Vector databases¶
The following endpoints outline how to manage vector databases.
List custom model embedding validations¶
Operation path: GET /api/v2/genai/customModelEmbeddingValidations/
Authentication requirements: BearerAuth
List custom model embedding validations.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| useCaseId | query | any | false | Only retrieve the custom model embedding validations associated with these use case IDs. |
| playgroundId | query | any | false | Only retrieve the custom model embedding 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 embedding 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 embedding validations. The default is false. |
| deploymentId | query | any | false | Only retrieve the custom model embedding validations associated with this deployment ID. |
| modelId | query | any | false | Only retrieve the custom model embedding validations associated with this model ID. |
| promptColumnName | query | any | false | Only retrieve the custom model embedding validations where the custom model uses this column name for prompt input. |
| targetColumnName | query | any | false | Only retrieve the custom model embedding validations where the custom model uses this column name for prediction output. |
Example responses¶
200 Response
{
"description": "Paginated list of custom model embedding 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 embedding validation.",
"properties": {
"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": "CustomModelEmbeddingValidationResponse",
"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": "ListCustomModelEmbeddingValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model embedding validations successfully retrieved. | ListCustomModelEmbeddingValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Validate custom model embedding¶
Operation path: POST /api/v2/genai/customModelEmbeddingValidations/
Authentication requirements: BearerAuth
Validate an embedding model hosted in a custom model deployment for use in the playground.
Body parameter¶
{
"description": "The body of the \"Validate custom model\" request.",
"properties": {
"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": {
"description": "The name of the column the custom model uses for prompt text input.",
"maxLength": 5000,
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"maxLength": 5000,
"title": "targetColumnName",
"type": "string"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case to associate with the validated custom model.",
"title": "useCaseId"
}
},
"required": [
"deploymentId",
"promptColumnName",
"targetColumnName"
],
"title": "CreateCustomModelEmbeddingValidationRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateCustomModelEmbeddingValidationRequest | true | none |
Example responses¶
202 Response
{
"description": "API response object for a single custom model embedding validation.",
"properties": {
"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": "CustomModelEmbeddingValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Custom model embedding validation job successfully accepted. Follow the Location header to poll for job execution status. |
CustomModelEmbeddingValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Delete custom model embedding validation by validation ID¶
Operation path: DELETE /api/v2/genai/customModelEmbeddingValidations/{validationId}/
Authentication requirements: BearerAuth
Delete an existing custom model embedding validation.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| validationId | path | string | true | The ID of the custom model embedding 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 embedding validation successfully deleted. | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Retrieve custom model embedding validation status by validation ID¶
Operation path: GET /api/v2/genai/customModelEmbeddingValidations/{validationId}/
Authentication requirements: BearerAuth
Retrieve the status of validating a custom model embedding.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| validationId | path | string | true | The ID of the custom model embedding validation to retrieve. |
Example responses¶
200 Response
{
"description": "API response object for a single custom model embedding validation.",
"properties": {
"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": "CustomModelEmbeddingValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model embedding validation status successfully retrieved. | CustomModelEmbeddingValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Edit custom model embedding validation by validation ID¶
Operation path: PATCH /api/v2/genai/customModelEmbeddingValidations/{validationId}/
Authentication requirements: BearerAuth
Edit an existing custom model embedding 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 embedding validation to edit. |
| body | body | EditCustomModelValidationRequest | true | none |
Example responses¶
200 Response
{
"description": "API response object for a single custom model embedding validation.",
"properties": {
"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": "CustomModelEmbeddingValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model embedding validation successfully updated. | CustomModelEmbeddingValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Revalidate custom model embedding by validation ID¶
Operation path: POST /api/v2/genai/customModelEmbeddingValidations/{validationId}/revalidate/
Authentication requirements: BearerAuth
Revalidate an existing custom model embedding validation.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| validationId | path | string | true | The ID of the custom model embedding validation to revalidate. |
Example responses¶
200 Response
{
"description": "API response object for a single custom model embedding validation.",
"properties": {
"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": "CustomModelEmbeddingValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model embedding successfully revalidated. | CustomModelEmbeddingValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
List custom model vector database validations¶
Operation path: GET /api/v2/genai/customModelVectorDatabaseValidations/
Authentication requirements: BearerAuth
List custom model vector database validations.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| useCaseId | query | any | false | Only retrieve the custom model vector database validations associated with these use case IDs. |
| playgroundId | query | any | false | Only retrieve the custom model vector database 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 vector database 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 vector database validations. The default is false. |
| deploymentId | query | any | false | Only retrieve the custom model vector database validations associated with this deployment ID. |
| modelId | query | any | false | Only retrieve the custom model vector database validations associated with this model ID. |
| promptColumnName | query | any | false | Only retrieve the custom model vector database validations where the custom model uses this column name for prompt input. |
| targetColumnName | query | any | false | Only retrieve the custom model vector database validations where the custom model uses this column name for prediction output. |
Example responses¶
200 Response
{
"description": "Paginated list of custom model vector database 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 vector database validation.",
"properties": {
"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": "CustomModelVectorDatabaseValidationResponse",
"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": "ListCustomModelVectorDatabaseValidationsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model vector database validations successfully retrieved. | ListCustomModelVectorDatabaseValidationsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Validate custom model vector database¶
Operation path: POST /api/v2/genai/customModelVectorDatabaseValidations/
Authentication requirements: BearerAuth
Validate a vector database hosted in a custom model deployment for use in the playground.
