Skip to content

On-premise users: click in-app to access the full platform documentation for your version of DataRobot.

LLM Blueprints (GenAI)

This page outlines the operations, endpoints, parameters, and example requests and responses for the LLM Blueprints (GenAI).

GET /api/v2/genai/llmBlueprints/

List LLM blueprints.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/genai/llmBlueprints/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
playgroundId query string 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 boolean false Retrieve only the LLM blueprints that have the specified draft/saved status.
isStarred query boolean 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.

Example responses

200 Response

{
  "count": 0,
  "data": [
    {
      "creationDate": "2019-08-24T14:15:22Z",
      "creationUserId": "string",
      "customModelLLMErrorMessage": "An unknown external LLM error occurred.",
      "customModelLLMErrorResolution": "An unknown error during custom model LLM retrieval or execution occured. Please validate the custom model LLM if applicable. Otherwise contact the DataRobot team for assistance.",
      "customModelLLMValidationStatus": "TESTING",
      "description": "string",
      "id": "string",
      "isSaved": true,
      "isStarred": true,
      "lastUpdateDate": "2019-08-24T14:15:22Z",
      "lastUpdateUserId": "string",
      "llmId": "azure-openai-gpt-3.5-turbo",
      "llmName": "string",
      "llmSettings": {
        "maxCompletionLength": 0,
        "systemPrompt": "string",
        "temperature": 0,
        "topP": 0
      },
      "name": "string",
      "playgroundId": "string",
      "promptType": "CHAT_HISTORY_AWARE",
      "vectorDatabaseErrorMessage": "Unknown vector database error occurred",
      "vectorDatabaseErrorResolution": "An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance.",
      "vectorDatabaseId": "string",
      "vectorDatabaseName": "string",
      "vectorDatabaseSettings": {
        "maxDocumentsRetrievedPerPrompt": 10,
        "maxTokens": 0
      },
      "vectorDatabaseStatus": "NEW"
    }
  ],
  "next": "string",
  "previous": "string",
  "totalCount": 0
}

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.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/genai/llmBlueprints/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "description": "",
  "llmId": "azure-openai-gpt-3.5-turbo",
  "llmSettings": {
    "maxCompletionLength": 0,
    "systemPrompt": "string",
    "temperature": 0,
    "topP": 0
  },
  "name": "string",
  "playgroundId": "string",
  "promptType": "CHAT_HISTORY_AWARE",
  "vectorDatabaseId": "string",
  "vectorDatabaseSettings": {
    "maxDocumentsRetrievedPerPrompt": 10,
    "maxTokens": 0
  }
}

Parameters

Name In Type Required Description
body body CreateLLMBlueprintRequest true none

Example responses

201 Response

{
  "creationDate": "2019-08-24T14:15:22Z",
  "creationUserId": "string",
  "customModelLLMErrorMessage": "An unknown external LLM error occurred.",
  "customModelLLMErrorResolution": "An unknown error during custom model LLM retrieval or execution occured. Please validate the custom model LLM if applicable. Otherwise contact the DataRobot team for assistance.",
  "customModelLLMValidationStatus": "TESTING",
  "description": "string",
  "id": "string",
  "isSaved": true,
  "isStarred": true,
  "lastUpdateDate": "2019-08-24T14:15:22Z",
  "lastUpdateUserId": "string",
  "llmId": "azure-openai-gpt-3.5-turbo",
  "llmName": "string",
  "llmSettings": {
    "maxCompletionLength": 0,
    "systemPrompt": "string",
    "temperature": 0,
    "topP": 0
  },
  "name": "string",
  "playgroundId": "string",
  "promptType": "CHAT_HISTORY_AWARE",
  "vectorDatabaseErrorMessage": "Unknown vector database error occurred",
  "vectorDatabaseErrorResolution": "An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance.",
  "vectorDatabaseId": "string",
  "vectorDatabaseName": "string",
  "vectorDatabaseSettings": {
    "maxDocumentsRetrievedPerPrompt": 10,
    "maxTokens": 0
  },
  "vectorDatabaseStatus": "NEW"
}

