DataRobot APIのリソース > APIリファレンスドキュメント > DataRobot REST API > Vector Databases (GenAI)

Vector Databases (GenAI)¶

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

GET /api/v2/genai/vectorDatabases/¶

List vector databases.

Code samples¶

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

Parameters

Name	In	Type	Required	Description
useCaseId	query	any	false	Only retrieve the vector databases linked to these use case IDs.
playgroundId	query	string	false	Only retrieve the vector databases linked to 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 vector databases with names matching the search query.
sort	query	any	false	Apply this sort order to the results. Valid options are "name", "creationDate", "creationUserId", "embeddingModel", "datasetId", "chunkingMethod", "chunksCount", "size", "userName", "datasetName", "playgroundsCount", "source". 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 vector databases that have finished building. The default is `false`.

Example responses¶

200 Response

{
  "count": 0,
  "data": [
    {
      "chunkOverlapPercentage": 0,
      "chunkSize": 0,
      "chunkingMethod": "recursive",
      "chunksCount": 0,
      "creationDate": "2019-08-24T14:15:22Z",
      "creationUserId": "string",
      "datasetId": "string",
      "datasetName": "string",
      "embeddingModel": "intfloat/e5-large-v2",
      "embeddingValidationId": "string",
      "errorMessage": "Unknown vector database error occurred",
      "executionStatus": "NEW",
      "id": "string",
      "isSeparatorRegex": true,
      "lastUpdateDate": "2019-08-24T14:15:22Z",
      "name": "string",
      "organizationId": "string",
      "playgroundsCount": 0,
      "separators": [
        null
      ],
      "size": 0,
      "source": "DataRobot",
      "tenantId": "string",
      "useCaseId": "string",
      "userName": "string",
      "validationId": "string"
    }
  ],
  "next": "string",
  "previous": "string",
  "totalCount": 0
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Vector databases successfully retrieved.	ListVectorDatabasesResponse
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/vectorDatabases/¶

Create a new vector database.

Code samples¶

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

Body parameter¶

{
  "chunkingParameters": {
    "chunkOverlapPercentage": 50,
    "chunkSize": 0,
    "chunkingMethod": "recursive",
    "embeddingModel": "intfloat/e5-large-v2",
    "embeddingValidationId": "string",
    "isSeparatorRegex": false,
    "separators": [
      "string"
    ]
  },
  "datasetId": "string",
  "name": "string",
  "useCaseId": "string"
}

Parameters

Name	In	Type	Required	Description
body	body	CreateVectorDatabaseRequest	true	none

Example responses¶

202 Response

{
  "chunkOverlapPercentage": 0,
  "chunkSize": 0,
  "chunkingMethod": "recursive",
  "chunksCount": 0,
  "creationDate": "2019-08-24T14:15:22Z",
  "creationUserId": "string",
  "datasetId": "string",
  "datasetName": "string",
  "embeddingModel": "intfloat/e5-large-v2",
  "embeddingValidationId": "string",
  "errorMessage": "Unknown vector database error occurred",
  "executionStatus": "NEW",
  "id": "string",
  "isSeparatorRegex": true,
  "lastUpdateDate": "2019-08-24T14:15:22Z",
  "name": "string",
  "organizationId": "string",
  "playgroundsCount": 0,
  "separators": [
    null
  ],
  "size": 0,
  "source": "DataRobot",
  "tenantId": "string",
  "useCaseId": "string",
  "userName": "string",
  "validationId": "string"
}

Responses¶

Status	Meaning	Description	Schema
202	Accepted	Vector database creation job successfully accepted. Follow the `Location` header to poll for job execution status.	VectorDatabaseResponse
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/vectorDatabases/fromCustomModelDeployment/¶

Create a new vector database from a custom model deployment.

Code samples¶

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

Body parameter¶

{
  "name": "string",
  "useCaseId": "string",
  "validationId": "string"
}

Parameters

Name	In	Type	Required	Description
body	body	any	true	none

Example responses¶

201 Response

{
  "chunkOverlapPercentage": 0,
  "chunkSize": 0,
  "chunkingMethod": "recursive",
  "chunksCount": 0,
  "creationDate": "2019-08-24T14:15:22Z",
  "creationUserId": "string",
  "datasetId": "string",
  "datasetName": "string",
  "embeddingModel": "intfloat/e5-large-v2",
  "embeddingValidationId": "string",
  "errorMessage": "Unknown vector database error occurred",
  "executionStatus": "NEW",
  "id": "string",
  "isSeparatorRegex": true,
  "lastUpdateDate": "2019-08-24T14:15:22Z",
  "name": "string",
  "organizationId": "string",
  "playgroundsCount": 0,
  "separators": [
    null
  ],
  "size": 0,
  "source": "DataRobot",
  "tenantId": "string",
  "useCaseId": "string",
  "userName": "string",
  "validationId": "string"
}

Responses¶

Status	Meaning	Description	Schema
201	Created	Custom model hosted vector database successfully added. Full representation is available in the response body.	VectorDatabaseResponse
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/vectorDatabases/supportedEmbeddings/¶

List the supported embedding models for building vector databases.