Body parameter¶
{
"description": "The body of the \"Validate custom model\" request.",
"properties": {
"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": {
"description": "The name of the column the custom model uses for prompt text input.",
"maxLength": 5000,
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"maxLength": 5000,
"title": "targetColumnName",
"type": "string"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case to associate with the validated custom model.",
"title": "useCaseId"
}
},
"required": [
"deploymentId",
"promptColumnName",
"targetColumnName"
],
"title": "CreateCustomModelVectorDatabaseValidationRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateCustomModelVectorDatabaseValidationRequest | true | none |
Example responses¶
202 Response
{
"description": "API response object for a single custom model vector database validation.",
"properties": {
"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": "CustomModelVectorDatabaseValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Custom model vector database validation job successfully accepted. Follow the Location header to poll for job execution status. |
CustomModelVectorDatabaseValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Delete custom model vector database validation by validation ID¶
Operation path: DELETE /api/v2/genai/customModelVectorDatabaseValidations/{validationId}/
Authentication requirements: BearerAuth
Delete an existing custom model vector database validation.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| validationId | path | string | true | The ID of the custom model vector database 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 | Successfully deleted custom model vector database validation | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Retrieve custom model vector database validation status by validation ID¶
Operation path: GET /api/v2/genai/customModelVectorDatabaseValidations/{validationId}/
Authentication requirements: BearerAuth
Retrieve the status of validating a custom model vector database.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| validationId | path | string | true | The ID of the custom model vector database validation to retrieve. |
Example responses¶
200 Response
{
"description": "API response object for a single custom model vector database validation.",
"properties": {
"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": "CustomModelVectorDatabaseValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model vector database validation status successfully retrieved. | CustomModelVectorDatabaseValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Edit custom model vector database validation by validation ID¶
Operation path: PATCH /api/v2/genai/customModelVectorDatabaseValidations/{validationId}/
Authentication requirements: BearerAuth
Edit an existing custom model vector database 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 vector database validation to edit. |
| body | body | EditCustomModelValidationRequest | true | none |
Example responses¶
200 Response
{
"description": "API response object for a single custom model vector database validation.",
"properties": {
"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": "CustomModelVectorDatabaseValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model vector database validation successfully updated. | CustomModelVectorDatabaseValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Revalidate custom model vector database by validation ID¶
Operation path: POST /api/v2/genai/customModelVectorDatabaseValidations/{validationId}/revalidate/
Authentication requirements: BearerAuth
Revalidate an existing custom model vector database.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| validationId | path | string | true | The ID of the custom model vector database validation to revalidate. |
Example responses¶
200 Response
{
"description": "API response object for a single custom model vector database validation.",
"properties": {
"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": "CustomModelVectorDatabaseValidationResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Custom model vector database successfully revalidated. | CustomModelVectorDatabaseValidationResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
List vector databases¶
Operation path: GET /api/v2/genai/vectorDatabases/
Authentication requirements: BearerAuth
List vector databases.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| useCaseId | query | any | false | Only retrieve the vector databases linked to these use case IDs. |
| playgroundId | query | any | false | Only retrieve the vector databases linked to this playground ID. |
| familyId | query | any | false | Only retrieve the vector databases linked to this family ID. |
| parentsOnly | query | boolean | false | If true, only retrieve (root) parent vector databases. The default is false. |
| 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
{
"description": "Paginated list of vector databases.",
"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 vector database.",
"properties": {
"addedDatasetIds": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset IDs that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetIds"
},
"addedDatasetNames": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset names that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetNames"
},
"addedMetadataDatasetPairs": {
"anyOf": [
{
"items": {
"description": "Pair of metadata dataset and dataset added to the vector database.",
"properties": {
"datasetId": {
"description": "The ID of the dataset added to the vector database.",
"title": "datasetId",
"type": "string"
},
"datasetName": {
"description": "The name of the dataset added to the vector database.",
"title": "datasetName",
"type": "string"
},
"metadataDatasetId": {
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId",
"type": "string"
},
"metadataDatasetName": {
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName",
"type": "string"
}
},
"required": [
"metadataDatasetId",
"datasetId",
"metadataDatasetName",
"datasetName"
],
"title": "MetadataDatasetPairApiFormatted",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "Pairs of metadata dataset and dataset added to the vector database.",
"title": "addedMetadataDatasetPairs"
},
"chunkOverlapPercentage": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage that the vector database uses.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the text chunk (measured in tokens) that the vector database uses.",
"title": "chunkSize"
},
"chunkingLengthFunction": {
"anyOf": [
{
"description": "Supported length functions for text splitters.",
"enum": [
"tokenizer_length_function",
"approximate_token_count"
],
"title": "ChunkingLengthFunctionNames",
"type": "string"
},
{
"type": "null"
}
],
"default": "approximate_token_count",
"description": "The length function to use for the text splitter."
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method the vector database uses."
},
"chunksCount": {
"description": "The number of text chunks in the vector database.",
"title": "chunksCount",
"type": "integer"
},
"creationDate": {
"description": "The creation date of the vector database (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationDuration": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The duration of the vector database creation.",
"title": "creationDuration"
},
"creationUserId": {
"description": "The ID of the user that created this vector database.",
"title": "creationUserId",
"type": "string"
},
"customChunking": {
"description": "Whether the vector database uses custom chunking.",
"title": "customChunking",
"type": "boolean"
},
"datasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset the vector database was built from.",
"title": "datasetId"
},
"datasetName": {
"description": "The name of the dataset this vector database was built from.",
"title": "datasetName",
"type": "string"
},
"deploymentStatus": {
"anyOf": [
{
"description": "Sort order values for listing vector databases.",
"enum": [
"Created",
"Assembling",
"Registered",
"Deployed"
],
"title": "VectorDatabaseDeploymentStatuses",
"type": "string"
},
{
"type": "null"
}
],
"description": "How far along in the deployment process this vector database is."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model the vector database uses.",
"title": "embeddingModel"
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model embedding (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the vector database creation error (in case of a creation error).",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database creation error (in case of a creation error).",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"externalVectorDatabaseConnection": {
"anyOf": [
{
"discriminator": {
"mapping": {
"elasticsearch": "#/components/schemas/ElasticsearchConnection",
"pinecone": "#/components/schemas/PineconeConnection"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnection",
"type": "object"
},
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnection",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The external vector database connection to use.",
"title": "externalVectorDatabaseConnection"
},
"familyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "An ID associated with a family of vector databases, that is, a parent and all descendant vector databases. All vector databases that are descendants of the same root parent share a family ID.The family ID is equal to the vector database ID of the root parent.Like this each vector database knows it's direct parent and the root parent.",
"title": "familyId"
},
"id": {
"description": "The ID of the vector database.",
"title": "id",
"type": "string"
},
"isSeparatorRegex": {
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"metadataColumns": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of metadata columns in the vector database.",
"title": "metadataColumns"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId"
},
"metadataDatasetName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName"
},
"name": {
"description": "The name of the vector database.",
"title": "name",
"type": "string"
},
"organizationId": {
"description": "The ID of the DataRobot organization this vector database belongs to.",
"title": "organizationId",
"type": "string"
},
"parentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the direct parent vector database.It is generated when a vector database is created from another vector database.For the root (parent), ID is 'None'.",
"title": "parentId"
},
"percentage": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Vector database progress percentage.",
"title": "percentage"
},
"playgroundsCount": {
"description": "The number of playgrounds that use this vector database.",
"title": "playgroundsCount",
"type": "integer"
},
"separators": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"description": "The text chunking separators that the vector database uses.",
"title": "separators"
},
"size": {
"description": "The size of the vector database (in bytes).",
"title": "size",
"type": "integer"
},
"skippedChunksCount": {
"description": "The number of text chunks skipped during vector database creation.",
"title": "skippedChunksCount",
"type": "integer"
},
"source": {
"description": "The source of the vector database.",
"enum": [
"DataRobot",
"External",
"Pinecone",
"Elasticsearch"
],
"title": "VectorDatabaseSource",
"type": "string"
},
"tenantId": {
"description": "The ID of the DataRobot tenant this vector database belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case the vector database is linked to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this vector database.",
"title": "userName",
"type": "string"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model vector database (in case of using a custom model vector database).",
"title": "validationId"
},
"version": {
"description": "The version of the vector database linked to a certain family ID.",
"title": "version",
"type": "integer"
}
},
"required": [
"id",
"name",
"size",
"useCaseId",
"datasetId",
"embeddingModel",
"embeddingValidationId",
"embeddingRegisteredModelId",
"chunkSize",
"chunkingMethod",
"chunkOverlapPercentage",
"chunksCount",
"skippedChunksCount",
"customChunking",
"separators",
"isSeparatorRegex",
"creationDate",
"creationUserId",
"organizationId",
"tenantId",
"lastUpdateDate",
"executionStatus",
"errorMessage",
"errorResolution",
"source",
"validationId",
"parentId",
"familyId",
"addedDatasetIds",
"version",
"playgroundsCount",
"datasetName",
"userName",
"addedDatasetNames"
],
"title": "VectorDatabaseResponse",
"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": "ListVectorDatabasesResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Vector databases successfully retrieved. | ListVectorDatabasesResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Create vector database¶
Operation path: POST /api/v2/genai/vectorDatabases/
Authentication requirements: BearerAuth
Create a new vector database.
Body parameter¶
{
"description": "The body of the \"Create vector database\" request.",
"properties": {
"chunkingParameters": {
"anyOf": [
{
"description": "Chunking parameters for creating a vector database.",
"properties": {
"chunkOverlapPercentage": {
"anyOf": [
{
"maximum": 50,
"minimum": 0,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage to use for text chunking.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk size to use for text chunking (measured in tokens).",
"title": "chunkSize"
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method to use."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model to use. If omitted, DataRobot will choose the default embedding model automatically."
