
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation status of the custom model LLM (if using a custom model LLM)."
},
"description": {
"description": "The description of the LLM blueprint.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the LLM blueprint.",
"title": "id",
"type": "string"
},
"isActive": {
"description": "Whether the LLM specified in this blueprint is active in the current environment.",
"title": "isActive",
"type": "boolean"
},
"isDeprecated": {
"description": "Whether the LLM specified in this blueprint is deprecated.",
"title": "isDeprecated",
"type": "boolean"
},
"isSaved": {
"description": "If false, then this LLM blueprint is a draft and its settings can be changed. If true, then its settings are frozen and cannot be changed anymore.",
"title": "isSaved",
"type": "boolean"
},
"isStarred": {
"description": "Specifies whether this LLM blueprint is starred.",
"title": "isStarred",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this LLM blueprint.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM selected for this LLM blueprint."
},
"llmName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the LLM used by this LLM blueprint.",
"title": "llmName"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"name": {
"description": "The name of the LLM blueprint.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground this LLM blueprint belongs to.",
"title": "playgroundId",
"type": "string"
},
"promptType": {
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
"retirementDate": {
"anyOf": [
{
"format": "date",
"type": "string"
},
{
"type": "null"
}
],
"description": "When the LLM is expected to be retired and no longer available for submitting new prompts.",
"title": "retirementDate"
},
"vectorDatabaseErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the vector database associated with this LLM.",
"title": "vectorDatabaseErrorMessage"
},
"vectorDatabaseErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseErrorResolution"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family associated with this LLM blueprint.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseName"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
},
"vectorDatabaseStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database associated with this LLM blueprint."
}
},
"required": [
"id",
"name",
"description",
"isSaved",
"isStarred",
"promptType",
"playgroundId",
"llmName",
"creationDate",
"creationUserId",
"creationUserName",
"lastUpdateDate",
"lastUpdateUserId",
"vectorDatabaseName",
"vectorDatabaseStatus",
"vectorDatabaseErrorMessage",
"vectorDatabaseErrorResolution",
"customModelLLMValidationStatus",
"customModelLLMErrorMessage",
"customModelLLMErrorResolution",
"vectorDatabaseFamilyId",
"isActive",
"isDeprecated"
],
"title": "LLMBlueprintResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 201 | Created | Successful Response | LLMBlueprintResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/llmBlueprints/fromLLMBlueprint/¶
Create a new LLM blueprint using the LLM and vector database settings currently used by the specified existing LLM blueprint.
Body parameter¶
{
"description": "The body of the Create LLM Blueprint from an LLM Blueprint request.",
"properties": {
"description": {
"default": "",
"description": "The description of the new LLM blueprint.",
"maxLength": 5000,
"title": "description",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of an existing LLM blueprint to copy the LLM and vector database settings from.",
"title": "llmBlueprintId",
"type": "string"
},
"name": {
"description": "The name of the new LLM blueprint.",
"maxLength": 5000,
"title": "name",
"type": "string"
}
},
"required": [
"name",
"llmBlueprintId"
],
"title": "CreateFromLLMBlueprintRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateFromLLMBlueprintRequest | true | none |
Example responses¶
201 Response
{
"description": "API response object for a single LLM blueprint.",
"properties": {
"creationDate": {
"description": "The creation date of the LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this LLM blueprint.",
"title": "creationUserId",
"type": "string"
},
"creationUserName": {
"description": "The name of the user who created this LLM blueprint.",
"title": "creationUserName",
"type": "string"
},
"customModelLLMErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorMessage"
},
"customModelLLMErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorResolution"
},
"customModelLLMValidationStatus": {
"anyOf": [
{
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation status of the custom model LLM (if using a custom model LLM)."
},
"description": {
"description": "The description of the LLM blueprint.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the LLM blueprint.",
"title": "id",
"type": "string"
},
"isActive": {
"description": "Whether the LLM specified in this blueprint is active in the current environment.",
"title": "isActive",
"type": "boolean"
},
"isDeprecated": {
"description": "Whether the LLM specified in this blueprint is deprecated.",
"title": "isDeprecated",
"type": "boolean"
},
"isSaved": {
"description": "If false, then this LLM blueprint is a draft and its settings can be changed. If true, then its settings are frozen and cannot be changed anymore.",
"title": "isSaved",
"type": "boolean"
},
"isStarred": {
"description": "Specifies whether this LLM blueprint is starred.",
"title": "isStarred",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this LLM blueprint.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM selected for this LLM blueprint."
},
"llmName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the LLM used by this LLM blueprint.",
"title": "llmName"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"name": {
"description": "The name of the LLM blueprint.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground this LLM blueprint belongs to.",
"title": "playgroundId",
"type": "string"
},
"promptType": {
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
"retirementDate": {
"anyOf": [
{
"format": "date",
"type": "string"
},
{
"type": "null"
}
],
"description": "When the LLM is expected to be retired and no longer available for submitting new prompts.",
"title": "retirementDate"
},
"vectorDatabaseErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the vector database associated with this LLM.",
"title": "vectorDatabaseErrorMessage"
},
"vectorDatabaseErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseErrorResolution"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family associated with this LLM blueprint.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseName"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
},
"vectorDatabaseStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database associated with this LLM blueprint."
}
},
"required": [
"id",
"name",
"description",
"isSaved",
"isStarred",
"promptType",
"playgroundId",
"llmName",
"creationDate",
"creationUserId",
"creationUserName",
"lastUpdateDate",
"lastUpdateUserId",
"vectorDatabaseName",
"vectorDatabaseStatus",
"vectorDatabaseErrorMessage",
"vectorDatabaseErrorResolution",
"customModelLLMValidationStatus",
"customModelLLMErrorMessage",
"customModelLLMErrorResolution",
"vectorDatabaseFamilyId",
"isActive",
"isDeprecated"
],
"title": "LLMBlueprintResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 201 | Created | Successful Response | LLMBlueprintResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
DELETE /api/v2/genai/llmBlueprints/{llmBlueprintId}/¶
Delete an existing LLM blueprint.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| llmBlueprintId | path | string | true | The ID of the LLM blueprint to delete. |
Example responses¶
422 Response
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 204 | No Content | Successful Response | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/llmBlueprints/{llmBlueprintId}/¶
Retrieve an existing LLM blueprint.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| llmBlueprintId | path | string | true | The ID of the LLM blueprint to retrieve. |
Example responses¶
200 Response
{
"description": "API response object for a single LLM blueprint.",
"properties": {
"creationDate": {
"description": "The creation date of the LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this LLM blueprint.",
"title": "creationUserId",
"type": "string"
},
"creationUserName": {
"description": "The name of the user who created this LLM blueprint.",
"title": "creationUserName",
"type": "string"
},
"customModelLLMErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorMessage"
},
"customModelLLMErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorResolution"
},
"customModelLLMValidationStatus": {
"anyOf": [
{
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation status of the custom model LLM (if using a custom model LLM)."
},
"description": {
"description": "The description of the LLM blueprint.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the LLM blueprint.",
"title": "id",
"type": "string"
},
"isActive": {
"description": "Whether the LLM specified in this blueprint is active in the current environment.",
"title": "isActive",
"type": "boolean"
},
"isDeprecated": {
"description": "Whether the LLM specified in this blueprint is deprecated.",
"title": "isDeprecated",
"type": "boolean"
},
"isSaved": {
"description": "If false, then this LLM blueprint is a draft and its settings can be changed. If true, then its settings are frozen and cannot be changed anymore.",
"title": "isSaved",
"type": "boolean"
},
"isStarred": {
"description": "Specifies whether this LLM blueprint is starred.",
"title": "isStarred",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this LLM blueprint.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM selected for this LLM blueprint."
},
"llmName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the LLM used by this LLM blueprint.",
"title": "llmName"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"name": {
"description": "The name of the LLM blueprint.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground this LLM blueprint belongs to.",
"title": "playgroundId",
"type": "string"
},
"promptType": {
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
"retirementDate": {
"anyOf": [
{
"format": "date",
"type": "string"
},
{
"type": "null"
}
],
"description": "When the LLM is expected to be retired and no longer available for submitting new prompts.",
"title": "retirementDate"
},
"vectorDatabaseErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the vector database associated with this LLM.",
"title": "vectorDatabaseErrorMessage"
},
"vectorDatabaseErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseErrorResolution"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family associated with this LLM blueprint.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseName"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
},
"vectorDatabaseStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database associated with this LLM blueprint."
}
},
"required": [
"id",
"name",
"description",
"isSaved",
"isStarred",
"promptType",
"playgroundId",
"llmName",
"creationDate",
"creationUserId",
"creationUserName",
"lastUpdateDate",
"lastUpdateUserId",
"vectorDatabaseName",
"vectorDatabaseStatus",
"vectorDatabaseErrorMessage",
"vectorDatabaseErrorResolution",
"customModelLLMValidationStatus",
"customModelLLMErrorMessage",
"customModelLLMErrorResolution",
"vectorDatabaseFamilyId",
"isActive",
"isDeprecated"
],
"title": "LLMBlueprintResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | LLMBlueprintResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
PATCH /api/v2/genai/llmBlueprints/{llmBlueprintId}/¶
Edit an existing LLM blueprint.
Body parameter¶
{
"description": "The body of the Update LLM Blueprint request.",
"properties": {
"description": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, updates the LLM blueprint description to this value.",
"title": "description"
},
"isSaved": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "If specified, updates the saved status of the LLM blueprint to this value.",
"title": "isSaved"
},
"isStarred": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "If specified, updates the starred status of the LLM blueprint to this value.",
"title": "isStarred"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the LLM used by the LLM blueprint."
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "If specified, updates the LLM settings to these values.",
"title": "llmSettings"
},
"name": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, renames the LLM blueprint to this value.",
"title": "name"
},
"promptType": {
"anyOf": [
{
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, updates the chat context behavior of the LLM blueprint to this value."
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the vector database used by the LLM blueprint. If the specified value is `null`, unlinks the vector database from the LLM blueprint. If omitted, the currently used vector database remains in use.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Specifies the vector database retrieval settings in LLM blueprint API requests.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettingsRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "If specified, updates the vector database retrieval settings to these values."
}
},
"title": "UpdateLLMBlueprintRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| llmBlueprintId | path | string | true | The ID of the LLM blueprint to edit. |
| body | body | UpdateLLMBlueprintRequest | true | none |
Example responses¶
200 Response
{
"description": "API response object for a single LLM blueprint.",
"properties": {
"creationDate": {
"description": "The creation date of the LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this LLM blueprint.",
"title": "creationUserId",
"type": "string"
},
"creationUserName": {
"description": "The name of the user who created this LLM blueprint.",
"title": "creationUserName",
"type": "string"
},
"customModelLLMErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorMessage"
},
"customModelLLMErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorResolution"
},
"customModelLLMValidationStatus": {
"anyOf": [
{
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation status of the custom model LLM (if using a custom model LLM)."
},
"description": {
"description": "The description of the LLM blueprint.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the LLM blueprint.",
"title": "id",
"type": "string"
},
"isActive": {
"description": "Whether the LLM specified in this blueprint is active in the current environment.",
"title": "isActive",
"type": "boolean"
},
"isDeprecated": {
"description": "Whether the LLM specified in this blueprint is deprecated.",
"title": "isDeprecated",
"type": "boolean"
},
"isSaved": {
"description": "If false, then this LLM blueprint is a draft and its settings can be changed. If true, then its settings are frozen and cannot be changed anymore.",
"title": "isSaved",
"type": "boolean"
},
"isStarred": {
"description": "Specifies whether this LLM blueprint is starred.",
"title": "isStarred",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this LLM blueprint.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM selected for this LLM blueprint."
},
"llmName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the LLM used by this LLM blueprint.",
"title": "llmName"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"name": {
"description": "The name of the LLM blueprint.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground this LLM blueprint belongs to.",
"title": "playgroundId",
"type": "string"
},
"promptType": {
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
"retirementDate": {
"anyOf": [
{
"format": "date",
"type": "string"
},
{
"type": "null"
}
],
"description": "When the LLM is expected to be retired and no longer available for submitting new prompts.",
"title": "retirementDate"
},
"vectorDatabaseErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the vector database associated with this LLM.",
"title": "vectorDatabaseErrorMessage"
},
"vectorDatabaseErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseErrorResolution"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family associated with this LLM blueprint.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseName"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
},
"vectorDatabaseStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database associated with this LLM blueprint."
}
},
"required": [
"id",
"name",
"description",
"isSaved",
"isStarred",
"promptType",
"playgroundId",
"llmName",
"creationDate",
"creationUserId",
"creationUserName",
"lastUpdateDate",
"lastUpdateUserId",
"vectorDatabaseName",
"vectorDatabaseStatus",
"vectorDatabaseErrorMessage",
"vectorDatabaseErrorResolution",
"customModelLLMValidationStatus",
"customModelLLMErrorMessage",
"customModelLLMErrorResolution",
"vectorDatabaseFamilyId",
"isActive",
"isDeprecated"
],
"title": "LLMBlueprintResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | LLMBlueprintResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/llms/¶
List the large language models (LLMs) available in the DataRobot platform for the current user.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| offset | query | integer | false | Skip the specified number of values. |
| limit | query | integer | false | Retrieve only the specified number of values. |
| useCaseId | query | any | false | If specified, include custom model LLMs available for this use case. |
| activeOnly | query | boolean | false | Whether to include only active models. |
Example responses¶
200 Response
{
"description": "Paginated list of LLMs.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "The metadata that defines an LLM.",
"properties": {
"contextSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the LLM's context, measured in tokens. `null` if unknown.",
"title": "contextSize"
},
"creator": {
"description": "The creator of the LLM.",
"enum": [
"OpenAI",
"Amazon",
"Google",
"Anthropic",
"Unknown"
],
"title": "LLMCreator",
"type": "string"
},
"dateAdded": {
"description": "The date the LLM was added to the GenAI playground.",
"format": "date",
"title": "dateAdded",
"type": "string"
},
"description": {
"description": "The details about the LLM.",
"title": "description",
"type": "string"
},
"documentationLink": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The link to the vendor documentation for the LLM.",
"title": "documentationLink"
},
"id": {
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
"isActive": {
"description": "Whether the LLM is active.",
"title": "isActive",
"type": "boolean"
},
"isDeprecated": {
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "isDeprecated",
"type": "boolean"
},
"isMetered": {
"default": true,
"description": "Whether the LLM usage is metered.",
"title": "isMetered",
"type": "boolean"
},
"license": {
"description": "The usage license information for the LLM.",
"title": "license",
"type": "string"
},
"name": {
"description": "The name of the LLM.",
"title": "name",
"type": "string"
},
"provider": {
"description": "The party that provides access to the LLM.",
"title": "provider",
"type": "string"
},
"referenceLinks": {
"description": "The references for the LLM.",
"items": {
"description": "A reference link for an LLM.",
"properties": {
"name": {
"description": "Description of the reference document.",
"title": "name",
"type": "string"
},
"url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "URL of the reference document.",
"title": "url"
}
},
"required": [
"name",
"url"
],
"title": "LLMReference",
"type": "object"
},
"title": "referenceLinks",
"type": "array"
},
"retirementDate": {
"anyOf": [
{
"format": "date",
"type": "string"
},
{
"type": "null"
}
],
"description": "When the LLM is expected to be retired and no longer available for submitting new prompts.",
"title": "retirementDate"
},
"settings": {
"description": "The settings supported by the LLM.",
"items": {
"description": "Metadata describing a single setting.",
"properties": {
"constraints": {
"anyOf": [
{
"discriminator": {
"mapping": {
"boolean": "#/components/schemas/BooleanSettingConstraints",
"float": "#/components/schemas/FloatSettingConstraints",
"integer": "#/components/schemas/IntegerSettingConstraints",
"object_id": "#/components/schemas/ObjectIdSettingConstraints",
"string": "#/components/schemas/StringSettingConstraints"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Available constraints for integer settings.",
"properties": {
"maxValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the setting (inclusive).",
"title": "maxValue"
},
"minValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the setting (inclusive).",
"title": "minValue"
},
"type": {
"const": "integer",
"default": "integer",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "IntegerSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for float settings.",
"properties": {
"maxValue": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The maximum value of the setting (inclusive).",
"title": "maxValue"
},
"minValue": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The minimum value of the setting (inclusive).",
"title": "minValue"
},
"type": {
"const": "float",
"default": "float",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "FloatSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for string settings.",
"properties": {
"allowedChoices": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The allowed values for the setting.",
"title": "allowedChoices"
},
"maxLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum length of the value (inclusive).",
"title": "maxLength"
},
"minLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum length of the value (inclusive).",
"title": "minLength"
},
"type": {
"const": "string",
"default": "string",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "StringSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for boolean settings.",
"properties": {
"type": {
"const": "boolean",
"default": "boolean",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "BooleanSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for ObjectId settings.",
"properties": {
"allowedChoices": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The allowed values for the setting.",
"title": "allowedChoices"
},
"type": {
"const": "object_id",
"default": "object_id",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "ObjectIdSettingConstraints",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The constraints for the LLM setting values.",
"title": "constraints"
},
"defaultValue": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The default value of the LLM setting.",
"title": "defaultValue"
},
"description": {
"description": "The description of the LLM setting.",
"title": "description",
"type": "string"
},
"format": {
"anyOf": [
{
"description": "Supported formats for settings.",
"enum": [
"multiline"
],
"title": "SettingFormat",
"type": "string"
},
{
"type": "null"
}
],
"description": "The expected format of the value of the LLM setting."
},
"id": {
"description": "The ID of the LLM setting.",
"title": "id",
"type": "string"
},
"isNullable": {
"default": true,
"description": "Whether the setting allows null values (default: true).",
"title": "isNullable",
"type": "boolean"
},
"name": {
"description": "The name of the LLM setting.",
"title": "name",
"type": "string"
},
"type": {
"description": "Supported data types for settings.",
"enum": [
"integer",
"float",
"string",
"boolean",
"object_id",
"list"
],
"title": "SettingType",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"type",
"constraints",
"defaultValue"
],
"title": "LLMSettingDefinition",
"type": "object"
},
"title": "settings",
"type": "array"
},
"suggestedReplacement": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM suggested as a replacement for this one when it is retired."
},
"supportedCustomModelLLMValidations": {
"anyOf": [
{
"items": {
"description": "The metadata describing a validated custom model LLM.",
"properties": {
"id": {
"description": "The ID of the custom model LLM validation.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the custom model LLM validation.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "SupportedCustomModelLLMValidation",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The supported custom model validations if applicable for this LLM ID.",
"title": "supportedCustomModelLLMValidations"
},
"supportedLanguages": {
"description": "The languages supported by the LLM.",
"title": "supportedLanguages",
"type": "string"
},
"vendor": {
"description": "The vendor of the LLM.",
"title": "vendor",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"vendor",
"provider",
"creator",
"license",
"supportedLanguages",
"settings",
"documentationLink",
"referenceLinks",
"dateAdded",
"isDeprecated",
"isActive"
],
"title": "LanguageModelDefinitionResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListLLMsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ListLLMsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/playgrounds/¶
List playgrounds.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| useCaseId | query | any | false | Only retrieve the playgrounds linked to the specified use cases. |
| offset | query | integer | false | Skip the specified number of values. |
| limit | query | integer | false | Retrieve only the specified number of values. |
| search | query | any | false | Only retrieve the playgrounds with names matching the search query. |
| sort | query | any | false | Apply this sort order to the results. Valid options are "name", "description", "creationDate", "creationUserId", "lastUpdateDate", "lastUpdateUserId", "savedLLMBlueprintsCount". Prefix the attribute name with a dash to sort in descending order, e.g., sort=-creationDate. |
Example responses¶
200 Response
{
"description": "Paginated list of playgrounds.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "API response object for a single playground.",
"properties": {
"creationDate": {
"description": "The creation date of the playground (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this playground.",
"title": "creationUserId",
"type": "string"
},
"description": {
"description": "The description of the playground.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the playground.",
"title": "id",
"type": "string"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this playground.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmBlueprintsCount": {
"description": "The number of LLM blueprints in this playground.",
"title": "llmBlueprintsCount",
"type": "integer"
},
"name": {
"description": "The name of the playground.",
"title": "name",
"type": "string"
},
"savedLLMBlueprintsCount": {
"description": "The number of saved LLM blueprints in this playground.",
"title": "savedLLMBlueprintsCount",
"type": "integer"
},
"useCaseId": {
"description": "The ID of the use case this playground belongs to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this playground.",
"title": "userName",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"useCaseId",
"creationDate",
"creationUserId",
"lastUpdateDate",
"lastUpdateUserId",
"savedLLMBlueprintsCount",
"llmBlueprintsCount",
"userName"
],
"title": "PlaygroundResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListPlaygroundsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ListPlaygroundsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/playgrounds/¶
Create a new playground.
Body parameter¶
{
"description": "The body of the Create Playground request.",
"properties": {
"copyInsights": {
"anyOf": [
{
"description": "The body of the Copy Insights request.",
"properties": {
"sourcePlaygroundId": {
"description": "The ID of the existing playground from where to copy insights.",
"title": "sourcePlaygroundId",
"type": "string"
},
"withEvaluationDatasets": {
"default": false,
"description": "If `true` also copies source playground evaluation datasets to target playground.",
"title": "withEvaluationDatasets",
"type": "boolean"
}
},
"required": [
"sourcePlaygroundId"
],
"title": "CopyInsightsRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "If present, copy insights from source playground to the created playground."
},
"description": {
"description": "The description of the playground.",
"maxLength": 5000,
"title": "description",
"type": "string"
},
"name": {
"description": "The name of the playground.",
"maxLength": 5000,
"title": "name",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case to link the playground to.",
"title": "useCaseId",
"type": "string"
}
},
"required": [
"useCaseId",
"name",
"description"
],
"title": "CreatePlaygroundRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreatePlaygroundRequest | true | none |
Example responses¶
201 Response
{
"description": "API response object for a single playground.",
"properties": {
"creationDate": {
"description": "The creation date of the playground (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this playground.",
"title": "creationUserId",
"type": "string"
},
"description": {
"description": "The description of the playground.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the playground.",
"title": "id",
"type": "string"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this playground.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmBlueprintsCount": {
"description": "The number of LLM blueprints in this playground.",
"title": "llmBlueprintsCount",
"type": "integer"
},
"name": {
"description": "The name of the playground.",
"title": "name",
"type": "string"
},
"savedLLMBlueprintsCount": {
"description": "The number of saved LLM blueprints in this playground.",
"title": "savedLLMBlueprintsCount",
"type": "integer"
},
"useCaseId": {
"description": "The ID of the use case this playground belongs to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this playground.",
"title": "userName",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"useCaseId",
"creationDate",
"creationUserId",
"lastUpdateDate",
"lastUpdateUserId",
"savedLLMBlueprintsCount",
"llmBlueprintsCount",
"userName"
],
"title": "PlaygroundResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 201 | Created | Successful Response | PlaygroundResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
DELETE /api/v2/genai/playgrounds/{playgroundId}/¶
Delete an existing playground.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground to delete. |
Example responses¶
422 Response
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 204 | No Content | Successful Response | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/playgrounds/{playgroundId}/¶
Retrieve an existing playground.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground to retrieve. |
Example responses¶
200 Response
{
"description": "API response object for a single playground.",
"properties": {
"creationDate": {
"description": "The creation date of the playground (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this playground.",
"title": "creationUserId",
"type": "string"
},
"description": {
"description": "The description of the playground.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the playground.",
"title": "id",
"type": "string"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this playground.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmBlueprintsCount": {
"description": "The number of LLM blueprints in this playground.",
"title": "llmBlueprintsCount",
"type": "integer"
},
"name": {
"description": "The name of the playground.",
"title": "name",
"type": "string"
},
"savedLLMBlueprintsCount": {
"description": "The number of saved LLM blueprints in this playground.",
"title": "savedLLMBlueprintsCount",
"type": "integer"
},
"useCaseId": {
"description": "The ID of the use case this playground belongs to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this playground.",
"title": "userName",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"useCaseId",
"creationDate",
"creationUserId",
"lastUpdateDate",
"lastUpdateUserId",
"savedLLMBlueprintsCount",
"llmBlueprintsCount",
"userName"
],
"title": "PlaygroundResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | PlaygroundResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
PATCH /api/v2/genai/playgrounds/{playgroundId}/¶
Edit an existing playground.