Code samples¶

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

Parameters

Name	In	Type	Required	Description
datasetId	query	string	false	Only retrieve the embedding models compatible with this dataset ID.
useCaseId	query	string	false	If specified, include the custom model embeddings available for this use case ID.

Example responses¶

200 Response

{
  "customModelEmbeddingValidations": [
    {
      "id": "string",
      "name": "string"
    }
  ],
  "defaultEmbeddingModel": "string",
  "embeddingModels": [
    {
      "description": "string",
      "embeddingModel": "intfloat/e5-large-v2",
      "languages": [
        "Afrikaans"
      ],
      "maxSequenceLength": 0
    }
  ]
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Supported embeddings successfully retrieved.	SupportedEmbeddingsResponse
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/vectorDatabases/supportedTextChunkings/¶

List the supported text chunking methods for building vector databases.

Code samples¶

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

Example responses¶

200 Response

{
  "textChunkingConfigs": [
    {
      "defaultMethod": "string",
      "embeddingModel": "intfloat/e5-large-v2",
      "methods": [
        {
          "chunkingMethod": "recursive",
          "chunkingParameters": [
            {
              "default": 0,
              "description": "string",
              "max": 0,
              "min": 0,
              "name": "string",
              "type": "int"
            }
          ],
          "description": "string"
        }
      ]
    }
  ]
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Supported text chunking methods successfully retrieved.	SupportedTextChunkingResponse

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

DELETE /api/v2/genai/vectorDatabases/{vectorDatabaseId}/¶

Delete an existing vector database.

Code samples¶

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

Parameters

Name	In	Type	Required	Description
vectorDatabaseId	path	string	true	The ID of the vector database to delete.

Example responses¶

422 Response

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

Responses¶

Status	Meaning	Description	Schema
204	No Content	Vector database 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/vectorDatabases/{vectorDatabaseId}/¶

Retrieve an existing vector database.

Code samples¶

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

Parameters

Name	In	Type	Required	Description
vectorDatabaseId	path	string	true	The ID of the vector database to retrieve.

Example responses¶

200 Response

{
  "chunkOverlapPercentage": 0,
  "chunkSize": 0,
  "chunkingMethod": "recursive",
  "chunksCount": 0,
  "creationDate": "2019-08-24T14:15:22Z",
  "creationUserId": "string",
  "datasetId": "string",
  "datasetName": "string",
  "embeddingModel": "intfloat/e5-large-v2",
  "embeddingValidationId": "string",
  "errorMessage": "Unknown vector database error occurred",
  "executionStatus": "NEW",
  "id": "string",
  "isSeparatorRegex": true,
  "lastUpdateDate": "2019-08-24T14:15:22Z",
  "name": "string",
  "organizationId": "string",
  "playgroundsCount": 0,
  "separators": [
    null
  ],
  "size": 0,
  "source": "DataRobot",
  "tenantId": "string",
  "useCaseId": "string",
  "userName": "string",
  "validationId": "string"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Vector database successfully retrieved.	VectorDatabaseResponse
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/vectorDatabases/{vectorDatabaseId}/¶

Edit an existing vector database.

Code samples¶

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

Body parameter¶

{
  "name": "string"
}

Parameters

Name	In	Type	Required	Description
vectorDatabaseId	path	string	true	The ID of the vector database to edit.
body	body	EditVectorDatabaseRequest	true	none

Example responses¶

200 Response

{
  "chunkOverlapPercentage": 0,
  "chunkSize": 0,
  "chunkingMethod": "recursive",
  "chunksCount": 0,
  "creationDate": "2019-08-24T14:15:22Z",
  "creationUserId": "string",
  "datasetId": "string",
  "datasetName": "string",
  "embeddingModel": "intfloat/e5-large-v2",
  "embeddingValidationId": "string",
  "errorMessage": "Unknown vector database error occurred",
  "executionStatus": "NEW",
  "id": "string",
  "isSeparatorRegex": true,
  "lastUpdateDate": "2019-08-24T14:15:22Z",
  "name": "string",
  "organizationId": "string",
  "playgroundsCount": 0,
  "separators": [
    null
  ],
  "size": 0,
  "source": "DataRobot",
  "tenantId": "string",
  "useCaseId": "string",
  "userName": "string",
  "validationId": "string"
}