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom embedding model (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"isSeparatorRegex": {
"default": false,
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"separators": {
"anyOf": [
{
"items": {
"maxLength": 20,
"type": "string"
},
"maxItems": 9,
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of separators to use for text chunking.",
"title": "separators"
}
},
"title": "ChunkingParameters",
"type": "object"
},
{
"type": "null"
}
],
"description": "The text chunking parameters to use for building the vector database."
},
"datasetId": {
"description": "The ID of the dataset to use for building the vector database.",
"title": "datasetId",
"type": "string"
},
"externalVectorDatabaseConnection": {
"anyOf": [
{
"discriminator": {
"mapping": {
"elasticsearch": "#/components/schemas/ElasticsearchConnectionRequest",
"pinecone": "#/components/schemas/PineconeConnectionRequest"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnectionRequest",
"type": "object"
},
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnectionRequest",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The external vector database connection to use.",
"title": "externalVectorDatabaseConnection"
},
"metadataCombinationStrategy": {
"description": "Strategy to use when the dataset and the metadata file have duplicate columns.",
"enum": [
"replace",
"merge"
],
"title": "MetadataCombinationStrategy",
"type": "string"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset to add metadata for building the vector database.",
"title": "metadataDatasetId"
},
"name": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the vector database.",
"title": "name"
},
"parentVectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the parent vector database used as base for the re-building.",
"title": "parentVectorDatabaseId"
},
"updateDeployments": {
"default": false,
"description": "Whether to update the deployments that use the parent vector database.Can only be set to `true` if parent_vector_database_id is provided.",
"title": "updateDeployments",
"type": "boolean"
},
"updateLlmBlueprints": {
"default": false,
"description": "Whether to update the LLM blueprints that use the parent vector database.Can only be set to `true` if parent_vector_database_id is provided.",
"title": "updateLlmBlueprints",
"type": "boolean"
},
"useCaseId": {
"description": "The ID of the use case to link the vector database to.",
"title": "useCaseId",
"type": "string"
}
},
"required": [
"datasetId",
"useCaseId"
],
"title": "CreateVectorDatabaseRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | CreateVectorDatabaseRequest | true | none |
Example responses¶
202 Response
{
"description": "API response object for a single vector database.",
"properties": {
"addedDatasetIds": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset IDs that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetIds"
},
"addedDatasetNames": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset names that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetNames"
},
"addedMetadataDatasetPairs": {
"anyOf": [
{
"items": {
"description": "Pair of metadata dataset and dataset added to the vector database.",
"properties": {
"datasetId": {
"description": "The ID of the dataset added to the vector database.",
"title": "datasetId",
"type": "string"
},
"datasetName": {
"description": "The name of the dataset added to the vector database.",
"title": "datasetName",
"type": "string"
},
"metadataDatasetId": {
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId",
"type": "string"
},
"metadataDatasetName": {
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName",
"type": "string"
}
},
"required": [
"metadataDatasetId",
"datasetId",
"metadataDatasetName",
"datasetName"
],
"title": "MetadataDatasetPairApiFormatted",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "Pairs of metadata dataset and dataset added to the vector database.",
"title": "addedMetadataDatasetPairs"
},
"chunkOverlapPercentage": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage that the vector database uses.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the text chunk (measured in tokens) that the vector database uses.",
"title": "chunkSize"
},
"chunkingLengthFunction": {
"anyOf": [
{
"description": "Supported length functions for text splitters.",
"enum": [
"tokenizer_length_function",
"approximate_token_count"
],
"title": "ChunkingLengthFunctionNames",
"type": "string"
},
{
"type": "null"
}
],
"default": "approximate_token_count",
"description": "The length function to use for the text splitter."
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method the vector database uses."
},
"chunksCount": {
"description": "The number of text chunks in the vector database.",
"title": "chunksCount",
"type": "integer"
},
"creationDate": {
"description": "The creation date of the vector database (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationDuration": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The duration of the vector database creation.",
"title": "creationDuration"
},
"creationUserId": {
"description": "The ID of the user that created this vector database.",
"title": "creationUserId",
"type": "string"
},
"customChunking": {
"description": "Whether the vector database uses custom chunking.",
"title": "customChunking",
"type": "boolean"
},
"datasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset the vector database was built from.",
"title": "datasetId"
},
"datasetName": {
"description": "The name of the dataset this vector database was built from.",
"title": "datasetName",
"type": "string"
},
"deploymentStatus": {
"anyOf": [
{
"description": "Sort order values for listing vector databases.",
"enum": [
"Created",
"Assembling",
"Registered",
"Deployed"
],
"title": "VectorDatabaseDeploymentStatuses",
"type": "string"
},
{
"type": "null"
}
],
"description": "How far along in the deployment process this vector database is."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model the vector database uses.",
"title": "embeddingModel"
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model embedding (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the vector database creation error (in case of a creation error).",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database creation error (in case of a creation error).",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"externalVectorDatabaseConnection": {
"anyOf": [
{
"discriminator": {
"mapping": {
"elasticsearch": "#/components/schemas/ElasticsearchConnection",
"pinecone": "#/components/schemas/PineconeConnection"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnection",
"type": "object"
},
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnection",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The external vector database connection to use.",
"title": "externalVectorDatabaseConnection"
},
"familyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "An ID associated with a family of vector databases, that is, a parent and all descendant vector databases. All vector databases that are descendants of the same root parent share a family ID.The family ID is equal to the vector database ID of the root parent.Like this each vector database knows it's direct parent and the root parent.",
"title": "familyId"
},
"id": {
"description": "The ID of the vector database.",
"title": "id",
"type": "string"
},
"isSeparatorRegex": {
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"metadataColumns": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of metadata columns in the vector database.",
"title": "metadataColumns"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId"
},
"metadataDatasetName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName"
},
"name": {
"description": "The name of the vector database.",
"title": "name",
"type": "string"
},
"organizationId": {
"description": "The ID of the DataRobot organization this vector database belongs to.",
"title": "organizationId",
"type": "string"
},
"parentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the direct parent vector database.It is generated when a vector database is created from another vector database.For the root (parent), ID is 'None'.",
"title": "parentId"
},
"percentage": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Vector database progress percentage.",
"title": "percentage"
},
"playgroundsCount": {
"description": "The number of playgrounds that use this vector database.",
"title": "playgroundsCount",
"type": "integer"
},
"separators": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"description": "The text chunking separators that the vector database uses.",
"title": "separators"
},
"size": {
"description": "The size of the vector database (in bytes).",
"title": "size",
"type": "integer"
},
"skippedChunksCount": {
"description": "The number of text chunks skipped during vector database creation.",
"title": "skippedChunksCount",
"type": "integer"
},
"source": {
"description": "The source of the vector database.",
"enum": [
"DataRobot",
"External",
"Pinecone",
"Elasticsearch"
],
"title": "VectorDatabaseSource",
"type": "string"
},
"tenantId": {
"description": "The ID of the DataRobot tenant this vector database belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case the vector database is linked to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this vector database.",
"title": "userName",
"type": "string"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model vector database (in case of using a custom model vector database).",
"title": "validationId"
},
"version": {
"description": "The version of the vector database linked to a certain family ID.",
"title": "version",
"type": "integer"
}
},
"required": [
"id",
"name",
"size",
"useCaseId",
"datasetId",
"embeddingModel",
"embeddingValidationId",
"embeddingRegisteredModelId",
"chunkSize",
"chunkingMethod",
"chunkOverlapPercentage",
"chunksCount",
"skippedChunksCount",
"customChunking",
"separators",
"isSeparatorRegex",
"creationDate",
"creationUserId",
"organizationId",
"tenantId",
"lastUpdateDate",
"executionStatus",
"errorMessage",
"errorResolution",
"source",
"validationId",
"parentId",
"familyId",
"addedDatasetIds",
"version",
"playgroundsCount",
"datasetName",
"userName",
"addedDatasetNames"
],
"title": "VectorDatabaseResponse",
"type": "object"
}
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 |
Create a Vector Databases¶
Operation path: POST /api/v2/genai/vectorDatabases/fromCustomModelDeployment/
Authentication requirements: BearerAuth
Create a new vector database from a custom model deployment.