Body parameter¶
{
"description": "The body of the Edit Playground request.",
"properties": {
"description": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, updates the playground description to this value.",
"title": "description"
},
"name": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, renames the playground to this value.",
"title": "name"
}
},
"title": "EditPlaygroundRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground to edit. |
| body | body | EditPlaygroundRequest | true | none |
Example responses¶
200 Response
{
"description": "API response object for a single playground.",
"properties": {
"creationDate": {
"description": "The creation date of the playground (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this playground.",
"title": "creationUserId",
"type": "string"
},
"description": {
"description": "The description of the playground.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the playground.",
"title": "id",
"type": "string"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this playground.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmBlueprintsCount": {
"description": "The number of LLM blueprints in this playground.",
"title": "llmBlueprintsCount",
"type": "integer"
},
"name": {
"description": "The name of the playground.",
"title": "name",
"type": "string"
},
"savedLLMBlueprintsCount": {
"description": "The number of saved LLM blueprints in this playground.",
"title": "savedLLMBlueprintsCount",
"type": "integer"
},
"useCaseId": {
"description": "The ID of the use case this playground belongs to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this playground.",
"title": "userName",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"useCaseId",
"creationDate",
"creationUserId",
"lastUpdateDate",
"lastUpdateUserId",
"savedLLMBlueprintsCount",
"llmBlueprintsCount",
"userName"
],
"title": "PlaygroundResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | PlaygroundResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
DELETE /api/v2/genai/playgrounds/{playgroundId}/nemoConfiguration/¶
Delete the NeMo configuration for the playground.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground to retrieve NeMo configuration for. |
Example responses¶
422 Response
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 204 | No Content | Successful Response | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/playgrounds/{playgroundId}/nemoConfiguration/¶
Retrieve the NeMo configuration for the playground.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground to retrieve NeMo configuration for. |
Example responses¶
200 Response
{
"description": "API response object for a playground Nemo configuration.",
"properties": {
"blockedTermsFileContents": {
"description": "The contents of the blocked terms file.",
"title": "blockedTermsFileContents",
"type": "string"
},
"promptLlmConfiguration": {
"anyOf": [
{
"description": "Configuration of LLM used for NeMo guardrails.",
"properties": {
"llmType": {
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
},
"openaiApiBase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API base.",
"title": "openaiApiBase"
},
"openaiApiDeploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API deployment ID.",
"title": "openaiApiDeploymentId"
},
"openaiApiKeyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "OpenAI API Key.",
"title": "openaiApiKeyId"
}
},
"required": [
"llmType"
],
"title": "NemoLLMConfiguration",
"type": "object"
},
{
"type": "null"
}
],
"description": "The LLM configuration for the prompt pipeline."
},
"promptModerationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration for the prompt pipeline."
},
"promptPipelineFiles": {
"anyOf": [
{
"description": "Files used to setup a NeMo pipeline.",
"properties": {
"actionsFileContents": {
"description": "Contents of actions.py file.",
"title": "actionsFileContents",
"type": "string"
},
"configYamlFileContents": {
"description": "Contents of config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "Contents of flows.co file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "Contents of prompts.yaml file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"actionsFileContents",
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPipelineFiles",
"type": "object"
},
{
"type": "null"
}
],
"description": "The prompt pipeline files for this configuration."
},
"promptPipelineMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name for the NeMo Prompt pipeline metric.",
"title": "promptPipelineMetricName"
},
"promptPipelineTemplateId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Guard template to be used for the prompt pipeline, defines actions.py.",
"title": "promptPipelineTemplateId"
},
"responseLlmConfiguration": {
"anyOf": [
{
"description": "Configuration of LLM used for NeMo guardrails.",
"properties": {
"llmType": {
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
},
"openaiApiBase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API base.",
"title": "openaiApiBase"
},
"openaiApiDeploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API deployment ID.",
"title": "openaiApiDeploymentId"
},
"openaiApiKeyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "OpenAI API Key.",
"title": "openaiApiKeyId"
}
},
"required": [
"llmType"
],
"title": "NemoLLMConfiguration",
"type": "object"
},
{
"type": "null"
}
],
"description": "The LLM configuration for the response pipeline."
},
"responseModerationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration for the response pipeline."
},
"responsePipelineFiles": {
"anyOf": [
{
"description": "Files used to setup a NeMo pipeline.",
"properties": {
"actionsFileContents": {
"description": "Contents of actions.py file.",
"title": "actionsFileContents",
"type": "string"
},
"configYamlFileContents": {
"description": "Contents of config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "Contents of flows.co file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "Contents of prompts.yaml file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"actionsFileContents",
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPipelineFiles",
"type": "object"
},
{
"type": "null"
}
],
"description": "The response pipeline files for this configuration."
},
"responsePipelineMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name for the NeMo Response pipeline metric.",
"title": "responsePipelineMetricName"
},
"responsePipelineTemplateId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Guard template to be used for the response pipeline, defines actions.py.",
"title": "responsePipelineTemplateId"
}
},
"required": [
"promptPipelineMetricName",
"promptPipelineFiles",
"promptPipelineTemplateId",
"promptLlmConfiguration",
"responsePipelineMetricName",
"responsePipelineFiles",
"responsePipelineTemplateId",
"responseLlmConfiguration",
"blockedTermsFileContents"
],
"title": "NemoConfigurationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | NemoConfigurationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/playgrounds/{playgroundId}/nemoConfiguration/¶
Update/insert the NeMo configuration for the playground.
Body parameter¶
{
"description": "The body of the Nemo Configuration upsert request.",
"properties": {
"blockedTermsFileContents": {
"description": "The contents of the blocked terms file.",
"title": "blockedTermsFileContents",
"type": "string"
},
"promptLlmConfiguration": {
"anyOf": [
{
"description": "Configuration of LLM used for NeMo guardrails.",
"properties": {
"llmType": {
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
},
"openaiApiBase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API base.",
"title": "openaiApiBase"
},
"openaiApiDeploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API deployment ID.",
"title": "openaiApiDeploymentId"
},
"openaiApiKeyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "OpenAI API Key.",
"title": "openaiApiKeyId"
}
},
"required": [
"llmType"
],
"title": "NemoLLMConfiguration",
"type": "object"
},
{
"type": "null"
}
],
"description": "The LLM configuration for the prompt pipeline."
},
"promptModerationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration for the prompt pipeline."
},
"promptPipelineFiles": {
"anyOf": [
{
"description": "All of the files except for the actions.py file.",
"properties": {
"configYamlFileContents": {
"description": "The contents of the config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "The contents of the flow definition file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "The contents of the prompts file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPiplineFilesRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "The prompt pipeline files for this configuration."
},
"promptPipelineMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name for the NeMo Prompt pipeline metric.",
"title": "promptPipelineMetricName"
},
"promptPipelineTemplateId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Guard template to be used for the prompt pipeline, defines actions.py.",
"title": "promptPipelineTemplateId"
},
"responseLlmConfiguration": {
"anyOf": [
{
"description": "Configuration of LLM used for NeMo guardrails.",
"properties": {
"llmType": {
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
},
"openaiApiBase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API base.",
"title": "openaiApiBase"
},
"openaiApiDeploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API deployment ID.",
"title": "openaiApiDeploymentId"
},
"openaiApiKeyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "OpenAI API Key.",
"title": "openaiApiKeyId"
}
},
"required": [
"llmType"
],
"title": "NemoLLMConfiguration",
"type": "object"
},
{
"type": "null"
}
],
"description": "The LLM configuration for the response pipeline."
},
"responseModerationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration for the response pipeline."
},
"responsePipelineFiles": {
"anyOf": [
{
"description": "All of the files except for the actions.py file.",
"properties": {
"configYamlFileContents": {
"description": "The contents of the config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "The contents of the flow definition file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "The contents of the prompts file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPiplineFilesRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "The response pipeline files for this configuration."
},
"responsePipelineMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name for the NeMo Response pipeline metric.",
"title": "responsePipelineMetricName"
},
"responsePipelineTemplateId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Guard template to be used for the response pipeline, defines actions.py.",
"title": "responsePipelineTemplateId"
}
},
"required": [
"blockedTermsFileContents"
],
"title": "NemoConfigurationUpsertRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground to retrieve NeMo configuration for. |
| body | body | NemoConfigurationUpsertRequest | true | none |
Example responses¶
202 Response
{
"description": "API response object for a playground Nemo configuration.",
"properties": {
"blockedTermsFileContents": {
"description": "The contents of the blocked terms file.",
"title": "blockedTermsFileContents",
"type": "string"
},
"promptLlmConfiguration": {
"anyOf": [
{
"description": "Configuration of LLM used for NeMo guardrails.",
"properties": {
"llmType": {
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
},
"openaiApiBase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API base.",
"title": "openaiApiBase"
},
"openaiApiDeploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API deployment ID.",
"title": "openaiApiDeploymentId"
},
"openaiApiKeyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "OpenAI API Key.",
"title": "openaiApiKeyId"
}
},
"required": [
"llmType"
],
"title": "NemoLLMConfiguration",
"type": "object"
},
{
"type": "null"
}
],
"description": "The LLM configuration for the prompt pipeline."
},
"promptModerationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration for the prompt pipeline."
},
"promptPipelineFiles": {
"anyOf": [
{
"description": "Files used to setup a NeMo pipeline.",
"properties": {
"actionsFileContents": {
"description": "Contents of actions.py file.",
"title": "actionsFileContents",
"type": "string"
},
"configYamlFileContents": {
"description": "Contents of config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "Contents of flows.co file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "Contents of prompts.yaml file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"actionsFileContents",
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPipelineFiles",
"type": "object"
},
{
"type": "null"
}
],
"description": "The prompt pipeline files for this configuration."
},
"promptPipelineMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name for the NeMo Prompt pipeline metric.",
"title": "promptPipelineMetricName"
},
"promptPipelineTemplateId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Guard template to be used for the prompt pipeline, defines actions.py.",
"title": "promptPipelineTemplateId"
},
"responseLlmConfiguration": {
"anyOf": [
{
"description": "Configuration of LLM used for NeMo guardrails.",
"properties": {
"llmType": {
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
},
"openaiApiBase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API base.",
"title": "openaiApiBase"
},
"openaiApiDeploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API deployment ID.",
"title": "openaiApiDeploymentId"
},
"openaiApiKeyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "OpenAI API Key.",
"title": "openaiApiKeyId"
}
},
"required": [
"llmType"
],
"title": "NemoLLMConfiguration",
"type": "object"
},
{
"type": "null"
}
],
"description": "The LLM configuration for the response pipeline."
},
"responseModerationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration for the response pipeline."
},
"responsePipelineFiles": {
"anyOf": [
{
"description": "Files used to setup a NeMo pipeline.",
"properties": {
"actionsFileContents": {
"description": "Contents of actions.py file.",
"title": "actionsFileContents",
"type": "string"
},
"configYamlFileContents": {
"description": "Contents of config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "Contents of flows.co file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "Contents of prompts.yaml file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"actionsFileContents",
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPipelineFiles",
"type": "object"
},
{
"type": "null"
}
],
"description": "The response pipeline files for this configuration."
},
"responsePipelineMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name for the NeMo Response pipeline metric.",
"title": "responsePipelineMetricName"
},
"responsePipelineTemplateId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Guard template to be used for the response pipeline, defines actions.py.",
"title": "responsePipelineTemplateId"
}
},
"required": [
"promptPipelineMetricName",
"promptPipelineFiles",
"promptPipelineTemplateId",
"promptLlmConfiguration",
"responsePipelineMetricName",
"responsePipelineFiles",
"responsePipelineTemplateId",
"responseLlmConfiguration",
"blockedTermsFileContents"
],
"title": "NemoConfigurationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Successful Response | NemoConfigurationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
DELETE /api/v2/genai/playgrounds/{playgroundId}/nemoConfiguration/{metricId}/¶
Delete a NeMo metric for the playground.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground to retrieve NeMo configuration for. |
| metricId | path | string | true | The ID of the metric to delete. |
Example responses¶
422 Response
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 204 | No Content | Successful Response | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/playgrounds/{playgroundId}/ootbMetricConfigurations/¶
List OOTB metric configurations for the selected playground.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground. |
Example responses¶
200 Response
{
"description": "The response for the \"OOTB metric configurations\" retrieve request.",
"properties": {
"ootbMetricConfigurations": {
"description": "The list of OOTB metric configurations to use.",
"items": {
"description": "API response object for a single OOTB metric.",
"properties": {
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation (if using a custom model LLM).",
"title": "customModelLLMValidationId"
},
"customOotbMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The custom OOTB metric name to be associated with the OOTB metric.",
"title": "customOotbMetricName"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the OOTB metric configuration.",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"items": {
"description": "Error type linking directly to the field name that is related to the error.",
"enum": [
"ootbMetricName",
"intervention",
"guardCondition",
"sidecarOverall",
"sidecarRevalidate",
"sidecarDeploymentId",
"sidecarInputColumnName",
"sidecarOutputColumnName",
"promptPipelineFiles",
"promptPipelineTemplateId",
"responsePipelineFiles",
"responsePipelineTemplateId"
],
"title": "InsightErrorResolution",
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The error type associated with the insight error status and error message as an indicator of what fields needs to be edited if any.",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM to use for `correctness` and `faithfulness` metrics."
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration to be associated with the OOTB metric."
},
"ootbMetricConfigurationId": {
"description": "The ID of OOTB metric.",
"title": "ootbMetricConfigurationId",
"type": "string"
},
"ootbMetricName": {
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
}
},
"required": [
"ootbMetricName",
"ootbMetricConfigurationId",
"executionStatus"
],
"title": "OOTBMetricConfigurationResponse",
"type": "object"
},
"title": "ootbMetricConfigurations",
"type": "array"
}
},
"required": [
"ootbMetricConfigurations"
],
"title": "OOTBMetricConfigurationsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | OOTB metric configurations list | OOTBMetricConfigurationsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/playgrounds/{playgroundId}/ootbMetricConfigurations/¶
Create a new OOTB metric configuration.
Body parameter¶
{
"description": "The body of the \"Create OOTB metric configurations\" request.",
"properties": {
"ootbMetricConfigurations": {
"description": "The list of OOTB metrics to use.",
"items": {
"description": "API request object for a single OOTB metric configuration.",
"properties": {
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation (if using a custom model LLM).",
"title": "customModelLLMValidationId"
},
"customOotbMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The custom OOTB metric name to be associated with the OOTB metric. Will default to OOTB metric name if not defined.",
"title": "customOotbMetricName"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM to use for `correctness` and `faithfulness` metrics."
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration to be associated with the OOTB metric."
},
"ootbMetricName": {
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
}
},
"required": [
"ootbMetricName"
],
"title": "OOTBMetricConfigurationRequest",
"type": "object"
},
"title": "ootbMetricConfigurations",
"type": "array"
}
},
"required": [
"ootbMetricConfigurations"
],
"title": "CreateOOTBMetricConfigurationsRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground associated with the OOTB metric configuration. |
| body | body | CreateOOTBMetricConfigurationsRequest | true | none |
Example responses¶
201 Response
{
"description": "The response for the \"OOTB metric configurations\" retrieve request.",
"properties": {
"ootbMetricConfigurations": {
"description": "The list of OOTB metric configurations to use.",
"items": {
"description": "API response object for a single OOTB metric.",
"properties": {
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation (if using a custom model LLM).",
"title": "customModelLLMValidationId"
},
"customOotbMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The custom OOTB metric name to be associated with the OOTB metric.",
"title": "customOotbMetricName"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the OOTB metric configuration.",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"items": {
"description": "Error type linking directly to the field name that is related to the error.",
"enum": [
"ootbMetricName",
"intervention",
"guardCondition",
"sidecarOverall",
"sidecarRevalidate",
"sidecarDeploymentId",
"sidecarInputColumnName",
"sidecarOutputColumnName",
"promptPipelineFiles",
"promptPipelineTemplateId",
"responsePipelineFiles",
"responsePipelineTemplateId"
],
"title": "InsightErrorResolution",
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The error type associated with the insight error status and error message as an indicator of what fields needs to be edited if any.",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM to use for `correctness` and `faithfulness` metrics."
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration to be associated with the OOTB metric."
},
"ootbMetricConfigurationId": {
"description": "The ID of OOTB metric.",
"title": "ootbMetricConfigurationId",
"type": "string"
},
"ootbMetricName": {
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
}
},
"required": [
"ootbMetricName",
"ootbMetricConfigurationId",
"executionStatus"
],
"title": "OOTBMetricConfigurationResponse",
"type": "object"
},
"title": "ootbMetricConfigurations",
"type": "array"
}
},
"required": [
"ootbMetricConfigurations"
],
"title": "OOTBMetricConfigurationsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 201 | Created | OOTB metric configuration created successfully | OOTBMetricConfigurationsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/playgrounds/{playgroundId}/supportedInsights/¶
List the supported insights.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground to retrieve supported insights from. |
| withAggregationTypesOnly | query | boolean | false | If true, only include the insights containing aggregation types. The default is false. |
| productionOnly | query | boolean | false | If true, only include the insights that can be transferred to production. The default is false. |
| completedOnly | query | boolean | false | If true, only include the insights that are completed. The default is false. |
| llmBlueprintIds | query | any | false | The IDs of the LLM blueprints to check for VDB related metrics support. |
Example responses¶
200 Response
{
"description": "Response model for supported insights.",
"properties": {
"insightsConfiguration": {
"description": "The list of supported insights configurations.",
"items": {
"description": "The configuration of insights with extra data.",
"properties": {
"aggregationTypes": {
"anyOf": [
{
"items": {
"description": "The type of the metric aggregation.",
"enum": [
"average",
"percentYes",
"classPercentCoverage",
"ngramImportance",
"guardConditionPercentYes"
],
"title": "AggregationType",
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The aggregation types used in the insights configuration.",
"title": "aggregationTypes"
},
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom metric (if using a custom metric).",
"title": "customMetricId"
},
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation if using a custom model LLM for OOTB metrics.",
"title": "customModelLLMValidationId"
},
"deploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model deployment associated with the insight.",
"title": "deploymentId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the evaluation dataset configuration or sidecar model metric validation or OOTB metric.",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The error type associated with the insight error status and error message as an indicator of what fields needs to be edited if any.",
"title": "errorResolution"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The execution status of the evaluation dataset configuration."
},
"insightName": {
"description": "The name of the insight.",
"maxLength": 5000,
"minLength": 1,
"title": "insightName",
"type": "string"
},
"insightType": {
"anyOf": [
{
"description": "The type of insight.",
"enum": [
"Reference",
"Quality metric",
"Operational metric",
"Evaluation deployment",
"Custom metric",
"Nemo"
],
"title": "InsightTypes",
"type": "string"
},
{
"type": "null"
}
],
"description": "The type of the insight."
},
"isTransferable": {
"default": false,
"description": "Indicates if insight can be transferred to production.",
"title": "isTransferable",
"type": "boolean"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The LLM ID for OOTB metrics that use LLMs."
},
"llmIsActive": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is active.",
"title": "llmIsActive"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"modelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the model associated with `deploymentId`.",
"title": "modelId"
},
"modelPackageRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the registered model package associated with `deploymentId`.",
"title": "modelPackageRegisteredModelId"
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithID",
"type": "object"
},
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration associated with the insight configuration.",
"title": "moderationConfiguration"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the Nemo configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the ootb metric (if using an ootb metric).",
"title": "ootbMetricId"
},
"ootbMetricName": {
"anyOf": [
{
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The OOTB metric name."
},
"resultUnit": {
"anyOf": [
{
"description": "The unit of measurement associated with a metric.",
"enum": [
"s",
"ms",
"%"
],
"title": "MetricUnit",
"type": "string"
},
{
"type": "null"
}
],
"description": "The unit of measurement associated with the insight result."
},
"sidecarModelMetricMetadata": {
"anyOf": [
{
"description": "The metadata of a sidecar model metric.",
"properties": {
"expectedResponseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for expected response text input.",
"title": "expectedResponseColumnName"
},
"promptColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName"
},
"responseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for response text input.",
"title": "responseColumnName"
},
"targetColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName"
}
},
"required": [
"targetColumnName"
],
"title": "SidecarModelMetricMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata of the sidecar model metric (if using a sidecar model metric)."
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the sidecar model metric validation (if using a sidecar model metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) where insight is calculated at."
}
},
"required": [
"insightName",
"aggregationTypes"
],
"title": "InsightsConfigurationWithAdditionalData",
"type": "object"
},
"title": "insightsConfiguration",
"type": "array"
}
},
"required": [
"insightsConfiguration"
],
"title": "SupportedInsightsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Supported insights configuration successfully retrieved. | SupportedInsightsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/playgrounds/{playgroundId}/trace/¶
Retrieve the playground prompt traces for an existing playground.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground to retrieve prompt traces for. |
| offset | query | integer | false | Skip the specified number of values. |
| limit | query | integer | false | Retrieve only the specified number of values. |
Example responses¶
200 Response
{
"description": "Paginated list of playground prompt traces.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "API response object for a single playground prompt trace.",
"properties": {
"chatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat associated with the trace.",
"title": "chatId"
},
"chatName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the chat associated with the trace.",
"title": "chatName"
},
"chatPromptId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat prompt associated with the trace.",
"title": "chatPromptId"
},
"comparisonPromptId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the comparison prompts associated with the trace.",
"title": "comparisonPromptId"
},
"confidenceScores": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion for the prompt associated with the trace.",
"title": "confidenceScores"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset associated with the trace.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint associated with the trace.",
"title": "llmBlueprintId",
"type": "string"
},
"llmBlueprintName": {
"description": "The name of the LLM blueprint associated with the trace.",
"title": "llmBlueprintName",
"type": "string"
},
"llmLicense": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The usage license information for the LLM associated with the trace.",
"title": "llmLicense"
},
"llmName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the LLM associated with the trace.",
"title": "llmName"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "The settings of the LLM associated with the trace.",
"title": "llmSettings"
},
"llmVendor": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The vendor of the LLM associated with the trace.",
"title": "llmVendor"
},
"promptType": {
"anyOf": [
{
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
{
"type": "null"
}
],
"description": "The type of prompt, chat history awair or one time prompt."