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.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/genai/llmBlueprints/fromChatPrompt/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "chatPromptId": "string",
  "description": "",
  "name": "string"
}

Parameters

Name In Type Required Description
body body CreateFromChatPromptRequest true none

Example responses

201 Response

{
  "creationDate": "2019-08-24T14:15:22Z",
  "creationUserId": "string",
  "customModelLLMErrorMessage": "An unknown external LLM error occurred.",
  "customModelLLMErrorResolution": "An unknown error during custom model LLM retrieval or execution occured. Please validate the custom model LLM if applicable. Otherwise contact the DataRobot team for assistance.",
  "customModelLLMValidationStatus": "TESTING",
  "description": "string",
  "id": "string",
  "isSaved": true,
  "isStarred": true,
  "lastUpdateDate": "2019-08-24T14:15:22Z",
  "lastUpdateUserId": "string",
  "llmId": "azure-openai-gpt-3.5-turbo",
  "llmName": "string",
  "llmSettings": {
    "maxCompletionLength": 0,
    "systemPrompt": "string",
    "temperature": 0,
    "topP": 0
  },
  "name": "string",
  "playgroundId": "string",
  "promptType": "CHAT_HISTORY_AWARE",
  "vectorDatabaseErrorMessage": "Unknown vector database error occurred",
  "vectorDatabaseErrorResolution": "An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance.",
  "vectorDatabaseId": "string",
  "vectorDatabaseName": "string",
  "vectorDatabaseSettings": {
    "maxDocumentsRetrievedPerPrompt": 10,
    "maxTokens": 0
  },
  "vectorDatabaseStatus": "NEW"
}

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.

Code samples

# You can also use wget
curl -X POST https://app.datarobot.com/api/v2/genai/llmBlueprints/fromLLMBlueprint/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "description": "",
  "llmBlueprintId": "string",
  "name": "string"
}

Parameters

Name In Type Required Description
body body CreateFromLLMBlueprintRequest true none

Example responses

201 Response

{
  "creationDate": "2019-08-24T14:15:22Z",
  "creationUserId": "string",
  "customModelLLMErrorMessage": "An unknown external LLM error occurred.",
  "customModelLLMErrorResolution": "An unknown error during custom model LLM retrieval or execution occured. Please validate the custom model LLM if applicable. Otherwise contact the DataRobot team for assistance.",
  "customModelLLMValidationStatus": "TESTING",
  "description": "string",
  "id": "string",
  "isSaved": true,
  "isStarred": true,
  "lastUpdateDate": "2019-08-24T14:15:22Z",
  "lastUpdateUserId": "string",
  "llmId": "azure-openai-gpt-3.5-turbo",
  "llmName": "string",
  "llmSettings": {
    "maxCompletionLength": 0,
    "systemPrompt": "string",
    "temperature": 0,
    "topP": 0
  },
  "name": "string",
  "playgroundId": "string",
  "promptType": "CHAT_HISTORY_AWARE",
  "vectorDatabaseErrorMessage": "Unknown vector database error occurred",
  "vectorDatabaseErrorResolution": "An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance.",
  "vectorDatabaseId": "string",
  "vectorDatabaseName": "string",
  "vectorDatabaseSettings": {
    "maxDocumentsRetrievedPerPrompt": 10,
    "maxTokens": 0
  },
  "vectorDatabaseStatus": "NEW"
}

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.

Code samples

# You can also use wget
curl -X DELETE https://app.datarobot.com/api/v2/genai/llmBlueprints/{llmBlueprintId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
llmBlueprintId path string true The ID of the LLM blueprint to delete.

Example responses

422 Response

{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}

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.

Code samples

# You can also use wget
curl -X GET https://app.datarobot.com/api/v2/genai/llmBlueprints/{llmBlueprintId}/ \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Parameters

Name In Type Required Description
llmBlueprintId path string true The ID of the LLM blueprint to retrieve.