Body parameter¶
{
"anyOf": [
{
"description": "The body of the \"Create vector database from validation ID\" request.",
"properties": {
"name": {
"description": "The name of the vector database.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case to link the vector database to.",
"title": "useCaseId",
"type": "string"
},
"validationId": {
"description": "The validation ID of the custom model validation.",
"title": "validationId",
"type": "string"
}
},
"required": [
"name",
"useCaseId",
"validationId"
],
"title": "CreateCustomModelVectorDatabaseFromValidationIdPayload",
"type": "object"
},
{
"description": "The body of the \"Create vector database from custom model deployment\" request.",
"properties": {
"deploymentId": {
"description": "The ID of the custom model deployment.",
"title": "deploymentId",
"type": "string"
},
"modelId": {
"description": "The ID of the model in the custom model deployment.",
"title": "modelId",
"type": "string"
},
"name": {
"description": "The name of the vector database.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
},
"promptColumnName": {
"description": "The name of the column the custom model uses for prompt text input.",
"maxLength": 5000,
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"maxLength": 5000,
"title": "targetColumnName",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case to link the vector database to.",
"title": "useCaseId",
"type": "string"
}
},
"required": [
"name",
"useCaseId",
"promptColumnName",
"targetColumnName",
"deploymentId",
"modelId"
],
"title": "CreateCustomModelVectorDatabaseFromDeploymentRequest",
"type": "object"
}
],
"title": "Payload"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| body | body | any | true | none |
Example responses¶
201 Response
{
"description": "API response object for a single vector database.",
"properties": {
"addedDatasetIds": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset IDs that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetIds"
},
"addedDatasetNames": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset names that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetNames"
},
"addedMetadataDatasetPairs": {
"anyOf": [
{
"items": {
"description": "Pair of metadata dataset and dataset added to the vector database.",
"properties": {
"datasetId": {
"description": "The ID of the dataset added to the vector database.",
"title": "datasetId",
"type": "string"
},
"datasetName": {
"description": "The name of the dataset added to the vector database.",
"title": "datasetName",
"type": "string"
},
"metadataDatasetId": {
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId",
"type": "string"
},
"metadataDatasetName": {
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName",
"type": "string"
}
},
"required": [
"metadataDatasetId",
"datasetId",
"metadataDatasetName",
"datasetName"
],
"title": "MetadataDatasetPairApiFormatted",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "Pairs of metadata dataset and dataset added to the vector database.",
"title": "addedMetadataDatasetPairs"
},
"chunkOverlapPercentage": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage that the vector database uses.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the text chunk (measured in tokens) that the vector database uses.",
"title": "chunkSize"
},
"chunkingLengthFunction": {
"anyOf": [
{
"description": "Supported length functions for text splitters.",
"enum": [
"tokenizer_length_function",
"approximate_token_count"
],
"title": "ChunkingLengthFunctionNames",
"type": "string"
},
{
"type": "null"
}
],
"default": "approximate_token_count",
"description": "The length function to use for the text splitter."
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method the vector database uses."
},
"chunksCount": {
"description": "The number of text chunks in the vector database.",
"title": "chunksCount",
"type": "integer"
},
"creationDate": {
"description": "The creation date of the vector database (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationDuration": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The duration of the vector database creation.",
"title": "creationDuration"
},
"creationUserId": {
"description": "The ID of the user that created this vector database.",
"title": "creationUserId",
"type": "string"
},
"customChunking": {
"description": "Whether the vector database uses custom chunking.",
"title": "customChunking",
"type": "boolean"
},
"datasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset the vector database was built from.",
"title": "datasetId"
},
"datasetName": {
"description": "The name of the dataset this vector database was built from.",
"title": "datasetName",
"type": "string"
},
"deploymentStatus": {
"anyOf": [
{
"description": "Sort order values for listing vector databases.",
"enum": [
"Created",
"Assembling",
"Registered",
"Deployed"
],
"title": "VectorDatabaseDeploymentStatuses",
"type": "string"
},
{
"type": "null"
}
],
"description": "How far along in the deployment process this vector database is."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model the vector database uses.",
"title": "embeddingModel"
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model embedding (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the vector database creation error (in case of a creation error).",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database creation error (in case of a creation error).",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"externalVectorDatabaseConnection": {
"anyOf": [
{
"discriminator": {
"mapping": {
"elasticsearch": "#/components/schemas/ElasticsearchConnection",
"pinecone": "#/components/schemas/PineconeConnection"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnection",
"type": "object"
},
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnection",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The external vector database connection to use.",
"title": "externalVectorDatabaseConnection"
},
"familyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "An ID associated with a family of vector databases, that is, a parent and all descendant vector databases. All vector databases that are descendants of the same root parent share a family ID.The family ID is equal to the vector database ID of the root parent.Like this each vector database knows it's direct parent and the root parent.",
"title": "familyId"
},
"id": {
"description": "The ID of the vector database.",
"title": "id",
"type": "string"
},
"isSeparatorRegex": {
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"metadataColumns": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of metadata columns in the vector database.",
"title": "metadataColumns"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId"
},
"metadataDatasetName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName"
},
"name": {
"description": "The name of the vector database.",
"title": "name",
"type": "string"
},
"organizationId": {
"description": "The ID of the DataRobot organization this vector database belongs to.",
"title": "organizationId",
"type": "string"
},
"parentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the direct parent vector database.It is generated when a vector database is created from another vector database.For the root (parent), ID is 'None'.",
"title": "parentId"
},
"percentage": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Vector database progress percentage.",
"title": "percentage"
},
"playgroundsCount": {
"description": "The number of playgrounds that use this vector database.",
"title": "playgroundsCount",
"type": "integer"
},
"separators": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"description": "The text chunking separators that the vector database uses.",
"title": "separators"
},
"size": {
"description": "The size of the vector database (in bytes).",
"title": "size",
"type": "integer"
},
"skippedChunksCount": {
"description": "The number of text chunks skipped during vector database creation.",
"title": "skippedChunksCount",
"type": "integer"
},
"source": {
"description": "The source of the vector database.",
"enum": [
"DataRobot",
"External",
"Pinecone",
"Elasticsearch"
],
"title": "VectorDatabaseSource",
"type": "string"
},
"tenantId": {
"description": "The ID of the DataRobot tenant this vector database belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case the vector database is linked to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this vector database.",
"title": "userName",
"type": "string"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model vector database (in case of using a custom model vector database).",
"title": "validationId"
},
"version": {
"description": "The version of the vector database linked to a certain family ID.",
"title": "version",
"type": "integer"
}
},
"required": [
"id",
"name",
"size",
"useCaseId",
"datasetId",
"embeddingModel",
"embeddingValidationId",
"embeddingRegisteredModelId",
"chunkSize",
"chunkingMethod",
"chunkOverlapPercentage",
"chunksCount",
"skippedChunksCount",
"customChunking",
"separators",
"isSeparatorRegex",
"creationDate",
"creationUserId",
"organizationId",
"tenantId",
"lastUpdateDate",
"executionStatus",
"errorMessage",
"errorResolution",
"source",
"validationId",
"parentId",
"familyId",
"addedDatasetIds",
"version",
"playgroundsCount",
"datasetName",
"userName",
"addedDatasetNames"
],
"title": "VectorDatabaseResponse",
"type": "object"
}
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 |
List supported embedding models¶
Operation path: GET /api/v2/genai/vectorDatabases/supportedEmbeddings/
Authentication requirements: BearerAuth
List the supported embedding models for building vector databases.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| datasetId | query | any | false | Only retrieve the embedding models compatible with this dataset ID. |
| useCaseId | query | any | false | If specified, include the custom model embeddings available for this use case ID. |
Example responses¶
200 Response
{
"description": "API response object for \"List supported embeddings\".",
"properties": {
"customModelEmbeddingValidations": {
"description": "The list of validated custom embedding models.",
"items": {
"description": "API response object for a single custom embedding model.",
"properties": {
"id": {
"description": "The validation ID of the custom embedding model.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the custom embedding model.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "SupportedCustomModelEmbeddings",
"type": "object"
},