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the prompt associated with the trace."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The completion text of the prompt associated with the trace.",
"title": "resultText"
},
"text": {
"description": "The text of the prompt associated with the trace.",
"title": "text",
"type": "string"
},
"timestamp": {
"description": "The timestamp of the trace (ISO 8601 formatted).",
"format": "date-time",
"title": "timestamp",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case associated with the trace.",
"title": "useCaseId",
"type": "string"
},
"user": {
"description": "DataRobot application user.",
"properties": {
"id": {
"description": "The ID of the user.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the user.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "DataRobotUser",
"type": "object"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database associated with the trace.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "The settings of the vector database associated with the trace."
},
"warning": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The warning message for the prompt associated with the trace.",
"title": "warning"
}
},
"required": [
"timestamp",
"user",
"chatPromptId",
"comparisonPromptId",
"useCaseId",
"llmBlueprintId",
"llmBlueprintName",
"llmName",
"llmVendor",
"llmLicense",
"llmSettings",
"chatName",
"chatId",
"vectorDatabaseId",
"vectorDatabaseSettings",
"resultMetadata",
"resultText",
"confidenceScores",
"text",
"executionStatus",
"promptType",
"evaluationDatasetConfigurationId",
"warning"
],
"title": "PromptTraceResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListTracesResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | ListTracesResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/playgrounds/{playgroundId}/trace/metadata/¶
Retrieve the prompt traces metadata for an existing playground.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground to retrieve prompt traces for. |
Example responses¶
200 Response
{
"description": "API response for prompt trace metadata retrieval request.",
"properties": {
"chats": {
"description": "The list of combined chat and comparison prompt chats available in trace.",
"items": {
"description": "Reference to a chat or comparison chat available in a trace.",
"properties": {
"id": {
"description": "The ID of the chat associated with the trace.",
"title": "id",
"type": "string"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name of the chat associated with the trace.",
"title": "name"
}
},
"required": [
"id",
"name"
],
"title": "TraceChat",
"type": "object"
},
"title": "chats",
"type": "array"
},
"users": {
"description": "The list of unique users available in the trace response.",
"items": {
"description": "DataRobot application user.",
"properties": {
"id": {
"description": "The ID of the user.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the user.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "DataRobotUser",
"type": "object"
},
"title": "users",
"type": "array"
}
},
"required": [
"users",
"chats"
],
"title": "TraceMetadataResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | TraceMetadataResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/genai/playgrounds/{playgroundId}/traceDatasets/¶
Export prompt traces for an existing playground as a Data Registry dataset.
Body parameter¶
{
"description": "The body of the Create Playground request.",
"properties": {
"excludeTracesWithWarnings": {
"default": true,
"description": "Whether to exclude traces with warnings.",
"title": "excludeTracesWithWarnings",
"type": "boolean"
}
},
"title": "CreateTraceDatasetRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| playgroundId | path | string | true | The ID of the playground to export the prompt traces for. |
| body | body | CreateTraceDatasetRequest | false | none |
Example responses¶
202 Response
{
"description": "API response for prompt traces export request.",
"properties": {
"aiCatalogId": {
"description": "The Data Registry dataset ID.",
"title": "aiCatalogId",
"type": "string"
}
},
"required": [
"aiCatalogId"
],
"title": "TraceDatasetResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Successful Response | TraceDatasetResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
PUT /api/v2/genai/playgrounds/{targetPlaygroundId}/supportedInsights/{sourcePlaygroundId}/¶
Copy supported insights between playgrounds.
Body parameter¶
{
"description": "The body of the \"Copy supported insights\" request.",
"properties": {
"addToExisting": {
"default": true,
"description": "If `true`, adds copied insights to existing insights in the target playground. If `false`, replaces insights in the target playground with copied insights.",
"title": "addToExisting",
"type": "boolean"
},
"withEvaluationDatasets": {
"default": false,
"description": "If `true` also copies source playground evaluation datasets to target playground.",
"title": "withEvaluationDatasets",
"type": "boolean"
}
},
"title": "CopySupportedInsightsRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| sourcePlaygroundId | path | string | true | The ID of the source playground to copy supported insights from. |
| targetPlaygroundId | path | string | true | The ID of the target playground to copy supported insights to. |
| body | body | CopySupportedInsightsRequest | true | none |
Example responses¶
422 Response
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 204 | No Content | Supported insights configuration successfully copied. | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/status/{statusId}/¶
Retrieve the execution status of a GenAI worker job.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| statusId | path | string(uuid) | true | The ID of the job to retrieve the status for. |
Example responses¶
200 Response
{
"anyOf": [
{
"description": "API response object for job execution status.",
"properties": {
"code": {
"description": "Possible job error codes. This enum exists for consistency with the DataRobot Status API.",
"enum": [
0,
1
],
"title": "JobErrorCode",
"type": "integer"
},
"created": {
"description": "The creation date of the job (ISO 8601 formatted).",
"format": "date-time",
"title": "created",
"type": "string"
},
"description": {
"default": "",
"description": "The description associated with the job.",
"title": "description",
"type": "string"
},
"message": {
"default": "",
"description": "The error message associated with the job.",
"title": "message",
"type": "string"
},
"status": {
"description": "Possible job states. Values match the DataRobot Status API.",
"enum": [
"INITIALIZED",
"RUNNING",
"COMPLETED",
"ERROR",
"ABORTED",
"EXPIRED"
],
"title": "JobExecutionState",
"type": "string"
},
"statusId": {
"description": "The ID of the job.",
"format": "uuid",
"title": "statusId",
"type": "string"
},
"statusType": {
"default": "",
"description": "The type of the status object.",
"title": "statusType",
"type": "string"
}
},
"required": [
"statusId",
"status",
"created",
"code"
],
"title": "StatusResponse",
"type": "object"
},
{
"type": "string"
}
],
"title": "Response Get Status Status Statusid Get"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | Inline |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Response Schema¶
Status Code 200
Response Get Status Status Statusid Get
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| Response Get Status Status Statusid Get | any | false | none |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | StatusResponse | false | API response object for job execution status. | |
| »» code | JobErrorCode | true | Possible job error codes. This enum exists for consistency with the DataRobot Status API. | |
| »» created | string(date-time) | true | The creation date of the job (ISO 8601 formatted). | |
| »» description | string | false | The description associated with the job. | |
| »» message | string | false | The error message associated with the job. | |
| »» status | JobExecutionState | true | Possible job states. Values match the DataRobot Status API. | |
| »» statusId | string(uuid) | true | The ID of the job. | |
| »» statusType | string | false | The type of the status object. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
Enumerated Values¶
| Property | Value |
|---|---|
| code | [0, 1] |
| status | [INITIALIZED, RUNNING, COMPLETED, ERROR, ABORTED, EXPIRED] |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/userLimits/llmApiCalls/¶
Retrieve the number of LLM API calls the user has made which count towards the usage limit.
Example responses¶
200 Response
{
"description": "API response object for retrieving user limit counters.",
"properties": {
"counter": {
"description": "The number of completed operations which count towards the usage limit.",
"title": "counter",
"type": "integer"
}
},
"required": [
"counter"
],
"title": "RetrieveUserLimitCounterResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | RetrieveUserLimitCounterResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/genai/userLimits/vectorDatabases/¶
Retrieve the number of vector databases the user has created which count towards the usage limit.
Example responses¶
200 Response
{
"description": "API response object for retrieving user limit counters.",
"properties": {
"counter": {
"description": "The number of completed operations which count towards the usage limit.",
"title": "counter",
"type": "integer"
}
},
"required": [
"counter"
],
"title": "RetrieveUserLimitCounterResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Successful Response | RetrieveUserLimitCounterResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
Schemas¶
AggregationType
{
"description": "The type of the metric aggregation.",
"enum": [
"average",
"percentYes",
"classPercentCoverage",
"ngramImportance",
"guardConditionPercentYes"
],
"title": "AggregationType",
"type": "string"
}
AggregationType
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| AggregationType | string | false | The type of the metric aggregation. |
Enumerated Values¶
| Property | Value |
|---|---|
| AggregationType | [average, percentYes, classPercentCoverage, ngramImportance, guardConditionPercentYes] |
BooleanSettingConstraints
{
"description": "Available constraints for boolean settings.",
"properties": {
"type": {
"const": "boolean",
"default": "boolean",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "BooleanSettingConstraints",
"type": "object"
}
BooleanSettingConstraints
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| type | string | false | The data type of the setting. |
CommonLLMSettings
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
}
CommonLLMSettings
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| maxCompletionLength | any | false | Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| systemPrompt | any | false | System prompt guides the style of the LLM response. It is a "universal" prompt, prepended to all individual prompts. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 500000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| temperature | any | false | Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| topP | any | false | Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
CopyInsightsRequest
{
"description": "The body of the Copy Insights request.",
"properties": {
"sourcePlaygroundId": {
"description": "The ID of the existing playground from where to copy insights.",
"title": "sourcePlaygroundId",
"type": "string"
},
"withEvaluationDatasets": {
"default": false,
"description": "If `true` also copies source playground evaluation datasets to target playground.",
"title": "withEvaluationDatasets",
"type": "boolean"
}
},
"required": [
"sourcePlaygroundId"
],
"title": "CopyInsightsRequest",
"type": "object"
}
CopyInsightsRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| sourcePlaygroundId | string | true | The ID of the existing playground from where to copy insights. | |
| withEvaluationDatasets | boolean | false | If true also copies source playground evaluation datasets to target playground. |
CopySupportedInsightsRequest
{
"description": "The body of the \"Copy supported insights\" request.",
"properties": {
"addToExisting": {
"default": true,
"description": "If `true`, adds copied insights to existing insights in the target playground. If `false`, replaces insights in the target playground with copied insights.",
"title": "addToExisting",
"type": "boolean"
},
"withEvaluationDatasets": {
"default": false,
"description": "If `true` also copies source playground evaluation datasets to target playground.",
"title": "withEvaluationDatasets",
"type": "boolean"
}
},
"title": "CopySupportedInsightsRequest",
"type": "object"
}
CopySupportedInsightsRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| addToExisting | boolean | false | If true, adds copied insights to existing insights in the target playground. If false, replaces insights in the target playground with copied insights. |
|
| withEvaluationDatasets | boolean | false | If true also copies source playground evaluation datasets to target playground. |
CreateCustomModelLLMValidationRequest
{
"description": "The body of the \"Validate custom model\" request.",
"properties": {
"chatModelId": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The model ID to specify when calling the OpenAI chat completion API of the deployment. If this parameter is specified, the deployment must support the OpenAI chat completion API.",
"title": "chatModelId"
},
"deploymentId": {
"description": "The ID of the custom model deployment.",
"title": "deploymentId",
"type": "string"
},
"modelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the model used in the deployment.",
"title": "modelId"
},
"name": {
"default": "Untitled",
"description": "The name to use for the validated custom model.",
"maxLength": 5000,
"title": "name",
"type": "string"
},
"predictionTimeout": {
"default": 300,
"description": "The timeout in seconds for the prediction when validating a custom model. Defaults to 300.",
"maximum": 600,
"minimum": 1,
"title": "predictionTimeout",
"type": "integer"
},
"promptColumnName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prompt text input. This value is used to call the Prediction API of the deployment. For LLM deployments that support the OpenAI chat completion API, it is recommended to specify `chatModelId` instead.",
"title": "promptColumnName"
},
"targetColumnName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prediction output. This value is used to call the Prediction API of the deployment. For LLM deployments that support the OpenAI chat completion API, it is recommended to specify `chatModelId` instead.",
"title": "targetColumnName"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case to associate with the validated custom model.",
"title": "useCaseId"
}
},
"required": [
"deploymentId"
],
"title": "CreateCustomModelLLMValidationRequest",
"type": "object"
}
CreateCustomModelLLMValidationRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatModelId | any | false | The model ID to specify when calling the OpenAI chat completion API of the deployment. If this parameter is specified, the deployment must support the OpenAI chat completion API. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| deploymentId | string | true | The ID of the custom model deployment. | |
| modelId | any | false | The ID of the model used in the deployment. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | false | maxLength: 5000 |
The name to use for the validated custom model. |
| predictionTimeout | integer | false | maximum: 600 minimum: 1 |
The timeout in seconds for the prediction when validating a custom model. Defaults to 300. |
| promptColumnName | any | false | The name of the column the custom model uses for prompt text input. This value is used to call the Prediction API of the deployment. For LLM deployments that support the OpenAI chat completion API, it is recommended to specify chatModelId instead. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| targetColumnName | any | false | The name of the column the custom model uses for prediction output. This value is used to call the Prediction API of the deployment. For LLM deployments that support the OpenAI chat completion API, it is recommended to specify chatModelId instead. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| useCaseId | any | false | The ID of the use case to associate with the validated custom model. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
CreateCustomModelVersionRequest
{
"description": "The body of the \"Create custom model version\" request.",
"properties": {
"insightsConfiguration": {
"default": [],
"description": "The configuration of insights to transfer to production.",
"items": {
"description": "The configuration of insights with extra data.",
"properties": {
"aggregationTypes": {
"anyOf": [
{
"items": {
"description": "The type of the metric aggregation.",
"enum": [
"average",
"percentYes",
"classPercentCoverage",
"ngramImportance",
"guardConditionPercentYes"
],
"title": "AggregationType",
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The aggregation types used in the insights configuration.",
"title": "aggregationTypes"
},
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom metric (if using a custom metric).",
"title": "customMetricId"
},
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation if using a custom model LLM for OOTB metrics.",
"title": "customModelLLMValidationId"
},
"deploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model deployment associated with the insight.",
"title": "deploymentId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the evaluation dataset configuration or sidecar model metric validation or OOTB metric.",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The error type associated with the insight error status and error message as an indicator of what fields needs to be edited if any.",
"title": "errorResolution"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The execution status of the evaluation dataset configuration."
},
"insightName": {
"description": "The name of the insight.",
"maxLength": 5000,
"minLength": 1,
"title": "insightName",
"type": "string"
},
"insightType": {
"anyOf": [
{
"description": "The type of insight.",
"enum": [
"Reference",
"Quality metric",
"Operational metric",
"Evaluation deployment",
"Custom metric",
"Nemo"
],
"title": "InsightTypes",
"type": "string"
},
{
"type": "null"
}
],
"description": "The type of the insight."
},
"isTransferable": {
"default": false,
"description": "Indicates if insight can be transferred to production.",
"title": "isTransferable",
"type": "boolean"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The LLM ID for OOTB metrics that use LLMs."
},
"llmIsActive": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is active.",
"title": "llmIsActive"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"modelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the model associated with `deploymentId`.",
"title": "modelId"
},
"modelPackageRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the registered model package associated with `deploymentId`.",
"title": "modelPackageRegisteredModelId"
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithID",
"type": "object"
},
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration associated with the insight configuration.",
"title": "moderationConfiguration"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the Nemo configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the ootb metric (if using an ootb metric).",
"title": "ootbMetricId"
},
"ootbMetricName": {
"anyOf": [
{
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The OOTB metric name."
},
"resultUnit": {
"anyOf": [
{
"description": "The unit of measurement associated with a metric.",
"enum": [
"s",
"ms",
"%"
],
"title": "MetricUnit",
"type": "string"
},
{
"type": "null"
}
],
"description": "The unit of measurement associated with the insight result."
},
"sidecarModelMetricMetadata": {
"anyOf": [
{
"description": "The metadata of a sidecar model metric.",
"properties": {
"expectedResponseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for expected response text input.",
"title": "expectedResponseColumnName"
},
"promptColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName"
},
"responseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for response text input.",
"title": "responseColumnName"
},
"targetColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName"
}
},
"required": [
"targetColumnName"
],
"title": "SidecarModelMetricMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata of the sidecar model metric (if using a sidecar model metric)."
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the sidecar model metric validation (if using a sidecar model metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) where insight is calculated at."
}
},
"required": [
"insightName",
"aggregationTypes"
],
"title": "InsightsConfigurationWithAdditionalData",
"type": "object"
},
"minItems": 0,
"title": "insightsConfiguration",
"type": "array"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint to use for the custom model version.",
"title": "llmBlueprintId",
"type": "string"
},
"llmTestConfigurationIds": {
"default": [],
"description": "The IDs of the LLM test configurations to execute.",
"items": {
"type": "string"
},
"maxItems": 100,
"title": "llmTestConfigurationIds",
"type": "array"
},
"promptColumnName": {
"default": "promptText",
"description": "The name of the column to use for prompt text input in the custom model.",
"maxLength": 5000,
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"default": "resultText",
"description": "The name of the column to use for prediction output in the custom model.",
"maxLength": 5000,
"title": "targetColumnName",
"type": "string"
}
},
"required": [
"llmBlueprintId"
],
"title": "CreateCustomModelVersionRequest",
"type": "object"
}
CreateCustomModelVersionRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| insightsConfiguration | [InsightsConfigurationWithAdditionalData] | false | The configuration of insights to transfer to production. | |
| llmBlueprintId | string | true | The ID of the LLM blueprint to use for the custom model version. | |
| llmTestConfigurationIds | [string] | false | maxItems: 100 |
The IDs of the LLM test configurations to execute. |
| promptColumnName | string | false | maxLength: 5000 |
The name of the column to use for prompt text input in the custom model. |
| targetColumnName | string | false | maxLength: 5000 |
The name of the column to use for prediction output in the custom model. |
CreateCustomModelVersionResponse
{
"description": "API response object for the \"Create custom model version\" request.",
"properties": {
"customModelId": {
"description": "The ID of the created custom model.",
"title": "customModelId",
"type": "string"
}
},
"required": [
"customModelId"
],
"title": "CreateCustomModelVersionResponse",
"type": "object"
}
CreateCustomModelVersionResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customModelId | string | true | The ID of the created custom model. |
CreateFromChatPromptRequest
{
"description": "The body of the Create LLM Blueprint from a ChatPrompt request.",
"properties": {
"chatPromptId": {
"description": "The ID of an existing chat prompt to copy the LLM and vector database settings from.",
"title": "chatPromptId",
"type": "string"
},
"description": {
"default": "",
"description": "The description of the new LLM blueprint.",
"maxLength": 5000,
"title": "description",
"type": "string"
},
"name": {
"description": "The name of the new LLM blueprint.",
"maxLength": 5000,
"title": "name",
"type": "string"
}
},
"required": [
"name",
"chatPromptId"
],
"title": "CreateFromChatPromptRequest",
"type": "object"
}
CreateFromChatPromptRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatPromptId | string | true | The ID of an existing chat prompt to copy the LLM and vector database settings from. | |
| description | string | false | maxLength: 5000 |
The description of the new LLM blueprint. |
| name | string | true | maxLength: 5000 |
The name of the new LLM blueprint. |
CreateFromLLMBlueprintRequest
{
"description": "The body of the Create LLM Blueprint from an LLM Blueprint request.",
"properties": {
"description": {
"default": "",
"description": "The description of the new LLM blueprint.",
"maxLength": 5000,
"title": "description",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of an existing LLM blueprint to copy the LLM and vector database settings from.",
"title": "llmBlueprintId",
"type": "string"
},
"name": {
"description": "The name of the new LLM blueprint.",
"maxLength": 5000,
"title": "name",
"type": "string"
}
},
"required": [
"name",
"llmBlueprintId"
],
"title": "CreateFromLLMBlueprintRequest",
"type": "object"
}
CreateFromLLMBlueprintRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| description | string | false | maxLength: 5000 |
The description of the new LLM blueprint. |
| llmBlueprintId | string | true | The ID of an existing LLM blueprint to copy the LLM and vector database settings from. | |
| name | string | true | maxLength: 5000 |
The name of the new LLM blueprint. |
CreateLLMBlueprintRequest
{
"description": "The body of the Create LLM Blueprint request.",
"properties": {
"description": {
"default": "",
"description": "The description of the LLM blueprint.",
"maxLength": 5000,
"title": "description",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM selected for this LLM blueprint."
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"name": {
"description": "The name of the LLM blueprint.",
"maxLength": 5000,
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground to link this LLM blueprint to.",
"title": "playgroundId",
"type": "string"
},
"promptType": {
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Specifies the vector database retrieval settings in LLM blueprint API requests.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettingsRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
}
},
"required": [
"playgroundId",
"name"
],
"title": "CreateLLMBlueprintRequest",
"type": "object"
}
CreateLLMBlueprintRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| description | string | false | maxLength: 5000 |
The description of the LLM blueprint. |
| llmId | any | false | The ID of the LLM selected for this LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | LanguageModelTypeId | false | The ID that defines the type of the LLM. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmSettings | any | false | A key/value dictionary of LLM settings. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CommonLLMSettings | false | The settings that are available for all non-custom LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CustomModelLLMSettings | false | The settings that are available for custom model LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | true | maxLength: 5000 |
The name of the LLM blueprint. |
| playgroundId | string | true | The ID of the playground to link this LLM blueprint to. | |
| promptType | PromptType | false | Specifies whether chat history is submitted as context to the user prompt. | |
| vectorDatabaseId | any | false | The ID of the vector database linked to this LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseSettings | any | false | A key/value dictionary of vector database settings. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | VectorDatabaseSettingsRequest | false | Specifies the vector database retrieval settings in LLM blueprint API requests. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
CreateOOTBMetricConfigurationsRequest
{
"description": "The body of the \"Create OOTB metric configurations\" request.",
"properties": {
"ootbMetricConfigurations": {
"description": "The list of OOTB metrics to use.",
"items": {
"description": "API request object for a single OOTB metric configuration.",
"properties": {
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation (if using a custom model LLM).",
"title": "customModelLLMValidationId"
},
"customOotbMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The custom OOTB metric name to be associated with the OOTB metric. Will default to OOTB metric name if not defined.",
"title": "customOotbMetricName"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM to use for `correctness` and `faithfulness` metrics."
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration to be associated with the OOTB metric."
},
"ootbMetricName": {
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
}
},
"required": [
"ootbMetricName"
],
"title": "OOTBMetricConfigurationRequest",
"type": "object"
},
"title": "ootbMetricConfigurations",
"type": "array"
}
},
"required": [
"ootbMetricConfigurations"
],
"title": "CreateOOTBMetricConfigurationsRequest",
"type": "object"
}
CreateOOTBMetricConfigurationsRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ootbMetricConfigurations | [OOTBMetricConfigurationRequest] | true | The list of OOTB metrics to use. |
CreatePlaygroundRequest
{
"description": "The body of the Create Playground request.",
"properties": {
"copyInsights": {
"anyOf": [
{
"description": "The body of the Copy Insights request.",
"properties": {
"sourcePlaygroundId": {
"description": "The ID of the existing playground from where to copy insights.",
"title": "sourcePlaygroundId",
"type": "string"
},
"withEvaluationDatasets": {
"default": false,
"description": "If `true` also copies source playground evaluation datasets to target playground.",
"title": "withEvaluationDatasets",
"type": "boolean"
}
},
"required": [
"sourcePlaygroundId"
],
"title": "CopyInsightsRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "If present, copy insights from source playground to the created playground."