Example responses

200 Response

{
  "creationDate": "2019-08-24T14:15:22Z",
  "creationUserId": "string",
  "customModelLLMErrorMessage": "An unknown external LLM error occurred.",
  "customModelLLMErrorResolution": "An unknown error during custom model LLM retrieval or execution occured. Please validate the custom model LLM if applicable. Otherwise contact the DataRobot team for assistance.",
  "customModelLLMValidationStatus": "TESTING",
  "description": "string",
  "id": "string",
  "isSaved": true,
  "isStarred": true,
  "lastUpdateDate": "2019-08-24T14:15:22Z",
  "lastUpdateUserId": "string",
  "llmId": "azure-openai-gpt-3.5-turbo",
  "llmName": "string",
  "llmSettings": {
    "maxCompletionLength": 0,
    "systemPrompt": "string",
    "temperature": 0,
    "topP": 0
  },
  "name": "string",
  "playgroundId": "string",
  "promptType": "CHAT_HISTORY_AWARE",
  "vectorDatabaseErrorMessage": "Unknown vector database error occurred",
  "vectorDatabaseErrorResolution": "An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance.",
  "vectorDatabaseId": "string",
  "vectorDatabaseName": "string",
  "vectorDatabaseSettings": {
    "maxDocumentsRetrievedPerPrompt": 10,
    "maxTokens": 0
  },
  "vectorDatabaseStatus": "NEW"
}

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.

Code samples

# You can also use wget
curl -X PATCH https://app.datarobot.com/api/v2/genai/llmBlueprints/{llmBlueprintId}/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {access-token}"

Body parameter

{
  "description": "string",
  "isSaved": true,
  "isStarred": true,
  "llmId": "azure-openai-gpt-3.5-turbo",
  "llmSettings": {
    "maxCompletionLength": 0,
    "systemPrompt": "string",
    "temperature": 0,
    "topP": 0
  },
  "name": "string",
  "promptType": "CHAT_HISTORY_AWARE",
  "vectorDatabaseId": "string",
  "vectorDatabaseSettings": {
    "maxDocumentsRetrievedPerPrompt": 10,
    "maxTokens": 0
  }
}

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

{
  "creationDate": "2019-08-24T14:15:22Z",
  "creationUserId": "string",
  "customModelLLMErrorMessage": "An unknown external LLM error occurred.",
  "customModelLLMErrorResolution": "An unknown error during custom model LLM retrieval or execution occured. Please validate the custom model LLM if applicable. Otherwise contact the DataRobot team for assistance.",
  "customModelLLMValidationStatus": "TESTING",
  "description": "string",
  "id": "string",
  "isSaved": true,
  "isStarred": true,
  "lastUpdateDate": "2019-08-24T14:15:22Z",
  "lastUpdateUserId": "string",
  "llmId": "azure-openai-gpt-3.5-turbo",
  "llmName": "string",
  "llmSettings": {
    "maxCompletionLength": 0,
    "systemPrompt": "string",
    "temperature": 0,
    "topP": 0
  },
  "name": "string",
  "playgroundId": "string",
  "promptType": "CHAT_HISTORY_AWARE",
  "vectorDatabaseErrorMessage": "Unknown vector database error occurred",
  "vectorDatabaseErrorResolution": "An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance.",
  "vectorDatabaseId": "string",
  "vectorDatabaseName": "string",
  "vectorDatabaseSettings": {
    "maxDocumentsRetrievedPerPrompt": 10,
    "maxTokens": 0
  },
  "vectorDatabaseStatus": "NEW"
}

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

Schemas

CommonLLMSettings

{
  "maxCompletionLength": 0,
  "systemPrompt": "string",
  "temperature": 0,
  "topP": 0
}

CommonLLMSettings

Properties

Name Type Required Restrictions Description
maxCompletionLength integer¦null 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.
systemPrompt string¦null false maxLength: 500000
System prompt guides the style of the LLM response. It is a "universal" prompt, prepended to all individual prompts.
temperature number¦null false Temperature controls the randomness of model output, where higher values return more diverse output and lower values return more deterministic results.
topP number¦null 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.