"title": "customModelEmbeddingValidations",
"type": "array"
},
"defaultEmbeddingModel": {
"description": "The name of the default embedding model.",
"title": "defaultEmbeddingModel",
"type": "string"
},
"embeddingModels": {
"description": "The list of embeddings models.",
"items": {
"description": "API response object for a single embedding model.",
"properties": {
"description": {
"description": "The description of the embedding model.",
"title": "description",
"type": "string"
},
"embeddingModel": {
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
"languages": {
"description": "The list of languages the embedding models supports.",
"items": {
"description": "The names of dataset languages.",
"enum": [
"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"
],
"title": "DatasetLanguages",
"type": "string"
},
"title": "languages",
"type": "array"
},
"maxSequenceLength": {
"description": "The maximum input token sequence length that the embedding model can accept.",
"title": "maxSequenceLength",
"type": "integer"
}
},
"required": [
"embeddingModel",
"description",
"maxSequenceLength",
"languages"
],
"title": "EmbeddingModel",
"type": "object"
},
"title": "embeddingModels",
"type": "array"
},
"nimEmbeddingModels": {
"description": "The list of NIM registered models.",
"items": {
"description": "API response object for a single registered NIM embedding model.",
"properties": {
"description": {
"description": "The description of the registered NIM model.",
"title": "description",
"type": "string"
},
"id": {
"description": "The validation ID of the registered NIM model.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the registered NIM model.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name",
"description"
],
"title": "SupportedNIMModelEmbeddings",
"type": "object"
},
"title": "nimEmbeddingModels",
"type": "array"
}
},
"required": [
"embeddingModels",
"defaultEmbeddingModel"
],
"title": "SupportedEmbeddingsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Supported embeddings successfully retrieved. | SupportedEmbeddingsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
List supported vector database retrieval settings¶
Operation path: GET /api/v2/genai/vectorDatabases/supportedRetrievalSettings/
Authentication requirements: BearerAuth
List all vector database retrieval settings that are supported by LLM blueprints.
Example responses¶
200 Response
{
"description": "API response object for \"Retrieve supported retrieval settings\".",
"properties": {
"settings": {
"description": "The list of retrieval settings.",
"items": {
"description": "API response object for a single vector database setting parameter.",
"properties": {
"default": {
"description": "The default value of the parameter.",
"title": "default"
},
"description": {
"description": "The description of the parameter.",
"title": "description",
"type": "string"
},
"enum": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of possible values for the parameter.",
"title": "enum"
},
"groupId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The identifier of the group the parameter belongs to.",
"title": "groupId"
},
"maximum": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the parameter.",
"title": "maximum"
},
"minimum": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the parameter.",
"title": "minimum"
},
"name": {
"description": "The name of the parameter.",
"title": "name",
"type": "string"
},
"settings": {
"anyOf": [
{
"items": "[Circular]",
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of available settings for the parameter.",
"title": "settings"
},
"title": {
"description": "The title of the parameter.",
"title": "title",
"type": "string"
},
"type": {
"anyOf": [
{
"description": "The types of vector database setting parameters.",
"enum": [
"string",
"integer",
"boolean",
"null",
"number",
"array"
],
"title": "VectorDatabaseSettingTypes",
"type": "string"
},
{
"items": {
"description": "The types of vector database setting parameters.",
"enum": [
"string",
"integer",
"boolean",
"null",
"number",
"array"
],
"title": "VectorDatabaseSettingTypes",
"type": "string"
},
"type": "array"
}
],
"description": "The type of the parameter.",
"title": "type"
}
},
"required": [
"name",
"type",
"description",
"title"
],
"title": "VectorDatabaseSettingParameter",
"type": "object"
},
"title": "settings",
"type": "array"
}
},
"required": [
"settings"
],
"title": "SupportedRetrievalSettingsResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Supported vector database retrieval settings successfully retrieved. | SupportedRetrievalSettingsResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
List supported text chunking methods¶
Operation path: GET /api/v2/genai/vectorDatabases/supportedTextChunkings/
Authentication requirements: BearerAuth
List the supported text chunking methods for building vector databases.
Example responses¶
200 Response
{
"description": "API response for \"List text chunking methods\".",
"properties": {
"textChunkingConfigs": {
"description": "The list of text chunking configurations.",
"items": {
"description": "API response object for a single text chunking configuration.",
"properties": {
"defaultMethod": {
"description": "The name of the default text chunking method.",
"title": "defaultMethod",
"type": "string"
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"description": "Model names for custom embedding models.",
"enum": [
"custom-embeddings/default"
],
"title": "CustomEmbeddingModelNames",
"type": "string"
}
],
"description": "The name of the embedding model.",
"title": "embeddingModel"
},
"methods": {
"description": "The list of text chunking methods.",
"items": {
"description": "API response object for a single text chunking method.",
"properties": {
"chunkingMethod": {
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
"chunkingParameters": {
"description": "The list of text chunking parameters.",
"items": {
"description": "API response object for a single text chunking parameter.",
"properties": {
"default": {
"anyOf": [
{
"type": "integer"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "boolean"
}
],
"description": "The default value of the parameter.",
"title": "default"
},
"description": {
"description": "The description of the parameter.",
"title": "description",
"type": "string"
},
"max": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the parameter (inclusive).",
"title": "max"
},
"min": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the parameter (inclusive).",
"title": "min"
},
"name": {
"description": "The name of the parameter.",
"title": "name",
"type": "string"
},
"type": {
"description": "Supported parameter data types for text chunking parameters.",
"enum": [
"int",
"list[str]",
"bool"
],
"title": "ChunkingParameterTypes",
"type": "string"
}
},
"required": [
"name",
"type",
"min",
"max",
"description",
"default"
],
"title": "TextChunkingParameterFields",
"type": "object"
},
"title": "chunkingParameters",
"type": "array"
},
"description": {
"description": "The description of the text chunking method.",
"title": "description",
"type": "string"
},
"title": {
"description": "Supported user-facing friendly ames of text chunking methods.",
"enum": [
"Recursive",
"Semantic"
],
"title": "ChunkingMethodNamesTitle",
"type": "string"
}
},
"required": [
"chunkingMethod",
"title",
"chunkingParameters",
"description"
],
"title": "TextChunkingMethod",
"type": "object"
},
"title": "methods",
"type": "array"
}
},
"required": [
"embeddingModel",
"methods",
"defaultMethod"
],
"title": "TextChunkingConfig",
"type": "object"
},
"title": "textChunkingConfigs",
"type": "array"
}
},
"required": [
"textChunkingConfigs"
],
"title": "SupportedTextChunkingResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Supported text chunking methods successfully retrieved. | SupportedTextChunkingResponse |
Delete vector database by vector database ID¶
Operation path: DELETE /api/v2/genai/vectorDatabases/{vectorDatabaseId}/
Authentication requirements: BearerAuth
Delete an existing vector database.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| vectorDatabaseId | path | string | true | The ID of the vector database 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 | Vector database successfully deleted. | None |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Retrieve vector database by vector database ID¶
Operation path: GET /api/v2/genai/vectorDatabases/{vectorDatabaseId}/
Authentication requirements: BearerAuth
Retrieve an existing vector database.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| vectorDatabaseId | path | string | true | The ID of the vector database to retrieve. |
Example responses¶
200 Response
{
"description": "API response object for a single vector database.",
"properties": {
"addedDatasetIds": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset IDs that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetIds"
},
"addedDatasetNames": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset names that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetNames"
},
"addedMetadataDatasetPairs": {
"anyOf": [
{
"items": {
"description": "Pair of metadata dataset and dataset added to the vector database.",
"properties": {
"datasetId": {
"description": "The ID of the dataset added to the vector database.",
"title": "datasetId",
"type": "string"
},
"datasetName": {
"description": "The name of the dataset added to the vector database.",
"title": "datasetName",
"type": "string"
},
"metadataDatasetId": {
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId",
"type": "string"
},
"metadataDatasetName": {
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName",
"type": "string"
}
},
"required": [
"metadataDatasetId",
"datasetId",
"metadataDatasetName",
"datasetName"
],
"title": "MetadataDatasetPairApiFormatted",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "Pairs of metadata dataset and dataset added to the vector database.",
"title": "addedMetadataDatasetPairs"
},
"chunkOverlapPercentage": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage that the vector database uses.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the text chunk (measured in tokens) that the vector database uses.",
"title": "chunkSize"
},
"chunkingLengthFunction": {
"anyOf": [
{
"description": "Supported length functions for text splitters.",
"enum": [
"tokenizer_length_function",
"approximate_token_count"
],
"title": "ChunkingLengthFunctionNames",
"type": "string"
},
{
"type": "null"
}
],
"default": "approximate_token_count",
"description": "The length function to use for the text splitter."