},
"description": {
"description": "The description of the playground.",
"maxLength": 5000,
"title": "description",
"type": "string"
},
"name": {
"description": "The name of the playground.",
"maxLength": 5000,
"title": "name",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case to link the playground to.",
"title": "useCaseId",
"type": "string"
}
},
"required": [
"useCaseId",
"name",
"description"
],
"title": "CreatePlaygroundRequest",
"type": "object"
}
CreatePlaygroundRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| copyInsights | any | false | If present, copy insights from source playground to the created playground. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CopyInsightsRequest | false | The body of the Copy Insights request. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| description | string | true | maxLength: 5000 |
The description of the playground. |
| name | string | true | maxLength: 5000 |
The name of the playground. |
| useCaseId | string | true | The ID of the use case to link the playground to. |
CreateTraceDatasetRequest
{
"description": "The body of the Create Playground request.",
"properties": {
"excludeTracesWithWarnings": {
"default": true,
"description": "Whether to exclude traces with warnings.",
"title": "excludeTracesWithWarnings",
"type": "boolean"
}
},
"title": "CreateTraceDatasetRequest",
"type": "object"
}
CreateTraceDatasetRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| excludeTracesWithWarnings | boolean | false | Whether to exclude traces with warnings. |
CustomModelLLMSettings
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
}
CustomModelLLMSettings
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| externalLlmContextSize | any | false | The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | maximum: 128000 minimum: 128 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| systemPrompt | any | false | System prompt guides the style of the LLM response. It is a "universal" prompt, prepended to all individual prompts. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 500000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| validationId | any | false | The validation ID of the custom model LLM. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
CustomModelLLMValidationResponse
{
"description": "API response object for a single custom model LLM validation.",
"properties": {
"chatModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The model ID to specify when calling the OpenAI chat completion API of the deployment.",
"title": "chatModelId"
},
"creationDate": {
"description": "The creation date of the custom model validation (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"deploymentAccessData": {
"anyOf": [
{
"description": "Add authorization_header to avoid breaking change to API.",
"properties": {
"authorizationHeader": {
"default": "[REDACTED]",
"description": "The `Authorization` header to use for the deployment.",
"title": "authorizationHeader",
"type": "string"
},
"chatApiUrl": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the deployment's chat API.",
"title": "chatApiUrl"
},
"datarobotKey": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The server key associated with the prediction API.",
"title": "datarobotKey"
},
"inputType": {
"description": "The format of the input data submitted to a DataRobot deployment.",
"enum": [
"CSV",
"JSON"
],
"title": "DeploymentInputType",
"type": "string"
},
"modelType": {
"description": "The type of the target output a DataRobot deployment produces.",
"enum": [
"TEXT_GENERATION",
"VECTOR_DATABASE",
"UNSTRUCTURED",
"REGRESSION",
"MULTICLASS",
"BINARY",
"NOT_SUPPORTED"
],
"title": "SupportedDeploymentType",
"type": "string"
},
"predictionApiUrl": {
"description": "The URL of the deployment's prediction API.",
"title": "predictionApiUrl",
"type": "string"
}
},
"required": [
"predictionApiUrl",
"datarobotKey",
"inputType",
"modelType"
],
"title": "DeploymentAccessData",
"type": "object"
},
{
"type": "null"
}
],
"description": "The parameters used for accessing the deployment."
},
"deploymentId": {
"description": "The ID of the custom model deployment.",
"title": "deploymentId",
"type": "string"
},
"deploymentName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the custom model deployment.",
"title": "deploymentName"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the validation error (if the validation failed).",
"title": "errorMessage"
},
"id": {
"description": "The ID of the custom model validation.",
"title": "id",
"type": "string"
},
"modelId": {
"description": "The ID of the model used in the deployment.",
"title": "modelId",
"type": "string"
},
"name": {
"description": "The name of the validated custom model.",
"title": "name",
"type": "string"
},
"predictionTimeout": {
"description": "The timeout in seconds for the prediction API used in this custom model validation.",
"title": "predictionTimeout",
"type": "integer"
},
"promptColumnName": {
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName",
"type": "string"
},
"tenantId": {
"description": "The ID of the tenant the custom model validation belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case associated with the validated custom model.",
"title": "useCaseId"
},
"userId": {
"description": "The ID of the user that created this custom model validation.",
"title": "userId",
"type": "string"
},
"userName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the user that created this custom model validation.",
"title": "userName"
},
"validationStatus": {
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
}
},
"required": [
"id",
"deploymentId",
"targetColumnName",
"validationStatus",
"modelId",
"deploymentAccessData",
"tenantId",
"name",
"useCaseId",
"creationDate",
"userId",
"predictionTimeout",
"promptColumnName"
],
"title": "CustomModelLLMValidationResponse",
"type": "object"
}
CustomModelLLMValidationResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatModelId | any | false | The model ID to specify when calling the OpenAI chat completion API of the deployment. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| creationDate | string(date-time) | true | The creation date of the custom model validation (ISO 8601 formatted). | |
| deploymentAccessData | any | true | The parameters used for accessing the deployment. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | DeploymentAccessData | false | Add authorization_header to avoid breaking change to API. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| deploymentId | string | true | The ID of the custom model deployment. | |
| deploymentName | any | false | The name of the custom model deployment. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| errorMessage | any | false | The error message associated with the validation error (if the validation failed). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| id | string | true | The ID of the custom model validation. | |
| modelId | string | true | The ID of the model used in the deployment. | |
| name | string | true | The name of the validated custom model. | |
| predictionTimeout | integer | true | The timeout in seconds for the prediction API used in this custom model validation. | |
| promptColumnName | string | true | The name of the column the custom model uses for prompt text input. | |
| targetColumnName | string | true | The name of the column the custom model uses for prediction output. | |
| tenantId | string(uuid4) | true | The ID of the tenant the custom model validation belongs to. | |
| useCaseId | any | true | The ID of the use case associated with the validated custom model. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| userId | string | true | The ID of the user that created this custom model validation. | |
| userName | any | false | The name of the user that created this custom model validation. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| validationStatus | CustomModelValidationStatus | true | The status of the custom model validation. |
CustomModelValidationStatus
{
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
}
CustomModelValidationStatus
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| CustomModelValidationStatus | string | false | Status of custom model validation. |
Enumerated Values¶
| Property | Value |
|---|---|
| CustomModelValidationStatus | [TESTING, PASSED, FAILED] |
DataRobotUser
{
"description": "DataRobot application user.",
"properties": {
"id": {
"description": "The ID of the user.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the user.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "DataRobotUser",
"type": "object"
}
DataRobotUser
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| id | string | true | The ID of the user. | |
| name | string | true | The name of the user. |
DeploymentAccessData
{
"description": "Add authorization_header to avoid breaking change to API.",
"properties": {
"authorizationHeader": {
"default": "[REDACTED]",
"description": "The `Authorization` header to use for the deployment.",
"title": "authorizationHeader",
"type": "string"
},
"chatApiUrl": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the deployment's chat API.",
"title": "chatApiUrl"
},
"datarobotKey": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The server key associated with the prediction API.",
"title": "datarobotKey"
},
"inputType": {
"description": "The format of the input data submitted to a DataRobot deployment.",
"enum": [
"CSV",
"JSON"
],
"title": "DeploymentInputType",
"type": "string"
},
"modelType": {
"description": "The type of the target output a DataRobot deployment produces.",
"enum": [
"TEXT_GENERATION",
"VECTOR_DATABASE",
"UNSTRUCTURED",
"REGRESSION",
"MULTICLASS",
"BINARY",
"NOT_SUPPORTED"
],
"title": "SupportedDeploymentType",
"type": "string"
},
"predictionApiUrl": {
"description": "The URL of the deployment's prediction API.",
"title": "predictionApiUrl",
"type": "string"
}
},
"required": [
"predictionApiUrl",
"datarobotKey",
"inputType",
"modelType"
],
"title": "DeploymentAccessData",
"type": "object"
}
DeploymentAccessData
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| authorizationHeader | string | false | The Authorization header to use for the deployment. |
|
| chatApiUrl | any | false | The URL of the deployment's chat API. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| datarobotKey | any | true | The server key associated with the prediction API. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| inputType | DeploymentInputType | true | The format of the input data. | |
| modelType | SupportedDeploymentType | true | The type of the target output the deployment produces. | |
| predictionApiUrl | string | true | The URL of the deployment's prediction API. |
DeploymentInputType
{
"description": "The format of the input data submitted to a DataRobot deployment.",
"enum": [
"CSV",
"JSON"
],
"title": "DeploymentInputType",
"type": "string"
}
DeploymentInputType
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| DeploymentInputType | string | false | The format of the input data submitted to a DataRobot deployment. |
Enumerated Values¶
| Property | Value |
|---|---|
| DeploymentInputType | [CSV, JSON] |
EditCustomModelValidationRequest
{
"description": "The body of the \"Edit custom model validation\" request.",
"properties": {
"chatModelId": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The model ID to specify when calling the OpenAI chat completion API of the deployment. If this parameter is specified, the deployment must support the OpenAI chat completion API.",
"title": "chatModelId"
},
"deploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the ID of the deployment associated with this custom model validation.",
"title": "deploymentId"
},
"modelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the ID of the model associated with this custom model validation.",
"title": "modelId"
},
"name": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, renames the custom model validation to this value.",
"title": "name"
},
"predictionTimeout": {
"anyOf": [
{
"maximum": 600,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "If specified, sets the timeout in seconds for the prediction when validating a custom model.",
"title": "predictionTimeout"
},
"promptColumnName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the name of the column that will be used to format the prompt text input for the custom model deployment.",
"title": "promptColumnName"
},
"targetColumnName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the name of the column that will be used to extract the prediction response from the custom model deployment.",
"title": "targetColumnName"
}
},
"title": "EditCustomModelValidationRequest",
"type": "object"
}
EditCustomModelValidationRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatModelId | any | false | The model ID to specify when calling the OpenAI chat completion API of the deployment. If this parameter is specified, the deployment must support the OpenAI chat completion API. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| deploymentId | any | false | If specified, changes the ID of the deployment associated with this custom model validation. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| modelId | any | false | If specified, changes the ID of the model associated with this custom model validation. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | any | false | If specified, renames the custom model validation to this value. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 minLength: 1 minLength: 1 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| predictionTimeout | any | false | If specified, sets the timeout in seconds for the prediction when validating a custom model. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | maximum: 600 minimum: 1 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptColumnName | any | false | If specified, changes the name of the column that will be used to format the prompt text input for the custom model deployment. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| targetColumnName | any | false | If specified, changes the name of the column that will be used to extract the prediction response from the custom model deployment. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
EditPlaygroundRequest
{
"description": "The body of the Edit Playground request.",
"properties": {
"description": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, updates the playground description to this value.",
"title": "description"
},
"name": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, renames the playground to this value.",
"title": "name"
}
},
"title": "EditPlaygroundRequest",
"type": "object"
}
EditPlaygroundRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| description | any | false | If specified, updates the playground description to this value. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | any | false | If specified, renames the playground to this value. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
ExecutionStatus
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
}
ExecutionStatus
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ExecutionStatus | string | false | Job and entity execution status. |
Enumerated Values¶
| Property | Value |
|---|---|
| ExecutionStatus | [NEW, RUNNING, COMPLETED, REQUIRES_USER_INPUT, SKIPPED, ERROR] |
FeedbackResult
{
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
}
FeedbackResult
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| negativeUserIds | [string] | false | The list of user IDs whose feedback is negative. | |
| positiveUserIds | [string] | false | The list of user IDs whose feedback is positive. |
FloatSettingConstraints
{
"description": "Available constraints for float settings.",
"properties": {
"maxValue": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The maximum value of the setting (inclusive).",
"title": "maxValue"
},
"minValue": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The minimum value of the setting (inclusive).",
"title": "minValue"
},
"type": {
"const": "float",
"default": "float",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "FloatSettingConstraints",
"type": "object"
}
FloatSettingConstraints
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| maxValue | any | false | The maximum value of the setting (inclusive). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| minValue | any | false | The minimum value of the setting (inclusive). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| type | string | false | The data type of the setting. |
GuardCondition
{
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
}
GuardCondition
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| comparand | any | true | The comparand(s) used in the guard condition. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | boolean | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [string] | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| comparator | GuardConditionComparator | true | The comparator used in the guard condition. |
GuardConditionComparator
{
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
GuardConditionComparator
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| GuardConditionComparator | string | false | The comparator used in a guard condition. |
Enumerated Values¶
| Property | Value |
|---|---|
| GuardConditionComparator | [greaterThan, lessThan, equals, notEquals, is, isNot, matches, doesNotMatch, contains, doesNotContain] |
HTTPValidationErrorResponse
{
"properties": {
"detail": {
"items": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
},
"title": "detail",
"type": "array"
}
},
"title": "HTTPValidationErrorResponse",
"type": "object"
}
HTTPValidationErrorResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| detail | [ValidationError] | false | none |
InsightErrorResolution
{
"description": "Error type linking directly to the field name that is related to the error.",
"enum": [
"ootbMetricName",
"intervention",
"guardCondition",
"sidecarOverall",
"sidecarRevalidate",
"sidecarDeploymentId",
"sidecarInputColumnName",
"sidecarOutputColumnName",
"promptPipelineFiles",
"promptPipelineTemplateId",
"responsePipelineFiles",
"responsePipelineTemplateId"
],
"title": "InsightErrorResolution",
"type": "string"
}
InsightErrorResolution
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| InsightErrorResolution | string | false | Error type linking directly to the field name that is related to the error. |
Enumerated Values¶
| Property | Value |
|---|---|
| InsightErrorResolution | [ootbMetricName, intervention, guardCondition, sidecarOverall, sidecarRevalidate, sidecarDeploymentId, sidecarInputColumnName, sidecarOutputColumnName, promptPipelineFiles, promptPipelineTemplateId, responsePipelineFiles, responsePipelineTemplateId] |
InsightTypes
{
"description": "The type of insight.",
"enum": [
"Reference",
"Quality metric",
"Operational metric",
"Evaluation deployment",
"Custom metric",
"Nemo"
],
"title": "InsightTypes",
"type": "string"
}
InsightTypes
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| InsightTypes | string | false | The type of insight. |
Enumerated Values¶
| Property | Value |
|---|---|
| InsightTypes | [Reference, Quality metric, Operational metric, Evaluation deployment, Custom metric, Nemo] |
InsightsConfigurationWithAdditionalData
{
"description": "The configuration of insights with extra data.",
"properties": {
"aggregationTypes": {
"anyOf": [
{
"items": {
"description": "The type of the metric aggregation.",
"enum": [
"average",
"percentYes",
"classPercentCoverage",
"ngramImportance",
"guardConditionPercentYes"
],
"title": "AggregationType",
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The aggregation types used in the insights configuration.",
"title": "aggregationTypes"
},
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom metric (if using a custom metric).",
"title": "customMetricId"
},
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation if using a custom model LLM for OOTB metrics.",
"title": "customModelLLMValidationId"
},
"deploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model deployment associated with the insight.",
"title": "deploymentId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the evaluation dataset configuration or sidecar model metric validation or OOTB metric.",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The error type associated with the insight error status and error message as an indicator of what fields needs to be edited if any.",
"title": "errorResolution"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The execution status of the evaluation dataset configuration."
},
"insightName": {
"description": "The name of the insight.",
"maxLength": 5000,
"minLength": 1,
"title": "insightName",
"type": "string"
},
"insightType": {
"anyOf": [
{
"description": "The type of insight.",
"enum": [
"Reference",
"Quality metric",
"Operational metric",
"Evaluation deployment",
"Custom metric",
"Nemo"
],
"title": "InsightTypes",
"type": "string"
},
{
"type": "null"
}
],
"description": "The type of the insight."
},
"isTransferable": {
"default": false,
"description": "Indicates if insight can be transferred to production.",
"title": "isTransferable",
"type": "boolean"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The LLM ID for OOTB metrics that use LLMs."
},
"llmIsActive": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is active.",
"title": "llmIsActive"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"modelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the model associated with `deploymentId`.",
"title": "modelId"
},
"modelPackageRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the registered model package associated with `deploymentId`.",
"title": "modelPackageRegisteredModelId"
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithID",
"type": "object"
},
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration associated with the insight configuration.",
"title": "moderationConfiguration"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the Nemo configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the ootb metric (if using an ootb metric).",
"title": "ootbMetricId"
},
"ootbMetricName": {
"anyOf": [
{
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The OOTB metric name."
},
"resultUnit": {
"anyOf": [
{
"description": "The unit of measurement associated with a metric.",
"enum": [
"s",
"ms",
"%"
],
"title": "MetricUnit",
"type": "string"
},
{
"type": "null"
}
],
"description": "The unit of measurement associated with the insight result."
},
"sidecarModelMetricMetadata": {
"anyOf": [
{
"description": "The metadata of a sidecar model metric.",
"properties": {
"expectedResponseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for expected response text input.",
"title": "expectedResponseColumnName"
},
"promptColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName"
},
"responseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for response text input.",
"title": "responseColumnName"
},
"targetColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName"
}
},
"required": [
"targetColumnName"
],
"title": "SidecarModelMetricMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata of the sidecar model metric (if using a sidecar model metric)."
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the sidecar model metric validation (if using a sidecar model metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) where insight is calculated at."
}
},
"required": [
"insightName",
"aggregationTypes"
],
"title": "InsightsConfigurationWithAdditionalData",
"type": "object"
}
InsightsConfigurationWithAdditionalData
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| aggregationTypes | any | true | The aggregation types used in the insights configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [AggregationType] | false | [The type of the metric aggregation.] |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| costConfigurationId | any | false | The ID of the cost configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customMetricId | any | false | The ID of the custom metric (if using a custom metric). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customModelLLMValidationId | any | false | The ID of the custom model LLM validation if using a custom model LLM for OOTB metrics. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| deploymentId | any | false | The ID of the custom model deployment associated with the insight. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| errorMessage | any | false | The error message associated with the evaluation dataset configuration or sidecar model metric validation or OOTB metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| errorResolution | any | false | The error type associated with the insight error status and error message as an indicator of what fields needs to be edited if any. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [string] | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| evaluationDatasetConfigurationId | any | false | The ID of the evaluation dataset configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| executionStatus | any | false | The execution status of the evaluation dataset configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ExecutionStatus | false | Job and entity execution status. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| insightName | string | true | maxLength: 5000 minLength: 1 minLength: 1 |
The name of the insight. |
| insightType | any | false | The type of the insight. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | InsightTypes | false | The type of insight. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| isTransferable | boolean | false | Indicates if insight can be transferred to production. | |
| llmId | any | false | The LLM ID for OOTB metrics that use LLMs. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | LanguageModelTypeId | false | The ID that defines the type of the LLM. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmIsActive | any | false | Whether the LLM is active. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | boolean | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmIsDeprecated | any | false | Whether the LLM is deprecated and will be removed in a future release. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | boolean | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| modelId | any | false | The ID of the model associated with deploymentId. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| modelPackageRegisteredModelId | any | false | The ID of the registered model package associated with deploymentId. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| moderationConfiguration | any | false | The moderation configuration associated with the insight configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ModerationConfigurationWithID | false | Moderation Configuration associated with an insight. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ModerationConfigurationWithoutID | false | Moderation Configuration associated with an insight. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| nemoMetricId | any | false | The ID of the Nemo configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ootbMetricId | any | false | The ID of the ootb metric (if using an ootb metric). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ootbMetricName | any | false | The OOTB metric name. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | OOTBMetricInsightNames | false | The Out-Of-The-Box metric name that can be used in the playground. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| resultUnit | any | false | The unit of measurement associated with the insight result. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | MetricUnit | false | The unit of measurement associated with a metric. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| sidecarModelMetricMetadata | any | false | The metadata of the sidecar model metric (if using a sidecar model metric). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | SidecarModelMetricMetadata | false | The metadata of a sidecar model metric. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| sidecarModelMetricValidationId | any | false | The ID of the sidecar model metric validation (if using a sidecar model metric). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| stage | any | false | The stage (prompt or response) where insight is calculated at. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | PipelineStage | false | Enum that describes at which stage the metric may be calculated. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
IntegerSettingConstraints
{
"description": "Available constraints for integer settings.",
"properties": {
"maxValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the setting (inclusive).",
"title": "maxValue"
},
"minValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the setting (inclusive).",
"title": "minValue"
},
"type": {
"const": "integer",
"default": "integer",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "IntegerSettingConstraints",
"type": "object"
}
IntegerSettingConstraints
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| maxValue | any | false | The maximum value of the setting (inclusive). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| minValue | any | false | The minimum value of the setting (inclusive). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| type | string | false | The data type of the setting. |
Intervention
{
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
Intervention
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| action | ModerationAction | true | The intervention strategy. | |
| message | string | true | minLength: 1 minLength: 1 |
The intervention message to replace the prediction when a guard condition is satisfied. |
JobErrorCode
{
"description": "Possible job error codes. This enum exists for consistency with the DataRobot Status API.",
"enum": [
0,
1
],
"title": "JobErrorCode",
"type": "integer"
}
JobErrorCode
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| JobErrorCode | integer | false | Possible job error codes. This enum exists for consistency with the DataRobot Status API. |
Enumerated Values¶
| Property | Value |
|---|---|
| JobErrorCode | [0, 1] |
JobExecutionState
{
"description": "Possible job states. Values match the DataRobot Status API.",
"enum": [
"INITIALIZED",
"RUNNING",
"COMPLETED",
"ERROR",
"ABORTED",
"EXPIRED"
],
"title": "JobExecutionState",
"type": "string"
}
JobExecutionState
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| JobExecutionState | string | false | Possible job states. Values match the DataRobot Status API. |
Enumerated Values¶
| Property | Value |
|---|---|
| JobExecutionState | [INITIALIZED, RUNNING, COMPLETED, ERROR, ABORTED, EXPIRED] |
LLMBlueprintResponse
{
"description": "API response object for a single LLM blueprint.",
"properties": {
"creationDate": {
"description": "The creation date of the LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this LLM blueprint.",
"title": "creationUserId",
"type": "string"
},
"creationUserName": {
"description": "The name of the user who created this LLM blueprint.",
"title": "creationUserName",
"type": "string"
},
"customModelLLMErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorMessage"
},
"customModelLLMErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorResolution"
},
"customModelLLMValidationStatus": {
"anyOf": [
{
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation status of the custom model LLM (if using a custom model LLM)."
},
"description": {
"description": "The description of the LLM blueprint.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the LLM blueprint.",
"title": "id",
"type": "string"
},
"isActive": {
"description": "Whether the LLM specified in this blueprint is active in the current environment.",
"title": "isActive",
"type": "boolean"
},
"isDeprecated": {
"description": "Whether the LLM specified in this blueprint is deprecated.",
"title": "isDeprecated",
"type": "boolean"
},
"isSaved": {
"description": "If false, then this LLM blueprint is a draft and its settings can be changed. If true, then its settings are frozen and cannot be changed anymore.",
"title": "isSaved",
"type": "boolean"
},
"isStarred": {
"description": "Specifies whether this LLM blueprint is starred.",
"title": "isStarred",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this LLM blueprint.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM selected for this LLM blueprint."