Responses¶

Status	Meaning	Description	Schema
200	OK	Vector database successfully updated.	VectorDatabaseResponse
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/vectorDatabases/{vectorDatabaseId}/textAndEmbeddings/¶

Retrieve the text chunk and embeddings asset for an existing vector database.

Code samples¶

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

Parameters

Name	In	Type	Required	Description
vectorDatabaseId	path	string	true	The ID of the vector database to retrieve the assets for.

Example responses¶

200 Response

null

Responses¶

Status	Meaning	Description	Schema
200	OK	Text and embeddings asset successfully retrieved.	Inline
422	Unprocessable Entity	Validation Error	HTTPValidationErrorResponse

Response Schema¶

To perform this operation, you must be authenticated by means of one of the following methods:

BearerAuth

Schemas¶

ChunkingMethodNames

"recursive"

ChunkingMethodNames

Properties¶

Name	Type	Required	Restrictions	Description
ChunkingMethodNames	string	false		Supported names of text chunking methods.

Enumerated Values¶

Property	Value
ChunkingMethodNames	`recursive`

ChunkingParameterTypes

"int"

ChunkingParameterTypes

Properties¶

Name	Type	Required	Restrictions	Description
ChunkingParameterTypes	string	false		Supported parameter data types for text chunking parameters.

Enumerated Values¶

Property	Value
ChunkingParameterTypes	[`int`, `list[str]`, `bool`]

ChunkingParameters

{
  "chunkOverlapPercentage": 50,
  "chunkSize": 0,
  "chunkingMethod": "recursive",
  "embeddingModel": "intfloat/e5-large-v2",
  "embeddingValidationId": "string",
  "isSeparatorRegex": false,
  "separators": [
    "string"
  ]
}

ChunkingParameters

Properties¶

Name	Type	Required	Restrictions	Description
chunkOverlapPercentage	integer	true	maximum: 50 minimum: 0	The chunk overlap percentage to use for text chunking.
chunkSize	integer	true		The chunk size to use for text chunking (measured in tokens).
chunkingMethod	ChunkingMethodNames	true		The text chunking method to use.
embeddingModel	EmbeddingModelNames¦null	false		The name of the embedding model to use. If omitted, DataRobot will choose the default embedding model automatically.
embeddingValidationId	string¦null	false		The validation ID of the custom embedding model (in case of using a custom model for embeddings).
isSeparatorRegex	boolean	false		Whether the text chunking separator uses a regular expression.
separators	[string]	true	maxItems: 9	The list of separators to use for text chunking.

CreateCustomModelVectorDatabaseFromDeploymentRequest

{
  "deploymentId": "string",
  "modelId": "string",
  "name": "string",
  "promptColumnName": "string",
  "targetColumnName": "string",
  "useCaseId": "string"
}

CreateCustomModelVectorDatabaseFromDeploymentRequest

Properties¶

Name	Type	Required	Restrictions	Description
deploymentId	string	true		The ID of the custom model deployment.
modelId	string	true		The ID of the model in the custom model deployment.
name	string	true	maxLength: 5000	The name of the vector database.
promptColumnName	string	true	maxLength: 5000	The name of the column the custom model uses for prompt text input.
targetColumnName	string	true	maxLength: 5000	The name of the column the custom model uses for prediction output.
useCaseId	string	true		The ID of the use case to link the vector database to.

CreateCustomModelVectorDatabaseFromValidationIdPayload

{
  "name": "string",
  "useCaseId": "string",
  "validationId": "string"
}

CreateCustomModelVectorDatabaseFromValidationIdPayload

Properties¶

Name	Type	Required	Restrictions	Description
name	string	true	maxLength: 5000	The name of the vector database.
useCaseId	string	true		The ID of the use case to link the vector database to.
validationId	string	true		The validation ID of the custom model validation.