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method the vector database uses."
},
"chunksCount": {
"description": "The number of text chunks in the vector database.",
"title": "chunksCount",
"type": "integer"
},
"creationDate": {
"description": "The creation date of the vector database (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationDuration": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The duration of the vector database creation.",
"title": "creationDuration"
},
"creationUserId": {
"description": "The ID of the user that created this vector database.",
"title": "creationUserId",
"type": "string"
},
"customChunking": {
"description": "Whether the vector database uses custom chunking.",
"title": "customChunking",
"type": "boolean"
},
"datasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset the vector database was built from.",
"title": "datasetId"
},
"datasetName": {
"description": "The name of the dataset this vector database was built from.",
"title": "datasetName",
"type": "string"
},
"deploymentStatus": {
"anyOf": [
{
"description": "Sort order values for listing vector databases.",
"enum": [
"Created",
"Assembling",
"Registered",
"Deployed"
],
"title": "VectorDatabaseDeploymentStatuses",
"type": "string"
},
{
"type": "null"
}
],
"description": "How far along in the deployment process this vector database is."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model the vector database uses.",
"title": "embeddingModel"
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model embedding (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the vector database creation error (in case of a creation error).",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database creation error (in case of a creation error).",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"externalVectorDatabaseConnection": {
"anyOf": [
{
"discriminator": {
"mapping": {
"elasticsearch": "#/components/schemas/ElasticsearchConnection",
"pinecone": "#/components/schemas/PineconeConnection"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnection",
"type": "object"
},
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnection",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The external vector database connection to use.",
"title": "externalVectorDatabaseConnection"
},
"familyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "An ID associated with a family of vector databases, that is, a parent and all descendant vector databases. All vector databases that are descendants of the same root parent share a family ID.The family ID is equal to the vector database ID of the root parent.Like this each vector database knows it's direct parent and the root parent.",
"title": "familyId"
},
"id": {
"description": "The ID of the vector database.",
"title": "id",
"type": "string"
},
"isSeparatorRegex": {
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"metadataColumns": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of metadata columns in the vector database.",
"title": "metadataColumns"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId"
},
"metadataDatasetName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName"
},
"name": {
"description": "The name of the vector database.",
"title": "name",
"type": "string"
},
"organizationId": {
"description": "The ID of the DataRobot organization this vector database belongs to.",
"title": "organizationId",
"type": "string"
},
"parentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the direct parent vector database.It is generated when a vector database is created from another vector database.For the root (parent), ID is 'None'.",
"title": "parentId"
},
"percentage": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Vector database progress percentage.",
"title": "percentage"
},
"playgroundsCount": {
"description": "The number of playgrounds that use this vector database.",
"title": "playgroundsCount",
"type": "integer"
},
"separators": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"description": "The text chunking separators that the vector database uses.",
"title": "separators"
},
"size": {
"description": "The size of the vector database (in bytes).",
"title": "size",
"type": "integer"
},
"skippedChunksCount": {
"description": "The number of text chunks skipped during vector database creation.",
"title": "skippedChunksCount",
"type": "integer"
},
"source": {
"description": "The source of the vector database.",
"enum": [
"DataRobot",
"External",
"Pinecone",
"Elasticsearch"
],
"title": "VectorDatabaseSource",
"type": "string"
},
"tenantId": {
"description": "The ID of the DataRobot tenant this vector database belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case the vector database is linked to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this vector database.",
"title": "userName",
"type": "string"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model vector database (in case of using a custom model vector database).",
"title": "validationId"
},
"version": {
"description": "The version of the vector database linked to a certain family ID.",
"title": "version",
"type": "integer"
}
},
"required": [
"id",
"name",
"size",
"useCaseId",
"datasetId",
"embeddingModel",
"embeddingValidationId",
"embeddingRegisteredModelId",
"chunkSize",
"chunkingMethod",
"chunkOverlapPercentage",
"chunksCount",
"skippedChunksCount",
"customChunking",
"separators",
"isSeparatorRegex",
"creationDate",
"creationUserId",
"organizationId",
"tenantId",
"lastUpdateDate",
"executionStatus",
"errorMessage",
"errorResolution",
"source",
"validationId",
"parentId",
"familyId",
"addedDatasetIds",
"version",
"playgroundsCount",
"datasetName",
"userName",
"addedDatasetNames"
],
"title": "VectorDatabaseResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Vector database successfully retrieved. | VectorDatabaseResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Edit vector database by vector database ID¶
Operation path: PATCH /api/v2/genai/vectorDatabases/{vectorDatabaseId}/
Authentication requirements: BearerAuth
Edit an existing vector database.