},
"llmName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the LLM used by this LLM blueprint.",
"title": "llmName"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"name": {
"description": "The name of the LLM blueprint.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground this LLM blueprint belongs to.",
"title": "playgroundId",
"type": "string"
},
"promptType": {
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
"retirementDate": {
"anyOf": [
{
"format": "date",
"type": "string"
},
{
"type": "null"
}
],
"description": "When the LLM is expected to be retired and no longer available for submitting new prompts.",
"title": "retirementDate"
},
"vectorDatabaseErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the vector database associated with this LLM.",
"title": "vectorDatabaseErrorMessage"
},
"vectorDatabaseErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseErrorResolution"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family associated with this LLM blueprint.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseName"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
},
"vectorDatabaseStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database associated with this LLM blueprint."
}
},
"required": [
"id",
"name",
"description",
"isSaved",
"isStarred",
"promptType",
"playgroundId",
"llmName",
"creationDate",
"creationUserId",
"creationUserName",
"lastUpdateDate",
"lastUpdateUserId",
"vectorDatabaseName",
"vectorDatabaseStatus",
"vectorDatabaseErrorMessage",
"vectorDatabaseErrorResolution",
"customModelLLMValidationStatus",
"customModelLLMErrorMessage",
"customModelLLMErrorResolution",
"vectorDatabaseFamilyId",
"isActive",
"isDeprecated"
],
"title": "LLMBlueprintResponse",
"type": "object"
}
LLMBlueprintResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| creationDate | string(date-time) | true | The creation date of the LLM blueprint (ISO 8601 formatted). | |
| creationUserId | string | true | The ID of the user that created this LLM blueprint. | |
| creationUserName | string | true | The name of the user who created this LLM blueprint. | |
| customModelLLMErrorMessage | any | true | The error message of the custom model LLM (if using a custom model LLM). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customModelLLMErrorResolution | any | true | The suggested error resolution for the custom model LLM (if using a custom model LLM). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customModelLLMValidationStatus | any | true | The validation status of the custom model LLM (if using a custom model LLM). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CustomModelValidationStatus | false | Status of custom model validation. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| description | string | true | The description of the LLM blueprint. | |
| id | string | true | The ID of the LLM blueprint. | |
| isActive | boolean | true | Whether the LLM specified in this blueprint is active in the current environment. | |
| isDeprecated | boolean | true | Whether the LLM specified in this blueprint is deprecated. | |
| isSaved | boolean | true | If false, then this LLM blueprint is a draft and its settings can be changed. If true, then its settings are frozen and cannot be changed anymore. | |
| isStarred | boolean | true | Specifies whether this LLM blueprint is starred. | |
| lastUpdateDate | string(date-time) | true | The date of the most recent update of this LLM blueprint (ISO 8601 formatted). | |
| lastUpdateUserId | string | true | The ID of the user that made the most recent update to this LLM blueprint. | |
| llmId | any | false | The ID of the LLM selected for this LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | LanguageModelTypeId | false | The ID that defines the type of the LLM. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmName | any | true | The name of the LLM used by this LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmSettings | any | false | A key/value dictionary of LLM settings. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CommonLLMSettings | false | The settings that are available for all non-custom LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CustomModelLLMSettings | false | The settings that are available for custom model LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | true | The name of the LLM blueprint. | |
| playgroundId | string | true | The ID of the playground this LLM blueprint belongs to. | |
| promptType | PromptType | true | Specifies whether the chat history is submitted as context to the user prompt. | |
| retirementDate | any | false | When the LLM is expected to be retired and no longer available for submitting new prompts. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string(date) | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseErrorMessage | any | true | The error message of the vector database associated with this LLM. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseErrorResolution | any | true | The suggested error resolution for the vector database associated with this LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseFamilyId | any | true | The ID of the vector database family associated with this LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseId | any | false | The ID of the vector database linked to this LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseName | any | true | The name of the vector database associated with this LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseSettings | any | false | A key/value dictionary of vector database settings. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | VectorDatabaseSettings | false | Vector database retrieval settings. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseStatus | any | true | The creation status of the vector database associated with this LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ExecutionStatus | false | Job and entity execution status. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
LLMCreator
{
"description": "The creator of the LLM.",
"enum": [
"OpenAI",
"Amazon",
"Google",
"Anthropic",
"Unknown"
],
"title": "LLMCreator",
"type": "string"
}
LLMCreator
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| LLMCreator | string | false | The creator of the LLM. |
Enumerated Values¶
| Property | Value |
|---|---|
| LLMCreator | [OpenAI, Amazon, Google, Anthropic, Unknown] |
LLMReference
{
"description": "A reference link for an LLM.",
"properties": {
"name": {
"description": "Description of the reference document.",
"title": "name",
"type": "string"
},
"url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "URL of the reference document.",
"title": "url"
}
},
"required": [
"name",
"url"
],
"title": "LLMReference",
"type": "object"
}
LLMReference
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | true | Description of the reference document. | |
| url | any | true | URL of the reference document. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
LLMSettingDefinition
{
"description": "Metadata describing a single setting.",
"properties": {
"constraints": {
"anyOf": [
{
"discriminator": {
"mapping": {
"boolean": "#/components/schemas/BooleanSettingConstraints",
"float": "#/components/schemas/FloatSettingConstraints",
"integer": "#/components/schemas/IntegerSettingConstraints",
"object_id": "#/components/schemas/ObjectIdSettingConstraints",
"string": "#/components/schemas/StringSettingConstraints"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Available constraints for integer settings.",
"properties": {
"maxValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the setting (inclusive).",
"title": "maxValue"
},
"minValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the setting (inclusive).",
"title": "minValue"
},
"type": {
"const": "integer",
"default": "integer",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "IntegerSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for float settings.",
"properties": {
"maxValue": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The maximum value of the setting (inclusive).",
"title": "maxValue"
},
"minValue": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The minimum value of the setting (inclusive).",
"title": "minValue"
},
"type": {
"const": "float",
"default": "float",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "FloatSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for string settings.",
"properties": {
"allowedChoices": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The allowed values for the setting.",
"title": "allowedChoices"
},
"maxLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum length of the value (inclusive).",
"title": "maxLength"
},
"minLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum length of the value (inclusive).",
"title": "minLength"
},
"type": {
"const": "string",
"default": "string",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "StringSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for boolean settings.",
"properties": {
"type": {
"const": "boolean",
"default": "boolean",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "BooleanSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for ObjectId settings.",
"properties": {
"allowedChoices": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The allowed values for the setting.",
"title": "allowedChoices"
},
"type": {
"const": "object_id",
"default": "object_id",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "ObjectIdSettingConstraints",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The constraints for the LLM setting values.",
"title": "constraints"
},
"defaultValue": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The default value of the LLM setting.",
"title": "defaultValue"
},
"description": {
"description": "The description of the LLM setting.",
"title": "description",
"type": "string"
},
"format": {
"anyOf": [
{
"description": "Supported formats for settings.",
"enum": [
"multiline"
],
"title": "SettingFormat",
"type": "string"
},
{
"type": "null"
}
],
"description": "The expected format of the value of the LLM setting."
},
"id": {
"description": "The ID of the LLM setting.",
"title": "id",
"type": "string"
},
"isNullable": {
"default": true,
"description": "Whether the setting allows null values (default: true).",
"title": "isNullable",
"type": "boolean"
},
"name": {
"description": "The name of the LLM setting.",
"title": "name",
"type": "string"
},
"type": {
"description": "Supported data types for settings.",
"enum": [
"integer",
"float",
"string",
"boolean",
"object_id",
"list"
],
"title": "SettingType",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"type",
"constraints",
"defaultValue"
],
"title": "LLMSettingDefinition",
"type": "object"
}
LLMSettingDefinition
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| constraints | any | true | The constraints for the LLM setting values. |
anyOf - discriminator: type
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | any | false | none |
oneOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »» anonymous | IntegerSettingConstraints | false | Available constraints for integer settings. |
xor
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »» anonymous | FloatSettingConstraints | false | Available constraints for float settings. |
xor
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »» anonymous | StringSettingConstraints | false | Available constraints for string settings. |
xor
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »» anonymous | BooleanSettingConstraints | false | Available constraints for boolean settings. |
xor
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »» anonymous | ObjectIdSettingConstraints | false | Available constraints for ObjectId settings. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| defaultValue | any | true | The default value of the LLM setting. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | boolean | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| description | string | true | The description of the LLM setting. | |
| format | any | false | The expected format of the value of the LLM setting. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | SettingFormat | false | Supported formats for settings. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| id | string | true | The ID of the LLM setting. | |
| isNullable | boolean | false | Whether the setting allows null values (default: true). | |
| name | string | true | The name of the LLM setting. | |
| type | SettingType | true | The data type of the LLM setting. |
LLMType
{
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
}
LLMType
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| LLMType | string | false | LLM provider type. |
Enumerated Values¶
| Property | Value |
|---|---|
| LLMType | [openAi, azureOpenAi] |
LanguageModelDefinitionResponse
{
"description": "The metadata that defines an LLM.",
"properties": {
"contextSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the LLM's context, measured in tokens. `null` if unknown.",
"title": "contextSize"
},
"creator": {
"description": "The creator of the LLM.",
"enum": [
"OpenAI",
"Amazon",
"Google",
"Anthropic",
"Unknown"
],
"title": "LLMCreator",
"type": "string"
},
"dateAdded": {
"description": "The date the LLM was added to the GenAI playground.",
"format": "date",
"title": "dateAdded",
"type": "string"
},
"description": {
"description": "The details about the LLM.",
"title": "description",
"type": "string"
},
"documentationLink": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The link to the vendor documentation for the LLM.",
"title": "documentationLink"
},
"id": {
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
"isActive": {
"description": "Whether the LLM is active.",
"title": "isActive",
"type": "boolean"
},
"isDeprecated": {
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "isDeprecated",
"type": "boolean"
},
"isMetered": {
"default": true,
"description": "Whether the LLM usage is metered.",
"title": "isMetered",
"type": "boolean"
},
"license": {
"description": "The usage license information for the LLM.",
"title": "license",
"type": "string"
},
"name": {
"description": "The name of the LLM.",
"title": "name",
"type": "string"
},
"provider": {
"description": "The party that provides access to the LLM.",
"title": "provider",
"type": "string"
},
"referenceLinks": {
"description": "The references for the LLM.",
"items": {
"description": "A reference link for an LLM.",
"properties": {
"name": {
"description": "Description of the reference document.",
"title": "name",
"type": "string"
},
"url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "URL of the reference document.",
"title": "url"
}
},
"required": [
"name",
"url"
],
"title": "LLMReference",
"type": "object"
},
"title": "referenceLinks",
"type": "array"
},
"retirementDate": {
"anyOf": [
{
"format": "date",
"type": "string"
},
{
"type": "null"
}
],
"description": "When the LLM is expected to be retired and no longer available for submitting new prompts.",
"title": "retirementDate"
},
"settings": {
"description": "The settings supported by the LLM.",
"items": {
"description": "Metadata describing a single setting.",
"properties": {
"constraints": {
"anyOf": [
{
"discriminator": {
"mapping": {
"boolean": "#/components/schemas/BooleanSettingConstraints",
"float": "#/components/schemas/FloatSettingConstraints",
"integer": "#/components/schemas/IntegerSettingConstraints",
"object_id": "#/components/schemas/ObjectIdSettingConstraints",
"string": "#/components/schemas/StringSettingConstraints"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Available constraints for integer settings.",
"properties": {
"maxValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the setting (inclusive).",
"title": "maxValue"
},
"minValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the setting (inclusive).",
"title": "minValue"
},
"type": {
"const": "integer",
"default": "integer",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "IntegerSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for float settings.",
"properties": {
"maxValue": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The maximum value of the setting (inclusive).",
"title": "maxValue"
},
"minValue": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The minimum value of the setting (inclusive).",
"title": "minValue"
},
"type": {
"const": "float",
"default": "float",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "FloatSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for string settings.",
"properties": {
"allowedChoices": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The allowed values for the setting.",
"title": "allowedChoices"
},
"maxLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum length of the value (inclusive).",
"title": "maxLength"
},
"minLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum length of the value (inclusive).",
"title": "minLength"
},
"type": {
"const": "string",
"default": "string",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "StringSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for boolean settings.",
"properties": {
"type": {
"const": "boolean",
"default": "boolean",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "BooleanSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for ObjectId settings.",
"properties": {
"allowedChoices": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The allowed values for the setting.",
"title": "allowedChoices"
},
"type": {
"const": "object_id",
"default": "object_id",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "ObjectIdSettingConstraints",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The constraints for the LLM setting values.",
"title": "constraints"
},
"defaultValue": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The default value of the LLM setting.",
"title": "defaultValue"
},
"description": {
"description": "The description of the LLM setting.",
"title": "description",
"type": "string"
},
"format": {
"anyOf": [
{
"description": "Supported formats for settings.",
"enum": [
"multiline"
],
"title": "SettingFormat",
"type": "string"
},
{
"type": "null"
}
],
"description": "The expected format of the value of the LLM setting."
},
"id": {
"description": "The ID of the LLM setting.",
"title": "id",
"type": "string"
},
"isNullable": {
"default": true,
"description": "Whether the setting allows null values (default: true).",
"title": "isNullable",
"type": "boolean"
},
"name": {
"description": "The name of the LLM setting.",
"title": "name",
"type": "string"
},
"type": {
"description": "Supported data types for settings.",
"enum": [
"integer",
"float",
"string",
"boolean",
"object_id",
"list"
],
"title": "SettingType",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"type",
"constraints",
"defaultValue"
],
"title": "LLMSettingDefinition",
"type": "object"
},
"title": "settings",
"type": "array"
},
"suggestedReplacement": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM suggested as a replacement for this one when it is retired."
},
"supportedCustomModelLLMValidations": {
"anyOf": [
{
"items": {
"description": "The metadata describing a validated custom model LLM.",
"properties": {
"id": {
"description": "The ID of the custom model LLM validation.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the custom model LLM validation.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "SupportedCustomModelLLMValidation",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The supported custom model validations if applicable for this LLM ID.",
"title": "supportedCustomModelLLMValidations"
},
"supportedLanguages": {
"description": "The languages supported by the LLM.",
"title": "supportedLanguages",
"type": "string"
},
"vendor": {
"description": "The vendor of the LLM.",
"title": "vendor",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"vendor",
"provider",
"creator",
"license",
"supportedLanguages",
"settings",
"documentationLink",
"referenceLinks",
"dateAdded",
"isDeprecated",
"isActive"
],
"title": "LanguageModelDefinitionResponse",
"type": "object"
}
LanguageModelDefinitionResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| contextSize | any | false | The size of the LLM's context, measured in tokens. null if unknown. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| creator | LLMCreator | true | The company that originally created the LLM. | |
| dateAdded | string(date) | true | The date the LLM was added to the GenAI playground. | |
| description | string | true | The details about the LLM. | |
| documentationLink | any | true | The link to the vendor documentation for the LLM. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| id | LanguageModelTypeId | true | The ID of the LLM. | |
| isActive | boolean | true | Whether the LLM is active. | |
| isDeprecated | boolean | true | Whether the LLM is deprecated and will be removed in a future release. | |
| isMetered | boolean | false | Whether the LLM usage is metered. | |
| license | string | true | The usage license information for the LLM. | |
| name | string | true | The name of the LLM. | |
| provider | string | true | The party that provides access to the LLM. | |
| referenceLinks | [LLMReference] | true | The references for the LLM. | |
| retirementDate | any | false | When the LLM is expected to be retired and no longer available for submitting new prompts. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string(date) | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| settings | [LLMSettingDefinition] | true | The settings supported by the LLM. | |
| suggestedReplacement | any | false | The ID of the LLM suggested as a replacement for this one when it is retired. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | LanguageModelTypeId | false | The ID that defines the type of the LLM. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| supportedCustomModelLLMValidations | any | false | The supported custom model validations if applicable for this LLM ID. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [SupportedCustomModelLLMValidation] | false | [The metadata describing a validated custom model LLM.] |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| supportedLanguages | string | true | The languages supported by the LLM. | |
| vendor | string | true | The vendor of the LLM. |
LanguageModelTypeId
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
}
LanguageModelTypeId
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| LanguageModelTypeId | string | false | The ID that defines the type of the LLM. |
Enumerated Values¶
| Property | Value |
|---|---|
| LanguageModelTypeId | [azure-openai-gpt-3.5-turbo, azure-openai-gpt-3.5-turbo-16k, azure-openai-gpt-4, azure-openai-gpt-4-32k, azure-openai-gpt-4-turbo, azure-openai-gpt-4-o, azure-openai-gpt-4-o-mini, amazon-titan, amazon-nova-micro, amazon-nova-lite, amazon-nova-pro, anthropic-claude-2, anthropic-claude-3-haiku, anthropic-claude-3-sonnet, anthropic-claude-3-opus, anthropic-claude-3.5-sonnet-v1, amazon-anthropic-claude-3.5-sonnet-v2, google-bison, google-gemini-1.5-flash, google-gemini-1.5-pro, custom-model] |
ListCustomModelLLMValidationsResponse
{
"description": "Paginated list of custom model LLM validations.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "API response object for a single custom model LLM validation.",
"properties": {
"chatModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The model ID to specify when calling the OpenAI chat completion API of the deployment.",
"title": "chatModelId"
},
"creationDate": {
"description": "The creation date of the custom model validation (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"deploymentAccessData": {
"anyOf": [
{
"description": "Add authorization_header to avoid breaking change to API.",
"properties": {
"authorizationHeader": {
"default": "[REDACTED]",
"description": "The `Authorization` header to use for the deployment.",
"title": "authorizationHeader",
"type": "string"
},
"chatApiUrl": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the deployment's chat API.",
"title": "chatApiUrl"
},
"datarobotKey": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The server key associated with the prediction API.",
"title": "datarobotKey"
},
"inputType": {
"description": "The format of the input data submitted to a DataRobot deployment.",
"enum": [
"CSV",
"JSON"
],
"title": "DeploymentInputType",
"type": "string"
},
"modelType": {
"description": "The type of the target output a DataRobot deployment produces.",
"enum": [
"TEXT_GENERATION",
"VECTOR_DATABASE",
"UNSTRUCTURED",
"REGRESSION",
"MULTICLASS",
"BINARY",
"NOT_SUPPORTED"
],
"title": "SupportedDeploymentType",
"type": "string"
},
"predictionApiUrl": {
"description": "The URL of the deployment's prediction API.",
"title": "predictionApiUrl",
"type": "string"
}
},
"required": [
"predictionApiUrl",
"datarobotKey",
"inputType",
"modelType"
],
"title": "DeploymentAccessData",
"type": "object"
},
{
"type": "null"
}
],
"description": "The parameters used for accessing the deployment."
},
"deploymentId": {
"description": "The ID of the custom model deployment.",
"title": "deploymentId",
"type": "string"
},
"deploymentName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the custom model deployment.",
"title": "deploymentName"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the validation error (if the validation failed).",
"title": "errorMessage"
},
"id": {
"description": "The ID of the custom model validation.",
"title": "id",
"type": "string"
},
"modelId": {
"description": "The ID of the model used in the deployment.",
"title": "modelId",
"type": "string"
},
"name": {
"description": "The name of the validated custom model.",
"title": "name",
"type": "string"
},
"predictionTimeout": {
"description": "The timeout in seconds for the prediction API used in this custom model validation.",
"title": "predictionTimeout",
"type": "integer"
},
"promptColumnName": {
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName",
"type": "string"
},
"tenantId": {
"description": "The ID of the tenant the custom model validation belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case associated with the validated custom model.",
"title": "useCaseId"
},
"userId": {
"description": "The ID of the user that created this custom model validation.",
"title": "userId",
"type": "string"
},
"userName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the user that created this custom model validation.",
"title": "userName"
},
"validationStatus": {
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
}
},
"required": [
"id",
"deploymentId",
"targetColumnName",
"validationStatus",
"modelId",
"deploymentAccessData",
"tenantId",
"name",
"useCaseId",
"creationDate",
"userId",
"predictionTimeout",
"promptColumnName"
],
"title": "CustomModelLLMValidationResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListCustomModelLLMValidationsResponse",
"type": "object"
}
ListCustomModelLLMValidationsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [CustomModelLLMValidationResponse] | true | The list of records. | |
| next | any | true | The URL to the next page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| previous | any | true | The URL to the previous page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| totalCount | integer | true | The total number of records. |
ListCustomModelValidationSortQueryParam
{
"description": "Sort order values for listing custom model validations.",
"enum": [
"name",
"-name",
"deploymentName",
"-deploymentName",
"userName",
"-userName",
"creationDate",
"-creationDate"
],
"title": "ListCustomModelValidationSortQueryParam",
"type": "string"
}
ListCustomModelValidationSortQueryParam
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ListCustomModelValidationSortQueryParam | string | false | Sort order values for listing custom model validations. |
Enumerated Values¶
| Property | Value |
|---|---|
| ListCustomModelValidationSortQueryParam | [name, -name, deploymentName, -deploymentName, userName, -userName, creationDate, -creationDate] |
ListLLMBlueprintSortQueryParam
{
"description": "Sort order values for listing LLM blueprints.",
"enum": [
"name",
"-name",
"description",
"-description",
"creationUserId",
"-creationUserId",
"creationDate",
"-creationDate",
"lastUpdateUserId",
"-lastUpdateUserId",
"lastUpdateDate",
"-lastUpdateDate",
"llmId",
"-llmId",
"vectorDatabaseId",
"-vectorDatabaseId"
],
"title": "ListLLMBlueprintSortQueryParam",
"type": "string"
}
ListLLMBlueprintSortQueryParam
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ListLLMBlueprintSortQueryParam | string | false | Sort order values for listing LLM blueprints. |
Enumerated Values¶
| Property | Value |
|---|---|
| ListLLMBlueprintSortQueryParam | [name, -name, description, -description, creationUserId, -creationUserId, creationDate, -creationDate, lastUpdateUserId, -lastUpdateUserId, lastUpdateDate, -lastUpdateDate, llmId, -llmId, vectorDatabaseId, -vectorDatabaseId] |
ListLLMBlueprintsResponse
{
"description": "Paginated list of LLM blueprints.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "API response object for a single LLM blueprint.",
"properties": {
"creationDate": {
"description": "The creation date of the LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this LLM blueprint.",
"title": "creationUserId",
"type": "string"
},
"creationUserName": {
"description": "The name of the user who created this LLM blueprint.",
"title": "creationUserName",
"type": "string"
},
"customModelLLMErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorMessage"
},
"customModelLLMErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the custom model LLM (if using a custom model LLM).",
"title": "customModelLLMErrorResolution"
},
"customModelLLMValidationStatus": {
"anyOf": [
{
"description": "Status of custom model validation.",
"enum": [
"TESTING",
"PASSED",
"FAILED"
],
"title": "CustomModelValidationStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation status of the custom model LLM (if using a custom model LLM)."