CreateFromChatPromptRequest

{
  "chatPromptId": "string",
  "description": "",
  "name": "string"
}

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": "",
  "llmBlueprintId": "string",
  "name": "string"
}

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": "",
  "llmId": "azure-openai-gpt-3.5-turbo",
  "llmSettings": {
    "maxCompletionLength": 0,
    "systemPrompt": "string",
    "temperature": 0,
    "topP": 0
  },
  "name": "string",
  "playgroundId": "string",
  "promptType": "CHAT_HISTORY_AWARE",
  "vectorDatabaseId": "string",
  "vectorDatabaseSettings": {
    "maxDocumentsRetrievedPerPrompt": 10,
    "maxTokens": 0
  }
}

CreateLLMBlueprintRequest

Properties

Name Type Required Restrictions Description
description string false maxLength: 5000
The description of the LLM blueprint.
llmId LanguageModelTypeId¦null false The ID of the LLM selected for this LLM blueprint.
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.

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 string¦null false The ID of the vector database linked to this LLM blueprint.
vectorDatabaseSettings VectorDatabaseSettings¦null false A key/value dictionary of vector database settings.

CustomModelLLMErrorMessages

"An unknown external LLM error occurred."

CustomModelLLMErrorMessages

Properties

Name Type Required Restrictions Description
CustomModelLLMErrorMessages string false Error messages for custom model LLMs.

Enumerated Values

Property Value
CustomModelLLMErrorMessages [An unknown external LLM error occurred., A LLM prediction timeout error occurred., API token was deleted or revoked., External LLM access failed., External LLM does not exist or was deleted., External LLM has been unlinked., External LLM deployment has been deleted., No access to the external LLM deployment., Only unstructured deployment types are supported., An API token is required but was not provided in the request., Deployment prediction server did not accept the request., Deployment prediction does not comply with the expected format.]

CustomModelLLMErrorResolutions

"An unknown error during custom model LLM retrieval or execution occured. Please validate the custom model LLM if applicable. Otherwise contact the DataRobot team for assistance."

CustomModelLLMErrorResolutions

Properties

Name Type Required Restrictions Description
CustomModelLLMErrorResolutions string false The suggested error resolutions for custom model LLM errors.

Enumerated Values

Property Value
CustomModelLLMErrorResolutions [An unknown error during custom model LLM retrieval or execution occured. Please validate the custom model LLM if applicable. Otherwise contact the DataRobot team for assistance., A prediction timeout error occured for your custom model LLM. Please increase your prediction timeout for your custom model validation. And then try revalidating the custom model again. Otherwise contact the DataRobot team for assistance., The API token of the deployed custom model LLM was deleted or revoked. Please validate and recreate the custom model LLM using API access with your new token., An unknown error during retrieval of the custom model LLM occured. Please contact the DataRobot team for assistance., The linked custom model LLM does not exist or was deleted. Please create a custom model LLM and create a new LLM blueprint., The model of the deployed custom model LLM has been replaced with another model that isn't validated. You can replace the model in deployment back and use the API to revalidate it or validate a new custom model LLM from the deployment., The deployment for your custom model LLM was deleted. Please create a new custom model LLM from the deployment you have access to., Access to your custom model LLM deployment was revoked. Please create a new custom model LLM from the deployment you have access to., The deployment type of the custom model LLM is not supported. Please make sure the target type for your deployment is Unstructured or TextGeneration., You are attempting to access a custom model LLM validation through non-token authentication methods. Currently only token-based authentication is allowed., The prediction request to the deployed custom model LLM failed. Please make sure your deployment accepts JSON or CSV input with specified prompt column name., The prediction response to the deployment has an invalid format. Make sure your unstructured deployment responds with valid JSON with specified target column name.]

CustomModelLLMSettings

{
  "systemPrompt": "string",
  "validationId": "string"
}

CustomModelLLMSettings

Properties

Name Type Required Restrictions Description
systemPrompt string¦null false maxLength: 500000
System prompt guides the style of the LLM response. It is a "universal" prompt, prepended to all individual prompts.
validationId string¦null false The validation ID of the custom model LLM.