Body parameter¶
{
"description": "The body of the \"Edit vector database\" request.",
"properties": {
"credentialId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The new ID of the credential to access a connected vector database.",
"title": "credentialId"
},
"name": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The new name of the vector database.",
"title": "name"
}
},
"title": "EditVectorDatabaseRequest",
"type": "object"
}
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
{
"description": "API response object for a single vector database.",
"properties": {
"addedDatasetIds": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset IDs that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetIds"
},
"addedDatasetNames": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset names that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetNames"
},
"addedMetadataDatasetPairs": {
"anyOf": [
{
"items": {
"description": "Pair of metadata dataset and dataset added to the vector database.",
"properties": {
"datasetId": {
"description": "The ID of the dataset added to the vector database.",
"title": "datasetId",
"type": "string"
},
"datasetName": {
"description": "The name of the dataset added to the vector database.",
"title": "datasetName",
"type": "string"
},
"metadataDatasetId": {
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId",
"type": "string"
},
"metadataDatasetName": {
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName",
"type": "string"
}
},
"required": [
"metadataDatasetId",
"datasetId",
"metadataDatasetName",
"datasetName"
],
"title": "MetadataDatasetPairApiFormatted",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "Pairs of metadata dataset and dataset added to the vector database.",
"title": "addedMetadataDatasetPairs"
},
"chunkOverlapPercentage": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage that the vector database uses.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the text chunk (measured in tokens) that the vector database uses.",
"title": "chunkSize"
},
"chunkingLengthFunction": {
"anyOf": [
{
"description": "Supported length functions for text splitters.",
"enum": [
"tokenizer_length_function",
"approximate_token_count"
],
"title": "ChunkingLengthFunctionNames",
"type": "string"
},
{
"type": "null"
}
],
"default": "approximate_token_count",
"description": "The length function to use for the text splitter."
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method the vector database uses."
},
"chunksCount": {
"description": "The number of text chunks in the vector database.",
"title": "chunksCount",
"type": "integer"
},
"creationDate": {
"description": "The creation date of the vector database (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationDuration": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The duration of the vector database creation.",
"title": "creationDuration"
},
"creationUserId": {
"description": "The ID of the user that created this vector database.",
"title": "creationUserId",
"type": "string"
},
"customChunking": {
"description": "Whether the vector database uses custom chunking.",
"title": "customChunking",
"type": "boolean"
},
"datasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset the vector database was built from.",
"title": "datasetId"
},
"datasetName": {
"description": "The name of the dataset this vector database was built from.",
"title": "datasetName",
"type": "string"
},
"deploymentStatus": {
"anyOf": [
{
"description": "Sort order values for listing vector databases.",
"enum": [
"Created",
"Assembling",
"Registered",
"Deployed"
],
"title": "VectorDatabaseDeploymentStatuses",
"type": "string"
},
{
"type": "null"
}
],
"description": "How far along in the deployment process this vector database is."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model the vector database uses.",
"title": "embeddingModel"
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model embedding (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the vector database creation error (in case of a creation error).",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database creation error (in case of a creation error).",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"externalVectorDatabaseConnection": {
"anyOf": [
{
"discriminator": {
"mapping": {
"elasticsearch": "#/components/schemas/ElasticsearchConnection",
"pinecone": "#/components/schemas/PineconeConnection"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnection",
"type": "object"
},
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnection",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The external vector database connection to use.",
"title": "externalVectorDatabaseConnection"
},
"familyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "An ID associated with a family of vector databases, that is, a parent and all descendant vector databases. All vector databases that are descendants of the same root parent share a family ID.The family ID is equal to the vector database ID of the root parent.Like this each vector database knows it's direct parent and the root parent.",
"title": "familyId"
},
"id": {
"description": "The ID of the vector database.",
"title": "id",
"type": "string"
},
"isSeparatorRegex": {
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"metadataColumns": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of metadata columns in the vector database.",
"title": "metadataColumns"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId"
},
"metadataDatasetName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName"
},
"name": {
"description": "The name of the vector database.",
"title": "name",
"type": "string"
},
"organizationId": {
"description": "The ID of the DataRobot organization this vector database belongs to.",
"title": "organizationId",
"type": "string"
},
"parentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the direct parent vector database.It is generated when a vector database is created from another vector database.For the root (parent), ID is 'None'.",
"title": "parentId"
},
"percentage": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Vector database progress percentage.",
"title": "percentage"
},
"playgroundsCount": {
"description": "The number of playgrounds that use this vector database.",
"title": "playgroundsCount",
"type": "integer"
},
"separators": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"description": "The text chunking separators that the vector database uses.",
"title": "separators"
},
"size": {
"description": "The size of the vector database (in bytes).",
"title": "size",
"type": "integer"
},
"skippedChunksCount": {
"description": "The number of text chunks skipped during vector database creation.",
"title": "skippedChunksCount",
"type": "integer"
},
"source": {
"description": "The source of the vector database.",
"enum": [
"DataRobot",
"External",
"Pinecone",
"Elasticsearch"
],
"title": "VectorDatabaseSource",
"type": "string"
},
"tenantId": {
"description": "The ID of the DataRobot tenant this vector database belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case the vector database is linked to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this vector database.",
"title": "userName",
"type": "string"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model vector database (in case of using a custom model vector database).",
"title": "validationId"
},
"version": {
"description": "The version of the vector database linked to a certain family ID.",
"title": "version",
"type": "integer"
}
},
"required": [
"id",
"name",
"size",
"useCaseId",
"datasetId",
"embeddingModel",
"embeddingValidationId",
"embeddingRegisteredModelId",
"chunkSize",
"chunkingMethod",
"chunkOverlapPercentage",
"chunksCount",
"skippedChunksCount",
"customChunking",
"separators",
"isSeparatorRegex",
"creationDate",
"creationUserId",
"organizationId",
"tenantId",
"lastUpdateDate",
"executionStatus",
"errorMessage",
"errorResolution",
"source",
"validationId",
"parentId",
"familyId",
"addedDatasetIds",
"version",
"playgroundsCount",
"datasetName",
"userName",
"addedDatasetNames"
],
"title": "VectorDatabaseResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Vector database successfully updated. | VectorDatabaseResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Create custom model version by vector database ID¶
Operation path: POST /api/v2/genai/vectorDatabases/{vectorDatabaseId}/customModelVersions/
Authentication requirements: BearerAuth
Export the specified Vector Database as a custom model version in Model Registry.
Body parameter¶
{
"description": "The body of the \"Create custom model version\" request.",
"properties": {
"modelName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the custom model that this job will create.",
"title": "modelName"
},
"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"
},
"resources": {
"anyOf": [
{
"description": "The structure that describes resource settings for a custom model created from buzok.",
"properties": {
"maximumMemory": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum memory that can be allocated to the custom model.",
"title": "maximumMemory"
},
"networkEgressPolicy": {
"default": "Public",
"description": "Network egress policy for the custom model. Can be either Public or None.",
"maxLength": 5000,
"title": "networkEgressPolicy",
"type": "string"
},
"replicas": {
"default": 1,
"description": "A fixed number of replicas that will be created for the custom model.",
"title": "replicas",
"type": "integer"
},
"resourceBundleId": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "An identifier that represents a bundle of resources: Memory, CPU, GPU, etc. A list of available bundles can be obtained via the resource bundles endpoint.",
"title": "resourceBundleId"
}
},
"title": "CustomModelResourcesRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "The resources that the custom model will be provisioned with."
},
"targetColumnName": {
"default": "relevant",
"description": "The name of the column to use for prediction output in the custom model.",
"maxLength": 5000,
"title": "targetColumnName",
"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."
}
},
"title": "CreateVectorDatabaseCustomModelVersionRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| vectorDatabaseId | path | string | true | The ID of the vector database to create a custom model version for. |
| body | body | CreateVectorDatabaseCustomModelVersionRequest | 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 |
Export vector database dataset by vector database ID¶
Operation path: POST /api/v2/genai/vectorDatabases/{vectorDatabaseId}/datasetExportJobs/
Authentication requirements: BearerAuth
Export an existing vector database as dataset to Data Registry.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| vectorDatabaseId | path | string | true | The ID of the vector database to retrieve. |
Example responses¶
202 Response
{
"description": "API response object for exporting a vector database.",
"properties": {
"exportDatasetId": {
"description": "The Data Registry dataset ID.",
"title": "exportDatasetId",
"type": "string"
},
"jobId": {
"description": "The ID of the export job.",
"format": "uuid4",
"title": "jobId",
"type": "string"
},
"vectorDatabaseId": {
"description": "The ID of the vector database.",
"title": "vectorDatabaseId",
"type": "string"
}
},
"required": [
"jobId",
"exportDatasetId",
"vectorDatabaseId"
],
"title": "VectorDatabaseExportResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Vector database export job successfully accepted.Follow the Location header to poll for job execution status. |
VectorDatabaseExportResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Create new custom model version by vector database ID¶
Operation path: POST /api/v2/genai/vectorDatabases/{vectorDatabaseId}/deployments/
Authentication requirements: BearerAuth
Export the specified vector database as a custom model version, register it, and deploy it on a new deployment.