},
"description": {
"description": "The description of the LLM blueprint.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the LLM blueprint.",
"title": "id",
"type": "string"
},
"isActive": {
"description": "Whether the LLM specified in this blueprint is active in the current environment.",
"title": "isActive",
"type": "boolean"
},
"isDeprecated": {
"description": "Whether the LLM specified in this blueprint is deprecated.",
"title": "isDeprecated",
"type": "boolean"
},
"isSaved": {
"description": "If false, then this LLM blueprint is a draft and its settings can be changed. If true, then its settings are frozen and cannot be changed anymore.",
"title": "isSaved",
"type": "boolean"
},
"isStarred": {
"description": "Specifies whether this LLM blueprint is starred.",
"title": "isStarred",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this LLM blueprint (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this LLM blueprint.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM selected for this LLM blueprint."
},
"llmName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the LLM used by this LLM blueprint.",
"title": "llmName"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of LLM settings.",
"title": "llmSettings"
},
"name": {
"description": "The name of the LLM blueprint.",
"title": "name",
"type": "string"
},
"playgroundId": {
"description": "The ID of the playground this LLM blueprint belongs to.",
"title": "playgroundId",
"type": "string"
},
"promptType": {
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
"retirementDate": {
"anyOf": [
{
"format": "date",
"type": "string"
},
{
"type": "null"
}
],
"description": "When the LLM is expected to be retired and no longer available for submitting new prompts.",
"title": "retirementDate"
},
"vectorDatabaseErrorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message of the vector database associated with this LLM.",
"title": "vectorDatabaseErrorMessage"
},
"vectorDatabaseErrorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseErrorResolution"
},
"vectorDatabaseFamilyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database family associated with this LLM blueprint.",
"title": "vectorDatabaseFamilyId"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database linked to this LLM blueprint.",
"title": "vectorDatabaseId"
},
"vectorDatabaseName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the vector database associated with this LLM blueprint.",
"title": "vectorDatabaseName"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "A key/value dictionary of vector database settings."
},
"vectorDatabaseStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database associated with this LLM blueprint."
}
},
"required": [
"id",
"name",
"description",
"isSaved",
"isStarred",
"promptType",
"playgroundId",
"llmName",
"creationDate",
"creationUserId",
"creationUserName",
"lastUpdateDate",
"lastUpdateUserId",
"vectorDatabaseName",
"vectorDatabaseStatus",
"vectorDatabaseErrorMessage",
"vectorDatabaseErrorResolution",
"customModelLLMValidationStatus",
"customModelLLMErrorMessage",
"customModelLLMErrorResolution",
"vectorDatabaseFamilyId",
"isActive",
"isDeprecated"
],
"title": "LLMBlueprintResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListLLMBlueprintsResponse",
"type": "object"
}
ListLLMBlueprintsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [LLMBlueprintResponse] | true | The list of records. | |
| next | any | true | The URL to the next page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| previous | any | true | The URL to the previous page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| totalCount | integer | true | The total number of records. |
ListLLMsResponse
{
"description": "Paginated list of LLMs.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "The metadata that defines an LLM.",
"properties": {
"contextSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the LLM's context, measured in tokens. `null` if unknown.",
"title": "contextSize"
},
"creator": {
"description": "The creator of the LLM.",
"enum": [
"OpenAI",
"Amazon",
"Google",
"Anthropic",
"Unknown"
],
"title": "LLMCreator",
"type": "string"
},
"dateAdded": {
"description": "The date the LLM was added to the GenAI playground.",
"format": "date",
"title": "dateAdded",
"type": "string"
},
"description": {
"description": "The details about the LLM.",
"title": "description",
"type": "string"
},
"documentationLink": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The link to the vendor documentation for the LLM.",
"title": "documentationLink"
},
"id": {
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
"isActive": {
"description": "Whether the LLM is active.",
"title": "isActive",
"type": "boolean"
},
"isDeprecated": {
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "isDeprecated",
"type": "boolean"
},
"isMetered": {
"default": true,
"description": "Whether the LLM usage is metered.",
"title": "isMetered",
"type": "boolean"
},
"license": {
"description": "The usage license information for the LLM.",
"title": "license",
"type": "string"
},
"name": {
"description": "The name of the LLM.",
"title": "name",
"type": "string"
},
"provider": {
"description": "The party that provides access to the LLM.",
"title": "provider",
"type": "string"
},
"referenceLinks": {
"description": "The references for the LLM.",
"items": {
"description": "A reference link for an LLM.",
"properties": {
"name": {
"description": "Description of the reference document.",
"title": "name",
"type": "string"
},
"url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "URL of the reference document.",
"title": "url"
}
},
"required": [
"name",
"url"
],
"title": "LLMReference",
"type": "object"
},
"title": "referenceLinks",
"type": "array"
},
"retirementDate": {
"anyOf": [
{
"format": "date",
"type": "string"
},
{
"type": "null"
}
],
"description": "When the LLM is expected to be retired and no longer available for submitting new prompts.",
"title": "retirementDate"
},
"settings": {
"description": "The settings supported by the LLM.",
"items": {
"description": "Metadata describing a single setting.",
"properties": {
"constraints": {
"anyOf": [
{
"discriminator": {
"mapping": {
"boolean": "#/components/schemas/BooleanSettingConstraints",
"float": "#/components/schemas/FloatSettingConstraints",
"integer": "#/components/schemas/IntegerSettingConstraints",
"object_id": "#/components/schemas/ObjectIdSettingConstraints",
"string": "#/components/schemas/StringSettingConstraints"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Available constraints for integer settings.",
"properties": {
"maxValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the setting (inclusive).",
"title": "maxValue"
},
"minValue": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the setting (inclusive).",
"title": "minValue"
},
"type": {
"const": "integer",
"default": "integer",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "IntegerSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for float settings.",
"properties": {
"maxValue": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The maximum value of the setting (inclusive).",
"title": "maxValue"
},
"minValue": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The minimum value of the setting (inclusive).",
"title": "minValue"
},
"type": {
"const": "float",
"default": "float",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "FloatSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for string settings.",
"properties": {
"allowedChoices": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The allowed values for the setting.",
"title": "allowedChoices"
},
"maxLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum length of the value (inclusive).",
"title": "maxLength"
},
"minLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum length of the value (inclusive).",
"title": "minLength"
},
"type": {
"const": "string",
"default": "string",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "StringSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for boolean settings.",
"properties": {
"type": {
"const": "boolean",
"default": "boolean",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "BooleanSettingConstraints",
"type": "object"
},
{
"description": "Available constraints for ObjectId settings.",
"properties": {
"allowedChoices": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The allowed values for the setting.",
"title": "allowedChoices"
},
"type": {
"const": "object_id",
"default": "object_id",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "ObjectIdSettingConstraints",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The constraints for the LLM setting values.",
"title": "constraints"
},
"defaultValue": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The default value of the LLM setting.",
"title": "defaultValue"
},
"description": {
"description": "The description of the LLM setting.",
"title": "description",
"type": "string"
},
"format": {
"anyOf": [
{
"description": "Supported formats for settings.",
"enum": [
"multiline"
],
"title": "SettingFormat",
"type": "string"
},
{
"type": "null"
}
],
"description": "The expected format of the value of the LLM setting."
},
"id": {
"description": "The ID of the LLM setting.",
"title": "id",
"type": "string"
},
"isNullable": {
"default": true,
"description": "Whether the setting allows null values (default: true).",
"title": "isNullable",
"type": "boolean"
},
"name": {
"description": "The name of the LLM setting.",
"title": "name",
"type": "string"
},
"type": {
"description": "Supported data types for settings.",
"enum": [
"integer",
"float",
"string",
"boolean",
"object_id",
"list"
],
"title": "SettingType",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"type",
"constraints",
"defaultValue"
],
"title": "LLMSettingDefinition",
"type": "object"
},
"title": "settings",
"type": "array"
},
"suggestedReplacement": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM suggested as a replacement for this one when it is retired."
},
"supportedCustomModelLLMValidations": {
"anyOf": [
{
"items": {
"description": "The metadata describing a validated custom model LLM.",
"properties": {
"id": {
"description": "The ID of the custom model LLM validation.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the custom model LLM validation.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "SupportedCustomModelLLMValidation",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The supported custom model validations if applicable for this LLM ID.",
"title": "supportedCustomModelLLMValidations"
},
"supportedLanguages": {
"description": "The languages supported by the LLM.",
"title": "supportedLanguages",
"type": "string"
},
"vendor": {
"description": "The vendor of the LLM.",
"title": "vendor",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"vendor",
"provider",
"creator",
"license",
"supportedLanguages",
"settings",
"documentationLink",
"referenceLinks",
"dateAdded",
"isDeprecated",
"isActive"
],
"title": "LanguageModelDefinitionResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListLLMsResponse",
"type": "object"
}
ListLLMsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [LanguageModelDefinitionResponse] | true | The list of records. | |
| next | any | true | The URL to the next page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| previous | any | true | The URL to the previous page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| totalCount | integer | true | The total number of records. |
ListPlaygroundSortQueryParam
{
"description": "Sort order values for listing playgrounds.",
"enum": [
"name",
"-name",
"description",
"-description",
"creationUserId",
"-creationUserId",
"creationDate",
"-creationDate",
"lastUpdateUserId",
"-lastUpdateUserId",
"lastUpdateDate",
"-lastUpdateDate",
"savedLLMBlueprintsCount",
"-savedLLMBlueprintsCount",
"llmBlueprintsCount",
"-llmBlueprintsCount"
],
"title": "ListPlaygroundSortQueryParam",
"type": "string"
}
ListPlaygroundSortQueryParam
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ListPlaygroundSortQueryParam | string | false | Sort order values for listing playgrounds. |
Enumerated Values¶
| Property | Value |
|---|---|
| ListPlaygroundSortQueryParam | [name, -name, description, -description, creationUserId, -creationUserId, creationDate, -creationDate, lastUpdateUserId, -lastUpdateUserId, lastUpdateDate, -lastUpdateDate, savedLLMBlueprintsCount, -savedLLMBlueprintsCount, llmBlueprintsCount, -llmBlueprintsCount] |
ListPlaygroundsResponse
{
"description": "Paginated list of playgrounds.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "API response object for a single playground.",
"properties": {
"creationDate": {
"description": "The creation date of the playground (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this playground.",
"title": "creationUserId",
"type": "string"
},
"description": {
"description": "The description of the playground.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the playground.",
"title": "id",
"type": "string"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this playground.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmBlueprintsCount": {
"description": "The number of LLM blueprints in this playground.",
"title": "llmBlueprintsCount",
"type": "integer"
},
"name": {
"description": "The name of the playground.",
"title": "name",
"type": "string"
},
"savedLLMBlueprintsCount": {
"description": "The number of saved LLM blueprints in this playground.",
"title": "savedLLMBlueprintsCount",
"type": "integer"
},
"useCaseId": {
"description": "The ID of the use case this playground belongs to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this playground.",
"title": "userName",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"useCaseId",
"creationDate",
"creationUserId",
"lastUpdateDate",
"lastUpdateUserId",
"savedLLMBlueprintsCount",
"llmBlueprintsCount",
"userName"
],
"title": "PlaygroundResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListPlaygroundsResponse",
"type": "object"
}
ListPlaygroundsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [PlaygroundResponse] | true | The list of records. | |
| next | any | true | The URL to the next page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| previous | any | true | The URL to the previous page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| totalCount | integer | true | The total number of records. |
ListTracesResponse
{
"description": "Paginated list of playground prompt traces.",
"properties": {
"count": {
"description": "The number of records on this page.",
"title": "count",
"type": "integer"
},
"data": {
"description": "The list of records.",
"items": {
"description": "API response object for a single playground prompt trace.",
"properties": {
"chatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat associated with the trace.",
"title": "chatId"
},
"chatName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the chat associated with the trace.",
"title": "chatName"
},
"chatPromptId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat prompt associated with the trace.",
"title": "chatPromptId"
},
"comparisonPromptId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the comparison prompts associated with the trace.",
"title": "comparisonPromptId"
},
"confidenceScores": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion for the prompt associated with the trace.",
"title": "confidenceScores"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset associated with the trace.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint associated with the trace.",
"title": "llmBlueprintId",
"type": "string"
},
"llmBlueprintName": {
"description": "The name of the LLM blueprint associated with the trace.",
"title": "llmBlueprintName",
"type": "string"
},
"llmLicense": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The usage license information for the LLM associated with the trace.",
"title": "llmLicense"
},
"llmName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the LLM associated with the trace.",
"title": "llmName"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "The settings of the LLM associated with the trace.",
"title": "llmSettings"
},
"llmVendor": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The vendor of the LLM associated with the trace.",
"title": "llmVendor"
},
"promptType": {
"anyOf": [
{
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
{
"type": "null"
}
],
"description": "The type of prompt, chat history awair or one time prompt."
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the prompt associated with the trace."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The completion text of the prompt associated with the trace.",
"title": "resultText"
},
"text": {
"description": "The text of the prompt associated with the trace.",
"title": "text",
"type": "string"
},
"timestamp": {
"description": "The timestamp of the trace (ISO 8601 formatted).",
"format": "date-time",
"title": "timestamp",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case associated with the trace.",
"title": "useCaseId",
"type": "string"
},
"user": {
"description": "DataRobot application user.",
"properties": {
"id": {
"description": "The ID of the user.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the user.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "DataRobotUser",
"type": "object"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database associated with the trace.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "The settings of the vector database associated with the trace."
},
"warning": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The warning message for the prompt associated with the trace.",
"title": "warning"
}
},
"required": [
"timestamp",
"user",
"chatPromptId",
"comparisonPromptId",
"useCaseId",
"llmBlueprintId",
"llmBlueprintName",
"llmName",
"llmVendor",
"llmLicense",
"llmSettings",
"chatName",
"chatId",
"vectorDatabaseId",
"vectorDatabaseSettings",
"resultMetadata",
"resultText",
"confidenceScores",
"text",
"executionStatus",
"promptType",
"evaluationDatasetConfigurationId",
"warning"
],
"title": "PromptTraceResponse",
"type": "object"
},
"title": "data",
"type": "array"
},
"next": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the next page, or `null` if there is no such page.",
"title": "next"
},
"previous": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL to the previous page, or `null` if there is no such page.",
"title": "previous"
},
"totalCount": {
"description": "The total number of records.",
"title": "totalCount",
"type": "integer"
}
},
"required": [
"totalCount",
"count",
"next",
"previous",
"data"
],
"title": "ListTracesResponse",
"type": "object"
}
ListTracesResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [PromptTraceResponse] | true | The list of records. | |
| next | any | true | The URL to the next page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| previous | any | true | The URL to the previous page, or null if there is no such page. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| totalCount | integer | true | The total number of records. |
MetricMetadata
{
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
}
MetricMetadata
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| costConfigurationId | any | false | The ID of the cost configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customModelId | any | false | The ID of the custom model used for the metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| errorMessage | any | false | The error message associated with the metric computation. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| evaluationDatasetConfigurationId | any | false | The ID of the evaluation dataset configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| executionStatus | any | false | The creation status of the vector database. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ExecutionStatus | false | Job and entity execution status. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| formattedName | any | false | The formatted name of the metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| formattedValue | any | false | The formatted value of the metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmIsDeprecated | any | false | Whether the LLM is deprecated and will be removed in a future release. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | boolean | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | true | The name of the metric. | |
| nemoMetricId | any | false | The id of the NeMo Pipeline configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ootbMetricId | any | false | The id of the OOTB metric configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| sidecarModelMetricValidationId | any | false | The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| stage | any | false | The stage (prompt or response) that the metric applies to. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | PipelineStage | false | Enum that describes at which stage the metric may be calculated. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| value | any | true | The value of the metric. |
MetricUnit
{
"description": "The unit of measurement associated with a metric.",
"enum": [
"s",
"ms",
"%"
],
"title": "MetricUnit",
"type": "string"
}
MetricUnit
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| MetricUnit | string | false | The unit of measurement associated with a metric. |
Enumerated Values¶
| Property | Value |
|---|---|
| MetricUnit | [s, ms, %] |
ModerationAction
{
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
}
ModerationAction
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ModerationAction | string | false | The moderation strategy. |
Enumerated Values¶
| Property | Value |
|---|---|
| ModerationAction | [block, report, reportAndBlock] |
ModerationConfigurationWithID
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithID",
"type": "object"
}
ModerationConfigurationWithID
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| guardConditions | [GuardCondition] | true | maxItems: 1 minItems: 1 |
The guard conditions associated with a metric. |
| intervention | Intervention | true | The intervention specific moderation configuration. |
ModerationConfigurationWithoutID
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
}
ModerationConfigurationWithoutID
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| guardConditions | [GuardCondition] | true | maxItems: 1 minItems: 1 |
The guard conditions associated with a metric. |
| intervention | Intervention | true | The intervention specific moderation configuration. |
NemoConfigurationResponse
{
"description": "API response object for a playground Nemo configuration.",
"properties": {
"blockedTermsFileContents": {
"description": "The contents of the blocked terms file.",
"title": "blockedTermsFileContents",
"type": "string"
},
"promptLlmConfiguration": {
"anyOf": [
{
"description": "Configuration of LLM used for NeMo guardrails.",
"properties": {
"llmType": {
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
},
"openaiApiBase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API base.",
"title": "openaiApiBase"
},
"openaiApiDeploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API deployment ID.",
"title": "openaiApiDeploymentId"
},
"openaiApiKeyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "OpenAI API Key.",
"title": "openaiApiKeyId"
}
},
"required": [
"llmType"
],
"title": "NemoLLMConfiguration",
"type": "object"
},
{
"type": "null"
}
],
"description": "The LLM configuration for the prompt pipeline."
},
"promptModerationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration for the prompt pipeline."
},
"promptPipelineFiles": {
"anyOf": [
{
"description": "Files used to setup a NeMo pipeline.",
"properties": {
"actionsFileContents": {
"description": "Contents of actions.py file.",
"title": "actionsFileContents",
"type": "string"
},
"configYamlFileContents": {
"description": "Contents of config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "Contents of flows.co file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "Contents of prompts.yaml file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"actionsFileContents",
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPipelineFiles",
"type": "object"
},
{
"type": "null"
}
],
"description": "The prompt pipeline files for this configuration."
},
"promptPipelineMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name for the NeMo Prompt pipeline metric.",
"title": "promptPipelineMetricName"
},
"promptPipelineTemplateId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Guard template to be used for the prompt pipeline, defines actions.py.",
"title": "promptPipelineTemplateId"
},
"responseLlmConfiguration": {
"anyOf": [
{
"description": "Configuration of LLM used for NeMo guardrails.",
"properties": {
"llmType": {
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
},
"openaiApiBase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API base.",
"title": "openaiApiBase"
},
"openaiApiDeploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API deployment ID.",
"title": "openaiApiDeploymentId"
},
"openaiApiKeyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "OpenAI API Key.",
"title": "openaiApiKeyId"
}
},
"required": [
"llmType"
],
"title": "NemoLLMConfiguration",
"type": "object"
},
{
"type": "null"
}
],
"description": "The LLM configuration for the response pipeline."
},
"responseModerationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration for the response pipeline."
},
"responsePipelineFiles": {
"anyOf": [
{
"description": "Files used to setup a NeMo pipeline.",
"properties": {
"actionsFileContents": {
"description": "Contents of actions.py file.",
"title": "actionsFileContents",
"type": "string"
},
"configYamlFileContents": {
"description": "Contents of config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "Contents of flows.co file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "Contents of prompts.yaml file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"actionsFileContents",
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPipelineFiles",
"type": "object"
},
{
"type": "null"
}
],
"description": "The response pipeline files for this configuration."
},
"responsePipelineMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name for the NeMo Response pipeline metric.",
"title": "responsePipelineMetricName"
},
"responsePipelineTemplateId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Guard template to be used for the response pipeline, defines actions.py.",
"title": "responsePipelineTemplateId"
}
},
"required": [
"promptPipelineMetricName",
"promptPipelineFiles",
"promptPipelineTemplateId",
"promptLlmConfiguration",
"responsePipelineMetricName",
"responsePipelineFiles",
"responsePipelineTemplateId",
"responseLlmConfiguration",
"blockedTermsFileContents"
],
"title": "NemoConfigurationResponse",
"type": "object"
}
NemoConfigurationResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| blockedTermsFileContents | string | true | The contents of the blocked terms file. | |
| promptLlmConfiguration | any | true | The LLM configuration for the prompt pipeline. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | NemoLLMConfiguration | false | Configuration of LLM used for NeMo guardrails. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptModerationConfiguration | any | false | The moderation configuration for the prompt pipeline. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ModerationConfigurationWithoutID | false | Moderation Configuration associated with an insight. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptPipelineFiles | any | true | The prompt pipeline files for this configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | NemoPipelineFiles | false | Files used to setup a NeMo pipeline. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptPipelineMetricName | any | true | Name for the NeMo Prompt pipeline metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptPipelineTemplateId | any | true | Guard template to be used for the prompt pipeline, defines actions.py. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| responseLlmConfiguration | any | true | The LLM configuration for the response pipeline. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | NemoLLMConfiguration | false | Configuration of LLM used for NeMo guardrails. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| responseModerationConfiguration | any | false | The moderation configuration for the response pipeline. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ModerationConfigurationWithoutID | false | Moderation Configuration associated with an insight. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| responsePipelineFiles | any | true | The response pipeline files for this configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | NemoPipelineFiles | false | Files used to setup a NeMo pipeline. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| responsePipelineMetricName | any | true | Name for the NeMo Response pipeline metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| responsePipelineTemplateId | any | true | Guard template to be used for the response pipeline, defines actions.py. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
NemoConfigurationUpsertRequest
{
"description": "The body of the Nemo Configuration upsert request.",
"properties": {
"blockedTermsFileContents": {
"description": "The contents of the blocked terms file.",
"title": "blockedTermsFileContents",
"type": "string"
},
"promptLlmConfiguration": {
"anyOf": [
{
"description": "Configuration of LLM used for NeMo guardrails.",
"properties": {
"llmType": {
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
},
"openaiApiBase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API base.",
"title": "openaiApiBase"
},
"openaiApiDeploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API deployment ID.",
"title": "openaiApiDeploymentId"
},
"openaiApiKeyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "OpenAI API Key.",
"title": "openaiApiKeyId"
}
},
"required": [
"llmType"
],
"title": "NemoLLMConfiguration",
"type": "object"
},
{
"type": "null"
}
],
"description": "The LLM configuration for the prompt pipeline."
},
"promptModerationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration for the prompt pipeline."
},
"promptPipelineFiles": {
"anyOf": [
{
"description": "All of the files except for the actions.py file.",
"properties": {
"configYamlFileContents": {
"description": "The contents of the config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "The contents of the flow definition file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "The contents of the prompts file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPiplineFilesRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "The prompt pipeline files for this configuration."
},
"promptPipelineMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name for the NeMo Prompt pipeline metric.",
"title": "promptPipelineMetricName"
},
"promptPipelineTemplateId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Guard template to be used for the prompt pipeline, defines actions.py.",
"title": "promptPipelineTemplateId"
},
"responseLlmConfiguration": {
"anyOf": [
{
"description": "Configuration of LLM used for NeMo guardrails.",
"properties": {
"llmType": {
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
},
"openaiApiBase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API base.",
"title": "openaiApiBase"
},
"openaiApiDeploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API deployment ID.",
"title": "openaiApiDeploymentId"
},
"openaiApiKeyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "OpenAI API Key.",
"title": "openaiApiKeyId"
}
},
"required": [
"llmType"
],
"title": "NemoLLMConfiguration",
"type": "object"
},
{
"type": "null"
}
],
"description": "The LLM configuration for the response pipeline."