CustomModelValidationStatus

"TESTING"

CustomModelValidationStatus

Properties

Name Type Required Restrictions Description
CustomModelValidationStatus string false Status of custom model validation.

Enumerated Values

Property Value
CustomModelValidationStatus [TESTING, PASSED, FAILED]

ExecutionStatus

"NEW"

ExecutionStatus

Properties

Name Type Required Restrictions Description
ExecutionStatus string false Job execution status.

Enumerated Values

Property Value
ExecutionStatus [NEW, RUNNING, COMPLETED, ERROR]

HTTPValidationErrorResponse

{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}

HTTPValidationErrorResponse

Properties

Name Type Required Restrictions Description
detail [ValidationError] false none

LLMBlueprintResponse

{
  "creationDate": "2019-08-24T14:15:22Z",
  "creationUserId": "string",
  "customModelLLMErrorMessage": "An unknown external LLM error occurred.",
  "customModelLLMErrorResolution": "An unknown error during custom model LLM retrieval or execution occured. Please validate the custom model LLM if applicable. Otherwise contact the DataRobot team for assistance.",
  "customModelLLMValidationStatus": "TESTING",
  "description": "string",
  "id": "string",
  "isSaved": true,
  "isStarred": true,
  "lastUpdateDate": "2019-08-24T14:15:22Z",
  "lastUpdateUserId": "string",
  "llmId": "azure-openai-gpt-3.5-turbo",
  "llmName": "string",
  "llmSettings": {
    "maxCompletionLength": 0,
    "systemPrompt": "string",
    "temperature": 0,
    "topP": 0
  },
  "name": "string",
  "playgroundId": "string",
  "promptType": "CHAT_HISTORY_AWARE",
  "vectorDatabaseErrorMessage": "Unknown vector database error occurred",
  "vectorDatabaseErrorResolution": "An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance.",
  "vectorDatabaseId": "string",
  "vectorDatabaseName": "string",
  "vectorDatabaseSettings": {
    "maxDocumentsRetrievedPerPrompt": 10,
    "maxTokens": 0
  },
  "vectorDatabaseStatus": "NEW"
}

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.
customModelLLMErrorMessage CustomModelLLMErrorMessages¦null true The error message of the custom model LLM (if using a custom model LLM).
customModelLLMErrorResolution CustomModelLLMErrorResolutions¦null true The suggested error resolution for the custom model LLM (if using a custom model LLM).
customModelLLMValidationStatus CustomModelValidationStatus¦null true The validation status of the custom model LLM (if using a custom model LLM).
description string true The description of the LLM blueprint.
id string true The ID of the LLM blueprint.
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 LanguageModelTypeId¦null false The ID of the LLM selected for this LLM blueprint.
llmName string¦null true The name of the LLM used by this LLM blueprint.
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.

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.
vectorDatabaseErrorMessage VectorDatabaseErrorMessages¦null true The error message of the vector database associated with this LLM.
vectorDatabaseErrorResolution any true The suggested error resolution for the vector database associated with this LLM blueprint.

anyOf

Name Type Required Restrictions Description
» anonymous VectorDatabaseErrorResolutions false Vector database resolutions are not part of the vector database API response,
but added to llm-blueprint and chat- and comparison-prompt responses
to provide the user verbose information on how to resolve existing issues.

or

Name Type Required Restrictions Description
» anonymous VectorDatabaseErrorResolutionsForDrafts false Error resolutions for vector databases used in blueprint drafts.

continued

Name Type Required Restrictions Description
vectorDatabaseId string¦null false The ID of the vector database linked to this LLM blueprint.
vectorDatabaseName string¦null true The name of the vector database associated with this LLM blueprint.
vectorDatabaseSettings VectorDatabaseSettings¦null false A key/value dictionary of vector database settings.
vectorDatabaseStatus ExecutionStatus¦null true The creation status of the vector database associated with this LLM blueprint.