CreateVectorDatabaseRequest

{
  "chunkingParameters": {
    "chunkOverlapPercentage": 50,
    "chunkSize": 0,
    "chunkingMethod": "recursive",
    "embeddingModel": "intfloat/e5-large-v2",
    "embeddingValidationId": "string",
    "isSeparatorRegex": false,
    "separators": [
      "string"
    ]
  },
  "datasetId": "string",
  "name": "string",
  "useCaseId": "string"
}

CreateVectorDatabaseRequest

Properties¶

Name	Type	Required	Restrictions	Description
chunkingParameters	ChunkingParameters	true		The text chunking parameters to use for building the vector database.
datasetId	string	true		The ID of the dataset to use for building the vector database.
name	string¦null	false	maxLength: 5000	The name of the vector database.
useCaseId	string	true		The ID of the use case to link the vector database to.

CustomEmbeddingModelNames

"custom-embeddings/default"

CustomEmbeddingModelNames

Properties¶

Name	Type	Required	Restrictions	Description
CustomEmbeddingModelNames	string	false		Model names for custom embedding models.

Enumerated Values¶

Property	Value
CustomEmbeddingModelNames	`custom-embeddings/default`

DatasetLanguages

"Afrikaans"

DatasetLanguages

Properties¶

Name	Type	Required	Restrictions	Description
DatasetLanguages	string	false		The names of dataset languages.

Enumerated Values¶

Property Value

DatasetLanguages [Afrikaans, Amharic, Arabic, Assamese, Azerbaijani, Belarusian, Bulgarian, Bengali, Breton, Bosnian, Catalan, Czech, Welsh, Danish, German, Greek, English, Esperanto, Spanish, Estonian, Basque, Persian, Finnish, French, Western Frisian, Irish, Scottish Gaelic, Galician, Gujarati, Hausa, Hebrew, Hindi, Croatian, Hungarian, Armenian, Indonesian, Icelandic, Italian, Japanese, Javanese, Georgian, Kazakh, Khmer, Kannada, Korean, Kurdish, Kyrgyz, Latin, Lao, Lithuanian, Latvian, Malagasy, Macedonian, Malayalam, Mongolian, Marathi, Malay, Burmese, Nepali, Dutch, Norwegian, Oromo, Oriya, Panjabi, Polish, Pashto, Portuguese, Romanian, Russian, Sanskrit, Sindhi, Sinhala, Slovak, Slovenian, Somali, Albanian, Serbian, Sundanese, Swedish, Swahili, Tamil, Telugu, Thai, Tagalog, Turkish, Uyghur, Ukrainian, Urdu, Uzbek, Vietnamese, Xhosa, Yiddish, Chinese]

EditVectorDatabaseRequest

{
  "name": "string"
}

EditVectorDatabaseRequest

Properties¶

Name	Type	Required	Restrictions	Description
name	string	true	maxLength: 5000	The new name of the vector database.

EmbeddingModel

{
  "description": "string",
  "embeddingModel": "intfloat/e5-large-v2",
  "languages": [
    "Afrikaans"
  ],
  "maxSequenceLength": 0
}

EmbeddingModel

Properties¶

Name	Type	Required	Description
description	string	true	The description of the embedding model.
embeddingModel	EmbeddingModelNames	true	The name of the embedding model.
languages	[DatasetLanguages]	true	The list of languages the embedding models supports.
maxSequenceLength	integer	true	The maximum input token sequence length that the embedding model can accept.

EmbeddingModelNames

"intfloat/e5-large-v2"

EmbeddingModelNames

Properties¶

Name	Type	Required	Restrictions	Description
EmbeddingModelNames	string	false		Embedding model names (matching the format of HuggingFace repositories).

Enumerated Values¶

Property	Value
EmbeddingModelNames	[`intfloat/e5-large-v2`, `intfloat/e5-base-v2`, `intfloat/multilingual-e5-base`, `sentence-transformers/all-MiniLM-L6-v2`, `jinaai/jina-embedding-t-en-v1`, `cl-nagoya/sup-simcse-ja-base`]

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

ListVectorDatabaseSortQueryParam

"name"

ListVectorDatabaseSortQueryParam

Properties¶

Name	Type	Required	Restrictions	Description
ListVectorDatabaseSortQueryParam	string	false		Sort order values for listing vector databases.