},
"responseModerationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration for the response pipeline."
},
"responsePipelineFiles": {
"anyOf": [
{
"description": "All of the files except for the actions.py file.",
"properties": {
"configYamlFileContents": {
"description": "The contents of the config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "The contents of the flow definition file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "The contents of the prompts file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPiplineFilesRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "The response pipeline files for this configuration."
},
"responsePipelineMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name for the NeMo Response pipeline metric.",
"title": "responsePipelineMetricName"
},
"responsePipelineTemplateId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Guard template to be used for the response pipeline, defines actions.py.",
"title": "responsePipelineTemplateId"
}
},
"required": [
"blockedTermsFileContents"
],
"title": "NemoConfigurationUpsertRequest",
"type": "object"
}
NemoConfigurationUpsertRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| blockedTermsFileContents | string | true | The contents of the blocked terms file. | |
| promptLlmConfiguration | any | false | The LLM configuration for the prompt pipeline. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | NemoLLMConfiguration | false | Configuration of LLM used for NeMo guardrails. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptModerationConfiguration | any | false | The moderation configuration for the prompt pipeline. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ModerationConfigurationWithoutID | false | Moderation Configuration associated with an insight. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptPipelineFiles | any | false | The prompt pipeline files for this configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | NemoPiplineFilesRequest | false | All of the files except for the actions.py file. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptPipelineMetricName | any | false | Name for the NeMo Prompt pipeline metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptPipelineTemplateId | any | false | Guard template to be used for the prompt pipeline, defines actions.py. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| responseLlmConfiguration | any | false | The LLM configuration for the response pipeline. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | NemoLLMConfiguration | false | Configuration of LLM used for NeMo guardrails. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| responseModerationConfiguration | any | false | The moderation configuration for the response pipeline. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ModerationConfigurationWithoutID | false | Moderation Configuration associated with an insight. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| responsePipelineFiles | any | false | The response pipeline files for this configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | NemoPiplineFilesRequest | false | All of the files except for the actions.py file. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| responsePipelineMetricName | any | false | Name for the NeMo Response pipeline metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| responsePipelineTemplateId | any | false | Guard template to be used for the response pipeline, defines actions.py. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
NemoLLMConfiguration
{
"description": "Configuration of LLM used for NeMo guardrails.",
"properties": {
"llmType": {
"description": "LLM provider type.",
"enum": [
"openAi",
"azureOpenAi"
],
"title": "LLMType",
"type": "string"
},
"openaiApiBase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API base.",
"title": "openaiApiBase"
},
"openaiApiDeploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Azure OpenAI API deployment ID.",
"title": "openaiApiDeploymentId"
},
"openaiApiKeyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "OpenAI API Key.",
"title": "openaiApiKeyId"
}
},
"required": [
"llmType"
],
"title": "NemoLLMConfiguration",
"type": "object"
}
NemoLLMConfiguration
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmType | LLMType | true | LLM provider type. | |
| openaiApiBase | any | false | Azure OpenAI API base. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| openaiApiDeploymentId | any | false | Azure OpenAI API deployment ID. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| openaiApiKeyId | any | false | OpenAI API Key. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
NemoPipelineFiles
{
"description": "Files used to setup a NeMo pipeline.",
"properties": {
"actionsFileContents": {
"description": "Contents of actions.py file.",
"title": "actionsFileContents",
"type": "string"
},
"configYamlFileContents": {
"description": "Contents of config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "Contents of flows.co file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "Contents of prompts.yaml file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"actionsFileContents",
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPipelineFiles",
"type": "object"
}
NemoPipelineFiles
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| actionsFileContents | string | true | Contents of actions.py file. | |
| configYamlFileContents | string | true | Contents of config.yaml file. | |
| flowDefinitionFileContents | string | true | Contents of flows.co file. | |
| promptsFileContents | string | true | Contents of prompts.yaml file. |
NemoPiplineFilesRequest
{
"description": "All of the files except for the actions.py file.",
"properties": {
"configYamlFileContents": {
"description": "The contents of the config.yaml file.",
"title": "configYamlFileContents",
"type": "string"
},
"flowDefinitionFileContents": {
"description": "The contents of the flow definition file.",
"title": "flowDefinitionFileContents",
"type": "string"
},
"promptsFileContents": {
"description": "The contents of the prompts file.",
"title": "promptsFileContents",
"type": "string"
}
},
"required": [
"configYamlFileContents",
"flowDefinitionFileContents",
"promptsFileContents"
],
"title": "NemoPiplineFilesRequest",
"type": "object"
}
NemoPiplineFilesRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| configYamlFileContents | string | true | The contents of the config.yaml file. | |
| flowDefinitionFileContents | string | true | The contents of the flow definition file. | |
| promptsFileContents | string | true | The contents of the prompts file. |
OOTBMetricConfigurationRequest
{
"description": "API request object for a single OOTB metric configuration.",
"properties": {
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation (if using a custom model LLM).",
"title": "customModelLLMValidationId"
},
"customOotbMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The custom OOTB metric name to be associated with the OOTB metric. Will default to OOTB metric name if not defined.",
"title": "customOotbMetricName"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM to use for `correctness` and `faithfulness` metrics."
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration to be associated with the OOTB metric."
},
"ootbMetricName": {
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
}
},
"required": [
"ootbMetricName"
],
"title": "OOTBMetricConfigurationRequest",
"type": "object"
}
OOTBMetricConfigurationRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customModelLLMValidationId | any | false | The ID of the custom model LLM validation (if using a custom model LLM). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customOotbMetricName | any | false | The custom OOTB metric name to be associated with the OOTB metric. Will default to OOTB metric name if not defined. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmId | any | false | The ID of the LLM to use for correctness and faithfulness metrics. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | LanguageModelTypeId | false | The ID that defines the type of the LLM. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| moderationConfiguration | any | false | The moderation configuration to be associated with the OOTB metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ModerationConfigurationWithoutID | false | Moderation Configuration associated with an insight. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ootbMetricName | OOTBMetricInsightNames | true | The Out-Of-The-Box metric name that can be used in the playground. |
OOTBMetricConfigurationResponse
{
"description": "API response object for a single OOTB metric.",
"properties": {
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation (if using a custom model LLM).",
"title": "customModelLLMValidationId"
},
"customOotbMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The custom OOTB metric name to be associated with the OOTB metric.",
"title": "customOotbMetricName"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the OOTB metric configuration.",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"items": {
"description": "Error type linking directly to the field name that is related to the error.",
"enum": [
"ootbMetricName",
"intervention",
"guardCondition",
"sidecarOverall",
"sidecarRevalidate",
"sidecarDeploymentId",
"sidecarInputColumnName",
"sidecarOutputColumnName",
"promptPipelineFiles",
"promptPipelineTemplateId",
"responsePipelineFiles",
"responsePipelineTemplateId"
],
"title": "InsightErrorResolution",
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The error type associated with the insight error status and error message as an indicator of what fields needs to be edited if any.",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM to use for `correctness` and `faithfulness` metrics."
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration to be associated with the OOTB metric."
},
"ootbMetricConfigurationId": {
"description": "The ID of OOTB metric.",
"title": "ootbMetricConfigurationId",
"type": "string"
},
"ootbMetricName": {
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
}
},
"required": [
"ootbMetricName",
"ootbMetricConfigurationId",
"executionStatus"
],
"title": "OOTBMetricConfigurationResponse",
"type": "object"
}
OOTBMetricConfigurationResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customModelLLMValidationId | any | false | The ID of the custom model LLM validation (if using a custom model LLM). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| customOotbMetricName | any | false | The custom OOTB metric name to be associated with the OOTB metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| errorMessage | any | false | The error message associated with the OOTB metric configuration. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| errorResolution | any | false | The error type associated with the insight error status and error message as an indicator of what fields needs to be edited if any. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [InsightErrorResolution] | false | [Error type linking directly to the field name that is related to the error.] |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| executionStatus | ExecutionStatus | true | The execution status of the OOTB metric configuration. | |
| llmId | any | false | The ID of the LLM to use for correctness and faithfulness metrics. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | LanguageModelTypeId | false | The ID that defines the type of the LLM. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| moderationConfiguration | any | false | The moderation configuration to be associated with the OOTB metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ModerationConfigurationWithoutID | false | Moderation Configuration associated with an insight. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ootbMetricConfigurationId | string | true | The ID of OOTB metric. | |
| ootbMetricName | OOTBMetricInsightNames | true | The Out-Of-The-Box metric name that can be used in the playground. |
OOTBMetricConfigurationsResponse
{
"description": "The response for the \"OOTB metric configurations\" retrieve request.",
"properties": {
"ootbMetricConfigurations": {
"description": "The list of OOTB metric configurations to use.",
"items": {
"description": "API response object for a single OOTB metric.",
"properties": {
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation (if using a custom model LLM).",
"title": "customModelLLMValidationId"
},
"customOotbMetricName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The custom OOTB metric name to be associated with the OOTB metric.",
"title": "customOotbMetricName"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the OOTB metric configuration.",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"items": {
"description": "Error type linking directly to the field name that is related to the error.",
"enum": [
"ootbMetricName",
"intervention",
"guardCondition",
"sidecarOverall",
"sidecarRevalidate",
"sidecarDeploymentId",
"sidecarInputColumnName",
"sidecarOutputColumnName",
"promptPipelineFiles",
"promptPipelineTemplateId",
"responsePipelineFiles",
"responsePipelineTemplateId"
],
"title": "InsightErrorResolution",
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The error type associated with the insight error status and error message as an indicator of what fields needs to be edited if any.",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the LLM to use for `correctness` and `faithfulness` metrics."
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration to be associated with the OOTB metric."
},
"ootbMetricConfigurationId": {
"description": "The ID of OOTB metric.",
"title": "ootbMetricConfigurationId",
"type": "string"
},
"ootbMetricName": {
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
}
},
"required": [
"ootbMetricName",
"ootbMetricConfigurationId",
"executionStatus"
],
"title": "OOTBMetricConfigurationResponse",
"type": "object"
},
"title": "ootbMetricConfigurations",
"type": "array"
}
},
"required": [
"ootbMetricConfigurations"
],
"title": "OOTBMetricConfigurationsResponse",
"type": "object"
}
OOTBMetricConfigurationsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ootbMetricConfigurations | [OOTBMetricConfigurationResponse] | true | The list of OOTB metric configurations to use. |
OOTBMetricInsightNames
{
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
}
OOTBMetricInsightNames
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| OOTBMetricInsightNames | string | false | The Out-Of-The-Box metric name that can be used in the playground. |
Enumerated Values¶
| Property | Value |
|---|---|
| OOTBMetricInsightNames | [latency, citations, rouge_1, faithfulness, correctness, prompt_tokens, response_tokens, document_tokens, all_tokens, jailbreak_violation, toxicity_violation, pii_violation, exact_match, starts_with, contains] |
ObjectIdSettingConstraints
{
"description": "Available constraints for ObjectId settings.",
"properties": {
"allowedChoices": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The allowed values for the setting.",
"title": "allowedChoices"
},
"type": {
"const": "object_id",
"default": "object_id",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "ObjectIdSettingConstraints",
"type": "object"
}
ObjectIdSettingConstraints
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| allowedChoices | any | false | The allowed values for the setting. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [string] | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| type | string | false | The data type of the setting. |
PipelineStage
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
}
PipelineStage
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| PipelineStage | string | false | Enum that describes at which stage the metric may be calculated. |
Enumerated Values¶
| Property | Value |
|---|---|
| PipelineStage | [prompt_pipeline, response_pipeline] |
PlaygroundResponse
{
"description": "API response object for a single playground.",
"properties": {
"creationDate": {
"description": "The creation date of the playground (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationUserId": {
"description": "The ID of the user that created this playground.",
"title": "creationUserId",
"type": "string"
},
"description": {
"description": "The description of the playground.",
"title": "description",
"type": "string"
},
"id": {
"description": "The ID of the playground.",
"title": "id",
"type": "string"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"lastUpdateUserId": {
"description": "The ID of the user that made the most recent update to this playground.",
"title": "lastUpdateUserId",
"type": "string"
},
"llmBlueprintsCount": {
"description": "The number of LLM blueprints in this playground.",
"title": "llmBlueprintsCount",
"type": "integer"
},
"name": {
"description": "The name of the playground.",
"title": "name",
"type": "string"
},
"savedLLMBlueprintsCount": {
"description": "The number of saved LLM blueprints in this playground.",
"title": "savedLLMBlueprintsCount",
"type": "integer"
},
"useCaseId": {
"description": "The ID of the use case this playground belongs to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this playground.",
"title": "userName",
"type": "string"
}
},
"required": [
"id",
"name",
"description",
"useCaseId",
"creationDate",
"creationUserId",
"lastUpdateDate",
"lastUpdateUserId",
"savedLLMBlueprintsCount",
"llmBlueprintsCount",
"userName"
],
"title": "PlaygroundResponse",
"type": "object"
}
PlaygroundResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| creationDate | string(date-time) | true | The creation date of the playground (ISO 8601 formatted). | |
| creationUserId | string | true | The ID of the user that created this playground. | |
| description | string | true | The description of the playground. | |
| id | string | true | The ID of the playground. | |
| lastUpdateDate | string(date-time) | true | The date of the most recent update of this playground (ISO 8601 formatted). | |
| lastUpdateUserId | string | true | The ID of the user that made the most recent update to this playground. | |
| llmBlueprintsCount | integer | true | The number of LLM blueprints in this playground. | |
| name | string | true | The name of the playground. | |
| savedLLMBlueprintsCount | integer | true | The number of saved LLM blueprints in this playground. | |
| useCaseId | string | true | The ID of the use case this playground belongs to. | |
| userName | string | true | The name of the user that created this playground. |
PromptTraceResponse
{
"description": "API response object for a single playground prompt trace.",
"properties": {
"chatId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat associated with the trace.",
"title": "chatId"
},
"chatName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the chat associated with the trace.",
"title": "chatName"
},
"chatPromptId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the chat prompt associated with the trace.",
"title": "chatPromptId"
},
"comparisonPromptId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the comparison prompts associated with the trace.",
"title": "comparisonPromptId"
},
"confidenceScores": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"description": "The confidence scores that measure the similarity between the prompt context and the prompt completion for the prompt associated with the trace.",
"title": "confidenceScores"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset associated with the trace.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"llmBlueprintId": {
"description": "The ID of the LLM blueprint associated with the trace.",
"title": "llmBlueprintId",
"type": "string"
},
"llmBlueprintName": {
"description": "The name of the LLM blueprint associated with the trace.",
"title": "llmBlueprintName",
"type": "string"
},
"llmLicense": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The usage license information for the LLM associated with the trace.",
"title": "llmLicense"
},
"llmName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the LLM associated with the trace.",
"title": "llmName"
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "The settings of the LLM associated with the trace.",
"title": "llmSettings"
},
"llmVendor": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The vendor of the LLM associated with the trace.",
"title": "llmVendor"
},
"promptType": {
"anyOf": [
{
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
{
"type": "null"
}
],
"description": "The type of prompt, chat history awair or one time prompt."
},
"resultMetadata": {
"anyOf": [
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The additional information about the prompt associated with the trace."
},
"resultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The completion text of the prompt associated with the trace.",
"title": "resultText"
},
"text": {
"description": "The text of the prompt associated with the trace.",
"title": "text",
"type": "string"
},
"timestamp": {
"description": "The timestamp of the trace (ISO 8601 formatted).",
"format": "date-time",
"title": "timestamp",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case associated with the trace.",
"title": "useCaseId",
"type": "string"
},
"user": {
"description": "DataRobot application user.",
"properties": {
"id": {
"description": "The ID of the user.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the user.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "DataRobotUser",
"type": "object"
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the vector database associated with the trace.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "The settings of the vector database associated with the trace."
},
"warning": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The warning message for the prompt associated with the trace.",
"title": "warning"
}
},
"required": [
"timestamp",
"user",
"chatPromptId",
"comparisonPromptId",
"useCaseId",
"llmBlueprintId",
"llmBlueprintName",
"llmName",
"llmVendor",
"llmLicense",
"llmSettings",
"chatName",
"chatId",
"vectorDatabaseId",
"vectorDatabaseSettings",
"resultMetadata",
"resultText",
"confidenceScores",
"text",
"executionStatus",
"promptType",
"evaluationDatasetConfigurationId",
"warning"
],
"title": "PromptTraceResponse",
"type": "object"
}
PromptTraceResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatId | any | true | The ID of the chat associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatName | any | true | The name of the chat associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chatPromptId | any | true | The ID of the chat prompt associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| comparisonPromptId | any | true | The ID of the comparison prompts associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| confidenceScores | any | true | The confidence scores that measure the similarity between the prompt context and the prompt completion for the prompt associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | object | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| evaluationDatasetConfigurationId | any | true | The ID of the evaluation dataset associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| executionStatus | ExecutionStatus | true | The execution status of the prompt associated with the trace. | |
| llmBlueprintId | string | true | The ID of the LLM blueprint associated with the trace. | |
| llmBlueprintName | string | true | The name of the LLM blueprint associated with the trace. | |
| llmLicense | any | true | The usage license information for the LLM associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmName | any | true | The name of the LLM associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmSettings | any | true | The settings of the LLM associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CommonLLMSettings | false | The settings that are available for all non-custom LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CustomModelLLMSettings | false | The settings that are available for custom model LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmVendor | any | true | The vendor of the LLM associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptType | any | true | The type of prompt, chat history awair or one time prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | PromptType | false | Determines whether chat history is submitted as context to the user prompt. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| resultMetadata | any | true | The additional information about the prompt associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ResultMetadata | false | The additional information about prompt execution results. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| resultText | any | true | The completion text of the prompt associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| text | string | true | The text of the prompt associated with the trace. | |
| timestamp | string(date-time) | true | The timestamp of the trace (ISO 8601 formatted). | |
| useCaseId | string | true | The ID of the use case associated with the trace. | |
| user | DataRobotUser | true | The user associated with the trace. | |
| vectorDatabaseId | any | true | The ID of the vector database associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseSettings | any | true | The settings of the vector database associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | VectorDatabaseSettings | false | Vector database retrieval settings. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| warning | any | true | The warning message for the prompt associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
PromptType
{
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
}
PromptType
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| PromptType | string | false | Determines whether chat history is submitted as context to the user prompt. |
Enumerated Values¶
| Property | Value |
|---|---|
| PromptType | [CHAT_HISTORY_AWARE, ONE_TIME_PROMPT] |
ProviderGuardStage
{
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
}
ProviderGuardStage
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ProviderGuardStage | string | false | The data stage where the provider guard metric is acting upon. |
Enumerated Values¶
| Property | Value |
|---|---|
| ProviderGuardStage | [prompt, response] |
ProviderGuardsMetadata
{
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
}
ProviderGuardsMetadata
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | true | The name of the provider guard metric. | |
| satisfyCriteria | boolean | true | Whether the configured provider guard metric satisfied its hidden internal guard criteria. | |
| stage | ProviderGuardStage | true | The data stage where the provider guard metric is acting upon. | |
| value | any | true | The value of the provider guard metric. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
ResultMetadata
{
"description": "The additional information about prompt execution results.",
"properties": {
"blockedResultText": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The message to replace the result text if it is non empty, which represents a blocked response.",
"title": "blockedResultText"
},
"cost": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The estimated cost of executing the prompt.",
"title": "cost"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message for the prompt (in case of an errored prompt).",
"title": "errorMessage"
},
"estimatedDocsTokenCount": {
"default": 0,
"description": "The estimated number of tokens in the documents retrieved from the vector database.",
"title": "estimatedDocsTokenCount",
"type": "integer"
},
"feedbackResult": {
"description": "Prompt feedback included in the result metadata.",
"properties": {
"negativeUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is negative.",
"items": {
"type": "string"
},
"title": "negativeUserIds",
"type": "array"
},
"positiveUserIds": {
"default": [],
"description": "The list of user IDs whose feedback is positive.",
"items": {
"type": "string"
},
"title": "positiveUserIds",
"type": "array"
}
},
"title": "FeedbackResult",
"type": "object"
},
"finalPrompt": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
]
},
"type": "object"
},
"type": "array"
},
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
"type": "array"
},
{
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The final representation of the prompt that was submitted to the LLM.",
"title": "finalPrompt"
},
"inputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database).",
"title": "inputTokenCount",
"type": "integer"
},
"latencyMilliseconds": {
"description": "The latency of the LLM response (in milliseconds).",
"title": "latencyMilliseconds",
"type": "integer"
},
"metrics": {
"default": [],
"description": "The evaluation metrics for the prompt.",
"items": {
"description": "Prompt metric metadata.",
"properties": {
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model used for the metric.",
"title": "customModelId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the metric computation.",
"title": "errorMessage"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The creation status of the vector database."
},
"formattedName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted name of the metric.",
"title": "formattedName"
},
"formattedValue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The formatted value of the metric.",
"title": "formattedValue"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"name": {
"description": "The name of the metric.",
"title": "name",
"type": "string"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the NeMo Pipeline configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The id of the OOTB metric configuration.",
"title": "ootbMetricId"
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the sidecar model validation(in case of using a sidecar model deployment for the metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) that the metric applies to."