LanguageModelTypeId

"azure-openai-gpt-3.5-turbo"

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, amazon-titan, anthropic-claude-2, google-bison, custom-model]

ListLLMBlueprintSortQueryParam

"name"

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

{
  "count": 0,
  "data": [
    {
      "creationDate": "2019-08-24T14:15:22Z",
      "creationUserId": "string",
      "customModelLLMErrorMessage": "An unknown external LLM error occurred.",
      "customModelLLMErrorResolution": "An unknown error during custom model LLM retrieval or execution occured. Please validate the custom model LLM if applicable. Otherwise contact the DataRobot team for assistance.",
      "customModelLLMValidationStatus": "TESTING",
      "description": "string",
      "id": "string",
      "isSaved": true,
      "isStarred": true,
      "lastUpdateDate": "2019-08-24T14:15:22Z",
      "lastUpdateUserId": "string",
      "llmId": "azure-openai-gpt-3.5-turbo",
      "llmName": "string",
      "llmSettings": {
        "maxCompletionLength": 0,
        "systemPrompt": "string",
        "temperature": 0,
        "topP": 0
      },
      "name": "string",
      "playgroundId": "string",
      "promptType": "CHAT_HISTORY_AWARE",
      "vectorDatabaseErrorMessage": "Unknown vector database error occurred",
      "vectorDatabaseErrorResolution": "An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance.",
      "vectorDatabaseId": "string",
      "vectorDatabaseName": "string",
      "vectorDatabaseSettings": {
        "maxDocumentsRetrievedPerPrompt": 10,
        "maxTokens": 0
      },
      "vectorDatabaseStatus": "NEW"
    }
  ],
  "next": "string",
  "previous": "string",
  "totalCount": 0
}

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 string¦null true The URL to the next page, or null if there is no such page.
previous string¦null true The URL to the previous page, or null if there is no such page.
totalCount integer true The total number of records.

PromptType

"CHAT_HISTORY_AWARE"

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]

UpdateLLMBlueprintRequest

{
  "description": "string",
  "isSaved": true,
  "isStarred": true,
  "llmId": "azure-openai-gpt-3.5-turbo",
  "llmSettings": {
    "maxCompletionLength": 0,
    "systemPrompt": "string",
    "temperature": 0,
    "topP": 0
  },
  "name": "string",
  "promptType": "CHAT_HISTORY_AWARE",
  "vectorDatabaseId": "string",
  "vectorDatabaseSettings": {
    "maxDocumentsRetrievedPerPrompt": 10,
    "maxTokens": 0
  }
}

UpdateLLMBlueprintRequest

Properties

Name Type Required Restrictions Description
description string¦null false maxLength: 5000
If specified, updates the LLM blueprint description to this value.
isSaved boolean¦null false If specified, updates the saved status of the LLM blueprint to this value.
isStarred boolean¦null false If specified, updates the starred status of the LLM blueprint to this value.
llmId LanguageModelTypeId¦null false If specified, changes the LLM used by the LLM blueprint.
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.

continued

Name Type Required Restrictions Description
name string¦null false maxLength: 5000
If specified, renames the LLM blueprint to this value.
promptType PromptType¦null false If specified, updates the chat context behavior of the LLM blueprint to this value.
vectorDatabaseId string¦null 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.
vectorDatabaseSettings VectorDatabaseSettings¦null false If specified, updates the vector database retrieval settings to these values.

ValidationError

{
  "loc": [
    "string"
  ],
  "msg": "string",
  "type": "string"
}

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

VectorDatabaseErrorMessages

"Unknown vector database error occurred"

VectorDatabaseErrorMessages

Properties

Name Type Required Restrictions Description
VectorDatabaseErrorMessages string false Error messages for vector database errors.