Enumerated Values¶

Property	Value
ListVectorDatabaseSortQueryParam	[`name`, `-name`, `creationUserId`, `-creationUserId`, `creationDate`, `-creationDate`, `embeddingModel`, `-embeddingModel`, `datasetId`, `-datasetId`, `chunkingMethod`, `-chunkingMethod`, `chunksCount`, `-chunksCount`, `size`, `-size`, `userName`, `-userName`, `datasetName`, `-datasetName`, `playgroundsCount`, `-playgroundsCount`, `source`, `-source`]

ListVectorDatabasesResponse

{
  "count": 0,
  "data": [
    {
      "chunkOverlapPercentage": 0,
      "chunkSize": 0,
      "chunkingMethod": "recursive",
      "chunksCount": 0,
      "creationDate": "2019-08-24T14:15:22Z",
      "creationUserId": "string",
      "datasetId": "string",
      "datasetName": "string",
      "embeddingModel": "intfloat/e5-large-v2",
      "embeddingValidationId": "string",
      "errorMessage": "Unknown vector database error occurred",
      "executionStatus": "NEW",
      "id": "string",
      "isSeparatorRegex": true,
      "lastUpdateDate": "2019-08-24T14:15:22Z",
      "name": "string",
      "organizationId": "string",
      "playgroundsCount": 0,
      "separators": [
        null
      ],
      "size": 0,
      "source": "DataRobot",
      "tenantId": "string",
      "useCaseId": "string",
      "userName": "string",
      "validationId": "string"
    }
  ],
  "next": "string",
  "previous": "string",
  "totalCount": 0
}

ListVectorDatabasesResponse

Properties¶

Name	Type	Required	Description
count	integer	true	The number of records on this page.
data	[VectorDatabaseResponse]	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.

SupportedCustomModelEmbeddings

{
  "id": "string",
  "name": "string"
}

SupportedCustomModelEmbeddings

Properties¶

Name	Type	Required	Restrictions	Description
id	string	true		The validation ID of the custom embedding model.
name	string	true		The name of the custom embedding model.

SupportedEmbeddingsResponse

{
  "customModelEmbeddingValidations": [
    {
      "id": "string",
      "name": "string"
    }
  ],
  "defaultEmbeddingModel": "string",
  "embeddingModels": [
    {
      "description": "string",
      "embeddingModel": "intfloat/e5-large-v2",
      "languages": [
        "Afrikaans"
      ],
      "maxSequenceLength": 0
    }
  ]
}

SupportedEmbeddingsResponse

Properties¶

Name	Type	Required	Description
customModelEmbeddingValidations	[SupportedCustomModelEmbeddings]	false	The list of validated custom embedding models.
defaultEmbeddingModel	string	true	The name of the default embedding model.
embeddingModels	[EmbeddingModel]	true	The list of embeddings models.

SupportedTextChunkingResponse

{
  "textChunkingConfigs": [
    {
      "defaultMethod": "string",
      "embeddingModel": "intfloat/e5-large-v2",
      "methods": [
        {
          "chunkingMethod": "recursive",
          "chunkingParameters": [
            {
              "default": 0,
              "description": "string",
              "max": 0,
              "min": 0,
              "name": "string",
              "type": "int"
            }
          ],
          "description": "string"
        }
      ]
    }
  ]
}

SupportedTextChunkingResponse

Properties¶

Name	Type	Required	Restrictions	Description
textChunkingConfigs	[TextChunkingConfig]	true		The list of text chunking configurations.

TextChunkingConfig

{
  "defaultMethod": "string",
  "embeddingModel": "intfloat/e5-large-v2",
  "methods": [
    {
      "chunkingMethod": "recursive",
      "chunkingParameters": [
        {
          "default": 0,
          "description": "string",
          "max": 0,
          "min": 0,
          "name": "string",
          "type": "int"
        }
      ],
      "description": "string"
    }
  ]
}

TextChunkingConfig

Properties¶

Name	Type	Required	Restrictions	Description
defaultMethod	string	true		The name of the default text chunking method.
embeddingModel	any	true		The name of the embedding model.

anyOf

Name	Type	Required	Restrictions	Description
» anonymous	EmbeddingModelNames	false		Embedding model names (matching the format of HuggingFace repositories).

or

Name	Type	Required	Restrictions	Description
» anonymous	CustomEmbeddingModelNames	false		Model names for custom embedding models.

continued

Name	Type	Required	Restrictions	Description
methods	[TextChunkingMethod]	true		The list of text chunking methods.

TextChunkingMethod

{
  "chunkingMethod": "recursive",
  "chunkingParameters": [
    {
      "default": 0,
      "description": "string",
      "max": 0,
      "min": 0,
      "name": "string",
      "type": "int"
    }
  ],
  "description": "string"
}

TextChunkingMethod

Properties¶

Name	Type	Required	Description
chunkingMethod	ChunkingMethodNames	true	The name of the text chunking method.
chunkingParameters	[TextChunkingParameterFields]	true	The list of text chunking parameters.
description	string	true	The description of the text chunking method.