},
"value": {
"description": "The value of the metric.",
"title": "value"
}
},
"required": [
"name",
"value"
],
"title": "MetricMetadata",
"type": "object"
},
"title": "metrics",
"type": "array"
},
"outputTokenCount": {
"default": 0,
"description": "The number of tokens in the LLM output.",
"title": "outputTokenCount",
"type": "integer"
},
"providerLLMGuards": {
"anyOf": [
{
"items": {
"description": "Info on the provider guard metrics.",
"properties": {
"name": {
"description": "The name of the provider guard metric.",
"title": "name",
"type": "string"
},
"satisfyCriteria": {
"description": "Whether the configured provider guard metric satisfied its hidden internal guard criteria.",
"title": "satisfyCriteria",
"type": "boolean"
},
"stage": {
"description": "The data stage where the provider guard metric is acting upon.",
"enum": [
"prompt",
"response"
],
"title": "ProviderGuardStage",
"type": "string"
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The value of the provider guard metric.",
"title": "value"
}
},
"required": [
"satisfyCriteria",
"name",
"value",
"stage"
],
"title": "ProviderGuardsMetadata",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The provider llm guards metadata.",
"title": "providerLLMGuards"
},
"totalTokenCount": {
"default": 0,
"description": "The combined number of tokens in the LLM input and output.",
"title": "totalTokenCount",
"type": "integer"
}
},
"required": [
"latencyMilliseconds"
],
"title": "ResultMetadata",
"type": "object"
}
ResultMetadata
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| blockedResultText | any | false | The message to replace the result text if it is non empty, which represents a blocked response. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| cost | any | false | The estimated cost of executing the prompt. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | number | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| errorMessage | any | false | The error message for the prompt (in case of an errored prompt). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| estimatedDocsTokenCount | integer | false | The estimated number of tokens in the documents retrieved from the vector database. | |
| feedbackResult | FeedbackResult | false | The user feedback associated with the prompt. | |
| finalPrompt | any | false | The final representation of the prompt that was submitted to the LLM. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [object] | false | none | |
| »» additionalProperties | any | false | none |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | [object] | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | null | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [object] | false | none | |
| »» additionalProperties | any | false | none |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | [object] | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | object | false | none | |
| »» additionalProperties | any | false | none |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »»» anonymous | [object] | false | none | |
| »»»» additionalProperties | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| inputTokenCount | integer | false | The number of tokens in the LLM input. This number includes the tokens in the system prompt, the user prompt, the chat history (for history-aware chats) and the documents retrieved from the vector database (in case of using a vector database). | |
| latencyMilliseconds | integer | true | The latency of the LLM response (in milliseconds). | |
| metrics | [MetricMetadata] | false | The evaluation metrics for the prompt. | |
| outputTokenCount | integer | false | The number of tokens in the LLM output. | |
| providerLLMGuards | any | false | The provider llm guards metadata. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [ProviderGuardsMetadata] | false | [Info on the provider guard metrics.] |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| totalTokenCount | integer | false | The combined number of tokens in the LLM input and output. |
RetrieveUserLimitCounterResponse
{
"description": "API response object for retrieving user limit counters.",
"properties": {
"counter": {
"description": "The number of completed operations which count towards the usage limit.",
"title": "counter",
"type": "integer"
}
},
"required": [
"counter"
],
"title": "RetrieveUserLimitCounterResponse",
"type": "object"
}
RetrieveUserLimitCounterResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| counter | integer | true | The number of completed operations which count towards the usage limit. |
SettingFormat
{
"description": "Supported formats for settings.",
"enum": [
"multiline"
],
"title": "SettingFormat",
"type": "string"
}
SettingFormat
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| SettingFormat | string | false | Supported formats for settings. |
Enumerated Values¶
| Property | Value |
|---|---|
| SettingFormat | multiline |
SettingType
{
"description": "Supported data types for settings.",
"enum": [
"integer",
"float",
"string",
"boolean",
"object_id",
"list"
],
"title": "SettingType",
"type": "string"
}
SettingType
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| SettingType | string | false | Supported data types for settings. |
Enumerated Values¶
| Property | Value |
|---|---|
| SettingType | [integer, float, string, boolean, object_id, list] |
SidecarModelMetricMetadata
{
"description": "The metadata of a sidecar model metric.",
"properties": {
"expectedResponseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for expected response text input.",
"title": "expectedResponseColumnName"
},
"promptColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName"
},
"responseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for response text input.",
"title": "responseColumnName"
},
"targetColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName"
}
},
"required": [
"targetColumnName"
],
"title": "SidecarModelMetricMetadata",
"type": "object"
}
SidecarModelMetricMetadata
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| expectedResponseColumnName | any | false | The name of the column the custom model uses for expected response text input. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptColumnName | any | false | The name of the column the custom model uses for prompt text input. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| responseColumnName | any | false | The name of the column the custom model uses for response text input. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| targetColumnName | any | true | The name of the column the custom model uses for prediction output. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
StatusResponse
{
"description": "API response object for job execution status.",
"properties": {
"code": {
"description": "Possible job error codes. This enum exists for consistency with the DataRobot Status API.",
"enum": [
0,
1
],
"title": "JobErrorCode",
"type": "integer"
},
"created": {
"description": "The creation date of the job (ISO 8601 formatted).",
"format": "date-time",
"title": "created",
"type": "string"
},
"description": {
"default": "",
"description": "The description associated with the job.",
"title": "description",
"type": "string"
},
"message": {
"default": "",
"description": "The error message associated with the job.",
"title": "message",
"type": "string"
},
"status": {
"description": "Possible job states. Values match the DataRobot Status API.",
"enum": [
"INITIALIZED",
"RUNNING",
"COMPLETED",
"ERROR",
"ABORTED",
"EXPIRED"
],
"title": "JobExecutionState",
"type": "string"
},
"statusId": {
"description": "The ID of the job.",
"format": "uuid",
"title": "statusId",
"type": "string"
},
"statusType": {
"default": "",
"description": "The type of the status object.",
"title": "statusType",
"type": "string"
}
},
"required": [
"statusId",
"status",
"created",
"code"
],
"title": "StatusResponse",
"type": "object"
}
StatusResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| code | JobErrorCode | true | The error code associated with the job. | |
| created | string(date-time) | true | The creation date of the job (ISO 8601 formatted). | |
| description | string | false | The description associated with the job. | |
| message | string | false | The error message associated with the job. | |
| status | JobExecutionState | true | The execution status of the job. | |
| statusId | string(uuid) | true | The ID of the job. | |
| statusType | string | false | The type of the status object. |
StringSettingConstraints
{
"description": "Available constraints for string settings.",
"properties": {
"allowedChoices": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The allowed values for the setting.",
"title": "allowedChoices"
},
"maxLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum length of the value (inclusive).",
"title": "maxLength"
},
"minLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum length of the value (inclusive).",
"title": "minLength"
},
"type": {
"const": "string",
"default": "string",
"description": "The data type of the setting.",
"title": "type",
"type": "string"
}
},
"title": "StringSettingConstraints",
"type": "object"
}
StringSettingConstraints
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| allowedChoices | any | false | The allowed values for the setting. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [string] | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| maxLength | any | false | The maximum length of the value (inclusive). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| minLength | any | false | The minimum length of the value (inclusive). |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| type | string | false | The data type of the setting. |
SupportedCustomModelLLMValidation
{
"description": "The metadata describing a validated custom model LLM.",
"properties": {
"id": {
"description": "The ID of the custom model LLM validation.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the custom model LLM validation.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "SupportedCustomModelLLMValidation",
"type": "object"
}
SupportedCustomModelLLMValidation
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| id | string | true | The ID of the custom model LLM validation. | |
| name | string | true | The name of the custom model LLM validation. |
SupportedDeploymentType
{
"description": "The type of the target output a DataRobot deployment produces.",
"enum": [
"TEXT_GENERATION",
"VECTOR_DATABASE",
"UNSTRUCTURED",
"REGRESSION",
"MULTICLASS",
"BINARY",
"NOT_SUPPORTED"
],
"title": "SupportedDeploymentType",
"type": "string"
}
SupportedDeploymentType
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| SupportedDeploymentType | string | false | The type of the target output a DataRobot deployment produces. |
Enumerated Values¶
| Property | Value |
|---|---|
| SupportedDeploymentType | [TEXT_GENERATION, VECTOR_DATABASE, UNSTRUCTURED, REGRESSION, MULTICLASS, BINARY, NOT_SUPPORTED] |
SupportedInsightsResponse
{
"description": "Response model for supported insights.",
"properties": {
"insightsConfiguration": {
"description": "The list of supported insights configurations.",
"items": {
"description": "The configuration of insights with extra data.",
"properties": {
"aggregationTypes": {
"anyOf": [
{
"items": {
"description": "The type of the metric aggregation.",
"enum": [
"average",
"percentYes",
"classPercentCoverage",
"ngramImportance",
"guardConditionPercentYes"
],
"title": "AggregationType",
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The aggregation types used in the insights configuration.",
"title": "aggregationTypes"
},
"costConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the cost configuration.",
"title": "costConfigurationId"
},
"customMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom metric (if using a custom metric).",
"title": "customMetricId"
},
"customModelLLMValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model LLM validation if using a custom model LLM for OOTB metrics.",
"title": "customModelLLMValidationId"
},
"deploymentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the custom model deployment associated with the insight.",
"title": "deploymentId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the evaluation dataset configuration or sidecar model metric validation or OOTB metric.",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The error type associated with the insight error status and error message as an indicator of what fields needs to be edited if any.",
"title": "errorResolution"
},
"evaluationDatasetConfigurationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the evaluation dataset configuration.",
"title": "evaluationDatasetConfigurationId"
},
"executionStatus": {
"anyOf": [
{
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
{
"type": "null"
}
],
"description": "The execution status of the evaluation dataset configuration."
},
"insightName": {
"description": "The name of the insight.",
"maxLength": 5000,
"minLength": 1,
"title": "insightName",
"type": "string"
},
"insightType": {
"anyOf": [
{
"description": "The type of insight.",
"enum": [
"Reference",
"Quality metric",
"Operational metric",
"Evaluation deployment",
"Custom metric",
"Nemo"
],
"title": "InsightTypes",
"type": "string"
},
{
"type": "null"
}
],
"description": "The type of the insight."
},
"isTransferable": {
"default": false,
"description": "Indicates if insight can be transferred to production.",
"title": "isTransferable",
"type": "boolean"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "The LLM ID for OOTB metrics that use LLMs."
},
"llmIsActive": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is active.",
"title": "llmIsActive"
},
"llmIsDeprecated": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Whether the LLM is deprecated and will be removed in a future release.",
"title": "llmIsDeprecated"
},
"modelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the model associated with `deploymentId`.",
"title": "modelId"
},
"modelPackageRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the registered model package associated with `deploymentId`.",
"title": "modelPackageRegisteredModelId"
},
"moderationConfiguration": {
"anyOf": [
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithID",
"type": "object"
},
{
"description": "Moderation Configuration associated with an insight.",
"properties": {
"guardConditions": {
"description": "The guard conditions associated with a metric.",
"items": {
"description": "The guard condition for a metric.",
"properties": {
"comparand": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "boolean"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "The comparand(s) used in the guard condition.",
"title": "comparand"
},
"comparator": {
"description": "The comparator used in a guard condition.",
"enum": [
"greaterThan",
"lessThan",
"equals",
"notEquals",
"is",
"isNot",
"matches",
"doesNotMatch",
"contains",
"doesNotContain"
],
"title": "GuardConditionComparator",
"type": "string"
}
},
"required": [
"comparator",
"comparand"
],
"title": "GuardCondition",
"type": "object"
},
"maxItems": 1,
"minItems": 1,
"title": "guardConditions",
"type": "array"
},
"intervention": {
"description": "The intervention configuration for a metric.",
"properties": {
"action": {
"description": "The moderation strategy.",
"enum": [
"block",
"report",
"reportAndBlock"
],
"title": "ModerationAction",
"type": "string"
},
"message": {
"description": "The intervention message to replace the prediction when a guard condition is satisfied.",
"minLength": 1,
"title": "message",
"type": "string"
}
},
"required": [
"action",
"message"
],
"title": "Intervention",
"type": "object"
}
},
"required": [
"guardConditions",
"intervention"
],
"title": "ModerationConfigurationWithoutID",
"type": "object"
},
{
"type": "null"
}
],
"description": "The moderation configuration associated with the insight configuration.",
"title": "moderationConfiguration"
},
"nemoMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the Nemo configuration.",
"title": "nemoMetricId"
},
"ootbMetricId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the ootb metric (if using an ootb metric).",
"title": "ootbMetricId"
},
"ootbMetricName": {
"anyOf": [
{
"description": "The Out-Of-The-Box metric name that can be used in the playground.",
"enum": [
"latency",
"citations",
"rouge_1",
"faithfulness",
"correctness",
"prompt_tokens",
"response_tokens",
"document_tokens",
"all_tokens",
"jailbreak_violation",
"toxicity_violation",
"pii_violation",
"exact_match",
"starts_with",
"contains"
],
"title": "OOTBMetricInsightNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The OOTB metric name."
},
"resultUnit": {
"anyOf": [
{
"description": "The unit of measurement associated with a metric.",
"enum": [
"s",
"ms",
"%"
],
"title": "MetricUnit",
"type": "string"
},
{
"type": "null"
}
],
"description": "The unit of measurement associated with the insight result."
},
"sidecarModelMetricMetadata": {
"anyOf": [
{
"description": "The metadata of a sidecar model metric.",
"properties": {
"expectedResponseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for expected response text input.",
"title": "expectedResponseColumnName"
},
"promptColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prompt text input.",
"title": "promptColumnName"
},
"responseColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for response text input.",
"title": "responseColumnName"
},
"targetColumnName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the column the custom model uses for prediction output.",
"title": "targetColumnName"
}
},
"required": [
"targetColumnName"
],
"title": "SidecarModelMetricMetadata",
"type": "object"
},
{
"type": "null"
}
],
"description": "The metadata of the sidecar model metric (if using a sidecar model metric)."
},
"sidecarModelMetricValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the sidecar model metric validation (if using a sidecar model metric).",
"title": "sidecarModelMetricValidationId"
},
"stage": {
"anyOf": [
{
"description": "Enum that describes at which stage the metric may be calculated.",
"enum": [
"prompt_pipeline",
"response_pipeline"
],
"title": "PipelineStage",
"type": "string"
},
{
"type": "null"
}
],
"description": "The stage (prompt or response) where insight is calculated at."
}
},
"required": [
"insightName",
"aggregationTypes"
],
"title": "InsightsConfigurationWithAdditionalData",
"type": "object"
},
"title": "insightsConfiguration",
"type": "array"
}
},
"required": [
"insightsConfiguration"
],
"title": "SupportedInsightsResponse",
"type": "object"
}
SupportedInsightsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| insightsConfiguration | [InsightsConfigurationWithAdditionalData] | true | The list of supported insights configurations. |
TraceChat
{
"description": "Reference to a chat or comparison chat available in a trace.",
"properties": {
"id": {
"description": "The ID of the chat associated with the trace.",
"title": "id",
"type": "string"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name of the chat associated with the trace.",
"title": "name"
}
},
"required": [
"id",
"name"
],
"title": "TraceChat",
"type": "object"
}
TraceChat
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| id | string | true | The ID of the chat associated with the trace. | |
| name | any | true | Name of the chat associated with the trace. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
TraceDatasetResponse
{
"description": "API response for prompt traces export request.",
"properties": {
"aiCatalogId": {
"description": "The Data Registry dataset ID.",
"title": "aiCatalogId",
"type": "string"
}
},
"required": [
"aiCatalogId"
],
"title": "TraceDatasetResponse",
"type": "object"
}
TraceDatasetResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| aiCatalogId | string | true | The Data Registry dataset ID. |
TraceMetadataResponse
{
"description": "API response for prompt trace metadata retrieval request.",
"properties": {
"chats": {
"description": "The list of combined chat and comparison prompt chats available in trace.",
"items": {
"description": "Reference to a chat or comparison chat available in a trace.",
"properties": {
"id": {
"description": "The ID of the chat associated with the trace.",
"title": "id",
"type": "string"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Name of the chat associated with the trace.",
"title": "name"
}
},
"required": [
"id",
"name"
],
"title": "TraceChat",
"type": "object"
},
"title": "chats",
"type": "array"
},
"users": {
"description": "The list of unique users available in the trace response.",
"items": {
"description": "DataRobot application user.",
"properties": {
"id": {
"description": "The ID of the user.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the user.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "DataRobotUser",
"type": "object"
},
"title": "users",
"type": "array"
}
},
"required": [
"users",
"chats"
],
"title": "TraceMetadataResponse",
"type": "object"
}
TraceMetadataResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chats | [TraceChat] | true | The list of combined chat and comparison prompt chats available in trace. | |
| users | [DataRobotUser] | true | The list of unique users available in the trace response. |
UpdateLLMBlueprintRequest
{
"description": "The body of the Update LLM Blueprint request.",
"properties": {
"description": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, updates the LLM blueprint description to this value.",
"title": "description"
},
"isSaved": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "If specified, updates the saved status of the LLM blueprint to this value.",
"title": "isSaved"
},
"isStarred": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "If specified, updates the starred status of the LLM blueprint to this value.",
"title": "isStarred"
},
"llmId": {
"anyOf": [
{
"description": "The ID that defines the type of the LLM.",
"enum": [
"azure-openai-gpt-3.5-turbo",
"azure-openai-gpt-3.5-turbo-16k",
"azure-openai-gpt-4",
"azure-openai-gpt-4-32k",
"azure-openai-gpt-4-turbo",
"azure-openai-gpt-4-o",
"azure-openai-gpt-4-o-mini",
"amazon-titan",
"amazon-nova-micro",
"amazon-nova-lite",
"amazon-nova-pro",
"anthropic-claude-2",
"anthropic-claude-3-haiku",
"anthropic-claude-3-sonnet",
"anthropic-claude-3-opus",
"anthropic-claude-3.5-sonnet-v1",
"amazon-anthropic-claude-3.5-sonnet-v2",
"google-bison",
"google-gemini-1.5-flash",
"google-gemini-1.5-pro",
"custom-model"
],
"title": "LanguageModelTypeId",
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the LLM used by the LLM blueprint."
},
"llmSettings": {
"anyOf": [
{
"additionalProperties": false,
"description": "The settings that are available for all non-custom LLMs.",
"properties": {
"maxCompletionLength": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Maximum number of tokens allowed in the completion. The combined count of this value and prompt tokens must be below the model's maximum context size, where prompt token count is comprised of system prompt, user prompt, recent chat history, and vector database citations.",
"title": "maxCompletionLength"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.",
"title": "temperature"
},
"topP": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Top P sets a threshold that controls the selection of words included in the response, based on a cumulative probability cutoff for token selection. For example, 0.2 considers only the top 20% probability mass. Higher numbers return more diverse options for outputs.",
"title": "topP"
}
},
"title": "CommonLLMSettings",
"type": "object"
},
{
"additionalProperties": false,
"description": "The settings that are available for custom model LLMs.",
"properties": {
"externalLlmContextSize": {
"anyOf": [
{
"maximum": 128000,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The external LLM's context size, in tokens. This value is only used for pruning documents supplied to the LLM when a vector database is associated with the LLM blueprint. It does not affect the external LLM's actual context size in any way and is not supplied to the LLM.",
"title": "externalLlmContextSize"
},
"systemPrompt": {
"anyOf": [
{
"maxLength": 500000,
"type": "string"
},
{
"type": "null"
}
],
"description": "System prompt guides the style of the LLM response. It is a \"universal\" prompt, prepended to all individual prompts.",
"title": "systemPrompt"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model LLM.",
"title": "validationId"
}
},
"title": "CustomModelLLMSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "If specified, updates the LLM settings to these values.",
"title": "llmSettings"
},
"name": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, renames the LLM blueprint to this value.",
"title": "name"
},
"promptType": {
"anyOf": [
{
"description": "Determines whether chat history is submitted as context to the user prompt.",
"enum": [
"CHAT_HISTORY_AWARE",
"ONE_TIME_PROMPT"
],
"title": "PromptType",
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, updates the chat context behavior of the LLM blueprint to this value."
},
"vectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "If specified, changes the vector database used by the LLM blueprint. If the specified value is `null`, unlinks the vector database from the LLM blueprint. If omitted, the currently used vector database remains in use.",
"title": "vectorDatabaseId"
},
"vectorDatabaseSettings": {
"anyOf": [
{
"description": "Specifies the vector database retrieval settings in LLM blueprint API requests.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettingsRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "If specified, updates the vector database retrieval settings to these values."
}
},
"title": "UpdateLLMBlueprintRequest",
"type": "object"
}
UpdateLLMBlueprintRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| description | any | false | If specified, updates the LLM blueprint description to this value. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| isSaved | any | false | If specified, updates the saved status of the LLM blueprint to this value. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | boolean | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| isStarred | any | false | If specified, updates the starred status of the LLM blueprint to this value. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | boolean | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmId | any | false | If specified, changes the LLM used by the LLM blueprint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | LanguageModelTypeId | false | The ID that defines the type of the LLM. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| llmSettings | any | false | If specified, updates the LLM settings to these values. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CommonLLMSettings | false | The settings that are available for all non-custom LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CustomModelLLMSettings | false | The settings that are available for custom model LLMs. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | any | false | If specified, renames the LLM blueprint to this value. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| promptType | any | false | If specified, updates the chat context behavior of the LLM blueprint to this value. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | PromptType | false | Determines whether chat history is submitted as context to the user prompt. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseId | any | false | If specified, changes the vector database used by the LLM blueprint. If the specified value is null, unlinks the vector database from the LLM blueprint. If omitted, the currently used vector database remains in use. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| vectorDatabaseSettings | any | false | If specified, updates the vector database retrieval settings to these values. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | VectorDatabaseSettingsRequest | false | Specifies the vector database retrieval settings in LLM blueprint API requests. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
ValidationError
{
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "loc",
"type": "array"
},
"msg": {
"title": "msg",
"type": "string"
},
"type": {
"title": "type",
"type": "string"
}
},
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError",
"type": "object"
}
ValidationError
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| loc | [anyOf] | true | none |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| msg | string | true | none | |
| type | string | true | none |
VectorDatabaseRetrievers
{
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
VectorDatabaseRetrievers
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| VectorDatabaseRetrievers | string | false | The method used to retrieve relevant chunks from the vector database. |
Enumerated Values¶
| Property | Value |
|---|---|
| VectorDatabaseRetrievers | [SINGLE_LOOKUP_RETRIEVER, CONVERSATIONAL_RETRIEVER, MULTI_STEP_RETRIEVER] |
VectorDatabaseSettings
{
"description": "Vector database retrieval settings.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettings",
"type": "object"
}
VectorDatabaseSettings
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| addNeighborChunks | boolean | false | Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1. | |
| maxDocumentsRetrievedPerPrompt | any | false | The maximum number of chunks to retrieve from the vector database. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | maximum: 10 minimum: 1 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| maxTokens | any | false | The maximum number of tokens to retrieve from the vector database. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | maximum: 51200 minimum: 1 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| retriever | VectorDatabaseRetrievers | false | The method used to retrieve relevant chunks from the vector database. |
VectorDatabaseSettingsRequest
{
"description": "Specifies the vector database retrieval settings in LLM blueprint API requests.",
"properties": {
"addNeighborChunks": {
"default": false,
"description": "Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1.",
"title": "addNeighborChunks",
"type": "boolean"
},
"maxDocumentsRetrievedPerPrompt": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of chunks to retrieve from the vector database.",
"title": "maxDocumentsRetrievedPerPrompt"
},
"maxTokens": {
"anyOf": [
{
"maximum": 51200,
"minimum": 128,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum number of tokens to retrieve from the vector database.",
"title": "maxTokens"
},
"retriever": {
"description": "The method used to retrieve relevant chunks from the vector database.",
"enum": [
"SINGLE_LOOKUP_RETRIEVER",
"CONVERSATIONAL_RETRIEVER",
"MULTI_STEP_RETRIEVER"
],
"title": "VectorDatabaseRetrievers",
"type": "string"
}
},
"title": "VectorDatabaseSettingsRequest",
"type": "object"
}
VectorDatabaseSettingsRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| addNeighborChunks | boolean | false | Add neighboring chunks to those that the similarity search retrieves, such that when selected, search returns i, i-1, and i+1. | |
| maxDocumentsRetrievedPerPrompt | any | false | The maximum number of chunks to retrieve from the vector database. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | maximum: 10 minimum: 1 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| maxTokens | any | false | The maximum number of tokens to retrieve from the vector database. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | maximum: 51200 minimum: 128 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| retriever | VectorDatabaseRetrievers | false | The method used to retrieve relevant chunks from the vector database. |