Enumerated Values

Property Value
VectorDatabaseErrorMessages [Unknown vector database error occurred, A vector database prediction timeout error occurred., Downloading or finding embedding model weights failed, Loading dataset failed, All loaded documents are empty or contain no text, Raw loaded text dataset size exceeds the limit for the chosen embedding model, Splitting documents into text chunks failed, Generating embeddings from text chunks failed, Creating an index from embeddings failed, Storing vector database assets failed, Calcluating the size of stored vector database assets failed, API token was deleted or revoked, Document retrieval failed, Vector database was deleted, Loading the embedding model failed, External vector database connection is not available, External vector database deployment has been deleted, No access to external vector database deployment, Only unstructured deployment types are supported, An API token is required but was not provided in the request, Deployment prediction server did not accept the request, Deployment prediction does not comply with the expected format, API token was deleted or revoked, External embedding model connection is not available, External embedding deployment has been deleted, No access to external embedding deployment, Only unstructured deployment types are supported, An API token is required but was not provided in the request, Deployment prediction server did not accept the request, Deployment prediction does not comply with the expected format, Worker process was unexpectedly terminated]

VectorDatabaseErrorResolutions

"An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance."

VectorDatabaseErrorResolutions

Properties

Name Type Required Restrictions Description
VectorDatabaseErrorResolutions string false Vector database resolutions are not part of the vector database API response,
but added to llm-blueprint and chat- and comparison-prompt responses
to provide the user verbose information on how to resolve existing issues.

Enumerated Values

Property Value
VectorDatabaseErrorResolutions [An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance., A prediction timeout error occured for your vector database. Please increase your prediction timeout for your custom model validation. And then try revalidating the custom model again. Otherwise contact the DataRobot team for assistance., An unknown error occurred when loading the embedding weights. Choose another embedding model or contact DataRobot for assistance., An unknown error occurred when loading the dataset. Validate the dataset or contact DataRobot for assistance., Dataset must contain UTF-8 formatted text. PDFs that contain only images are not supported., Reduce the size of raw text in the dataset or choose a smaller embedding model., An unknown error occurred when splitting the dataset into chunks. Validate the dataset, try a different chunking configuration, or contact DataRobot for assistance., An unknown error occurred during embedding generation. Validate the dataset, choose a different embedding model, or contact DataRobot for assistance., An unknown error occurred during index creation. Contact DataRobot for assistance., An unknown error occurred when storing the vector database.Reduce the dataset size or choose a smaller embedding model. Otherwise, contact DataRobot for assistance., An unknown error occurred when reading the vector database settings. Contact DataRobot for assistance., An unknown error occurred during document retrieval. Contact DataRobot for assistance., This LLM blueprint's vector database was deleted, disabling the blueprint. To use the same blueprint configuration, copy it to a draft and select a new database., The embedding model cannot be loaded. Contact DataRobot for assistance., The API token of the deployed external vector database was deleted or revoked. Using a new token that provides API access, validate and recreate the external vector database., This LLM blueprint's external vector database is no longer available. Either restore the database connection or copy the saved LLM blueprint to a draft and select a new database., The deployment providing access to the configured external vector database was deleted. Create a new vector database from an active deployment., Access to the external vector database deployment was revoked. Create a new vector database from an authorized deployment., The deployment type of the external vector database is not supported. Ensure the target type for your deployment is Unstructured or TextGeneration., You are attempting to access external vector database validation through non-token authentication methods. Only token-based authentication is allowed., The prediction request to the deployed external vector database failed. Make sure the deployment accepts JSON or CSV input with specified prompt column name., The prediction response to the deployment has an invalid format. Ensure that the unstructured deployment responds with valid JSON and with the specified target column name., The API token of the deployed external embedding model was deleted or revoked. Using a new token that provides API access, validate and recreate the external embedding model., The external embedding model used with this LLM blueprint's vector database is no longer available. Either restore the external embedding connection or select a different vector database., The deployment providing access to the configured external embedding model was deleted. Create a new external embedding model from an active deployment., Access to the external embedding deployment was revoked. Create a new embedding model from an authorized deployment., The deployment type of the external embedding model is not supported. Ensure the target type for your deployment is Unstructured., You are attempting to access external embedding validation through non-token authentication methods. Only token-based authentication is allowed., The prediction request to the deployed external embedding model failed. Make sure the deployment accepts JSON or CSV input with specified prompt column name., The prediction response to the deployment has an invalid format. Ensure that the unstructured deployment responds with valid JSON and with the specified target column name., The worker process was unexpectedly terminated. This could have been caused by excessive memory usage or an internal system error. Try re-creating the vector database with a smaller dataset and a smaller embedding model.]