TextChunkingParameterFields

{
  "default": 0,
  "description": "string",
  "max": 0,
  "min": 0,
  "name": "string",
  "type": "int"
}

TextChunkingParameterFields

Properties¶

Name	Type	Required	Restrictions	Description
default	any	true		The default value of the parameter.

anyOf

Name	Type	Required	Restrictions	Description
» anonymous	integer	false		none

or

Name	Type	Required	Restrictions	Description
» anonymous	[string]	false		none

or

Name	Type	Required	Restrictions	Description
» anonymous	boolean	false		none

continued

Name	Type	Required	Description
description	string	true	The description of the parameter.
max	integer¦null	true	The maximum value of the parameter (inclusive).
min	integer¦null	true	The minimum value of the parameter (inclusive).
name	string	true	The name of the parameter.
type	ChunkingParameterTypes	true	The data type of the parameter.

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]

VectorDatabaseResponse

{
  "chunkOverlapPercentage": 0,
  "chunkSize": 0,
  "chunkingMethod": "recursive",
  "chunksCount": 0,
  "creationDate": "2019-08-24T14:15:22Z",
  "creationUserId": "string",
  "datasetId": "string",
  "datasetName": "string",
  "embeddingModel": "intfloat/e5-large-v2",
  "embeddingValidationId": "string",
  "errorMessage": "Unknown vector database error occurred",
  "executionStatus": "NEW",
  "id": "string",
  "isSeparatorRegex": true,
  "lastUpdateDate": "2019-08-24T14:15:22Z",
  "name": "string",
  "organizationId": "string",
  "playgroundsCount": 0,
  "separators": [
    null
  ],
  "size": 0,
  "source": "DataRobot",
  "tenantId": "string",
  "useCaseId": "string",
  "userName": "string",
  "validationId": "string"
}

VectorDatabaseResponse

Properties¶

Name	Type	Required	Description
chunkOverlapPercentage	integer	true	The chunk overlap percentage the vector database uses.
chunkSize	integer	true	The size of the text chunk (measured in tokens) the vector database uses.
chunkingMethod	ChunkingMethodNames¦null	true	The text chunking method the vector database uses.
chunksCount	integer	true	The number of text chunks in the vector database.
creationDate	string(date-time)	true	The creation date of the vector database (ISO 8601 formatted).
creationUserId	string	true	The ID of the user that created this vector database.
datasetId	string¦null	true	The ID of the dataset the vector database was built from.
datasetName	string	true	The name of the dataset this vector database was built from.
embeddingModel	EmbeddingModelNames¦null	true	The name of the embedding model the vector database uses.
embeddingValidationId	string¦null	true	The validation ID of the custom model embedding (in case of using a custom model for embeddings).
errorMessage	VectorDatabaseErrorMessages¦null	true	The error message associated with the vector database creation error (in case of a creation error).
executionStatus	ExecutionStatus	true	The creation status of the vector database.
id	string	true	The ID of the vector database.
isSeparatorRegex	boolean	true	Whether the text chunking separator uses a regular expression.
lastUpdateDate	string(date-time)	true	The date of the most recent update of this playground (ISO 8601 formatted).
name	string	true	The name of the vector database.
organizationId	string	true	The ID of the DataRobot organization this vector database belongs to.
playgroundsCount	integer	true	The number of playgrounds that use this vector database.
separators	[any]	true	The text chunking separators the vector database uses.
size	integer	true	The size of the vector database (in bytes).
source	VectorDatabaseSource	true	The source of the vector database.
tenantId	string(uuid4)	true	The ID of the DataRobot tenant this vector database belongs to.
useCaseId	string	true	The ID of the use case the vector database is linked to.
userName	string	true	The name of the user that created this vector database.
validationId	string¦null	true	The validation ID of the custom model vector database (in case of using a custom model vector database).

VectorDatabaseSource

"DataRobot"

VectorDatabaseSource

Properties¶

Name	Type	Required	Restrictions	Description
VectorDatabaseSource	string	false		The source of the vector database.

Enumerated Values¶

Property	Value
VectorDatabaseSource	[`DataRobot`, `External`]

更新しました May 14, 2024

このページは役に立ちましたか？

ありがとうございます。どのような点が役に立ちましたか？

より良いコンテンツを提供するには、どうすればよいでしょうか？

アンケートにご協力いただき、ありがとうございました。