VectorDatabaseErrorResolutionsForDrafts

"An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance."

VectorDatabaseErrorResolutionsForDrafts

Properties

Name Type Required Restrictions Description
VectorDatabaseErrorResolutionsForDrafts string false Error resolutions for vector databases used in blueprint drafts.

Enumerated Values

Property Value
VectorDatabaseErrorResolutionsForDrafts [An unknown error during vector database creation occurred. Validate the dataset or the external vector database if applicable. Otherwise, contact DataRobot for assistance., A prediction timeout error occured for your vector database. Please increase your prediction timeout for your custom model validation. And then try revalidating the custom model again. Otherwise contact the DataRobot team for assistance., An unknown error occurred when loading the embedding weights. Choose another embedding model or contact DataRobot for assistance., An unknown error occurred when loading the dataset. Validate the dataset or contact DataRobot for assistance., Dataset must contain UTF-8 formatted text. PDFs that contain only images are not supported., Reduce the size of raw text in the dataset or choose a smaller embedding model., An unknown error occurred when splitting the dataset into chunks. Validate the dataset, try a different chunking configuration, or contact DataRobot for assistance., An unknown error occurred during embedding generation. Validate the dataset, choose a different embedding model, or contact DataRobot for assistance., An unknown error occurred during index creation. Contact DataRobot for assistance., An unknown error occurred when storing the vector database.Reduce the dataset size or choose a smaller embedding model. Otherwise, contact DataRobot for assistance., An unknown error occurred when reading the vector database settings. Contact DataRobot for assistance., An unknown error occurred during document retrieval. Contact DataRobot for assistance., The vector database for this draft has been deleted. To proceed, select a new database in the configuration., The embedding model cannot be loaded. Contact DataRobot for assistance., The API token of the deployed external vector database was deleted or revoked. Using a new token that provides API access, validate and recreate the external vector database., The external vector database for this draft is no longer available. To proceed, either restore the database connection or select a new database in the configuration., The deployment providing access to the configured external vector database was deleted. Create a new vector database from an active deployment., Access to the external vector database deployment was revoked. Create a new vector database from an authorized deployment., The deployment type of the external vector database is not supported. Ensure the target type for your deployment is Unstructured or TextGeneration., You are attempting to access external vector database validation through non-token authentication methods. Only token-based authentication is allowed., The prediction request to the deployed external vector database failed. Make sure the deployment accepts JSON or CSV input with specified prompt column name., The prediction response to the deployment has an invalid format. Ensure that the unstructured deployment responds with valid JSON and with the specified target column name., The API token of the deployed external embedding model was deleted or revoked. Using a new token that provides API access, validate and recreate the external embedding model., The external embedding model used with this LLM blueprint's vector database is no longer available. Either restore the external embedding connection or select a different vector database., The deployment providing access to the configured external embedding model was deleted. Create a new external embedding model from an active deployment., Access to the external embedding deployment was revoked. Create a new embedding model from an authorized deployment., The deployment type of the external embedding model is not supported. Ensure the target type for your deployment is Unstructured., You are attempting to access external embedding validation through non-token authentication methods. Only token-based authentication is allowed., The prediction request to the deployed external embedding model failed. Make sure the deployment accepts JSON or CSV input with specified prompt column name., The worker process was unexpectedly terminated. This could have been caused by excessive memory usage or an internal system error. Try re-creating the vector database with a smaller dataset and a smaller embedding model.]

VectorDatabaseSettings

{
  "maxDocumentsRetrievedPerPrompt": 10,
  "maxTokens": 0
}

VectorDatabaseSettings

Properties

Name Type Required Restrictions Description
maxDocumentsRetrievedPerPrompt integer¦null false maximum: 10
The maximum number of documents to retrieve from the vector database.
maxTokens integer¦null false The maximum number of tokens to retrieve from the vector database.

Updated June 21, 2024