Body parameter¶
{
"description": "The body of the \"Create vector database deployment\" request.",
"properties": {
"credentialId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the credential to access the connected vector database.",
"title": "credentialId"
},
"defaultPredictionServerId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of a prediction server for the new deployment to use. Cannot be used with predictionEnvironmentId.",
"title": "defaultPredictionServerId"
},
"modelName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the custom model that this job will create.",
"title": "modelName"
},
"predictionEnvironmentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the prediction environment for the new deployment to use. Cannot be used with defaultPredictionServerId.",
"title": "predictionEnvironmentId"
},
"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"
},
"resources": {
"anyOf": [
{
"description": "The structure that describes resource settings for a custom model created from buzok.",
"properties": {
"maximumMemory": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum memory that can be allocated to the custom model.",
"title": "maximumMemory"
},
"networkEgressPolicy": {
"default": "Public",
"description": "Network egress policy for the custom model. Can be either Public or None.",
"maxLength": 5000,
"title": "networkEgressPolicy",
"type": "string"
},
"replicas": {
"default": 1,
"description": "A fixed number of replicas that will be created for the custom model.",
"title": "replicas",
"type": "integer"
},
"resourceBundleId": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "An identifier that represents a bundle of resources: Memory, CPU, GPU, etc. A list of available bundles can be obtained via the resource bundles endpoint.",
"title": "resourceBundleId"
}
},
"title": "CustomModelResourcesRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "The resources that the custom model will be provisioned with."
},
"targetColumnName": {
"default": "relevant",
"description": "The name of the column to use for prediction output in the custom model.",
"maxLength": 5000,
"title": "targetColumnName",
"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."
}
},
"title": "CreateVectorDatabaseDeploymentRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| vectorDatabaseId | path | string | true | The ID of the vector database to create a custom model version for. |
| body | body | CreateVectorDatabaseDeploymentRequest | true | none |
Example responses¶
202 Response
{
"description": "The response to the \"Create vector database deployment\" request.",
"properties": {
"jobId": {
"description": "The ID of the job that will create the new vector database deployment.",
"format": "uuid4",
"title": "jobId",
"type": "string"
}
},
"required": [
"jobId"
],
"title": "CreateVectorDatabaseDeploymentResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Successful Response | CreateVectorDatabaseDeploymentResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Add documents by vector database ID¶
Operation path: PATCH /api/v2/genai/vectorDatabases/{vectorDatabaseId}/externalVectorDatabaseDocuments/
Authentication requirements: BearerAuth
Add documents to a connected vector database.
Body parameter¶
{
"description": "The body of the \"Update connected vector database\" request.",
"properties": {
"datasetId": {
"description": "The ID of the dataset to use for building the vector database.",
"title": "datasetId",
"type": "string"
},
"metadataCombinationStrategy": {
"description": "Strategy to use when the dataset and the metadata file have duplicate columns.",
"enum": [
"replace",
"merge"
],
"title": "MetadataCombinationStrategy",
"type": "string"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset to add metadata for building the vector database.",
"title": "metadataDatasetId"
}
},
"required": [
"datasetId"
],
"title": "UpdateConnectedVectorDatabaseRequest",
"type": "object"
}
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| vectorDatabaseId | path | string | true | The ID of the vector database to edit. |
| body | body | UpdateConnectedVectorDatabaseRequest | true | none |
Example responses¶
202 Response
{
"description": "API response object for a single vector database.",
"properties": {
"addedDatasetIds": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset IDs that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetIds"
},
"addedDatasetNames": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset names that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetNames"
},
"addedMetadataDatasetPairs": {
"anyOf": [
{
"items": {
"description": "Pair of metadata dataset and dataset added to the vector database.",
"properties": {
"datasetId": {
"description": "The ID of the dataset added to the vector database.",
"title": "datasetId",
"type": "string"
},
"datasetName": {
"description": "The name of the dataset added to the vector database.",
"title": "datasetName",
"type": "string"
},
"metadataDatasetId": {
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId",
"type": "string"
},
"metadataDatasetName": {
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName",
"type": "string"
}
},
"required": [
"metadataDatasetId",
"datasetId",
"metadataDatasetName",
"datasetName"
],
"title": "MetadataDatasetPairApiFormatted",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "Pairs of metadata dataset and dataset added to the vector database.",
"title": "addedMetadataDatasetPairs"
},
"chunkOverlapPercentage": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage that the vector database uses.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the text chunk (measured in tokens) that the vector database uses.",
"title": "chunkSize"
},
"chunkingLengthFunction": {
"anyOf": [
{
"description": "Supported length functions for text splitters.",
"enum": [
"tokenizer_length_function",
"approximate_token_count"
],
"title": "ChunkingLengthFunctionNames",
"type": "string"
},
{
"type": "null"
}
],
"default": "approximate_token_count",
"description": "The length function to use for the text splitter."
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method the vector database uses."
},
"chunksCount": {
"description": "The number of text chunks in the vector database.",
"title": "chunksCount",
"type": "integer"
},
"creationDate": {
"description": "The creation date of the vector database (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationDuration": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The duration of the vector database creation.",
"title": "creationDuration"
},
"creationUserId": {
"description": "The ID of the user that created this vector database.",
"title": "creationUserId",
"type": "string"
},
"customChunking": {
"description": "Whether the vector database uses custom chunking.",
"title": "customChunking",
"type": "boolean"
},
"datasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset the vector database was built from.",
"title": "datasetId"
},
"datasetName": {
"description": "The name of the dataset this vector database was built from.",
"title": "datasetName",
"type": "string"
},
"deploymentStatus": {
"anyOf": [
{
"description": "Sort order values for listing vector databases.",
"enum": [
"Created",
"Assembling",
"Registered",
"Deployed"
],
"title": "VectorDatabaseDeploymentStatuses",
"type": "string"
},
{
"type": "null"
}
],
"description": "How far along in the deployment process this vector database is."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model the vector database uses.",
"title": "embeddingModel"
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model embedding (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the vector database creation error (in case of a creation error).",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database creation error (in case of a creation error).",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"externalVectorDatabaseConnection": {
"anyOf": [
{
"discriminator": {
"mapping": {
"elasticsearch": "#/components/schemas/ElasticsearchConnection",
"pinecone": "#/components/schemas/PineconeConnection"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnection",
"type": "object"
},
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnection",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The external vector database connection to use.",
"title": "externalVectorDatabaseConnection"
},
"familyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "An ID associated with a family of vector databases, that is, a parent and all descendant vector databases. All vector databases that are descendants of the same root parent share a family ID.The family ID is equal to the vector database ID of the root parent.Like this each vector database knows it's direct parent and the root parent.",
"title": "familyId"
},
"id": {
"description": "The ID of the vector database.",
"title": "id",
"type": "string"
},
"isSeparatorRegex": {
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"metadataColumns": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of metadata columns in the vector database.",
"title": "metadataColumns"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId"
},
"metadataDatasetName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName"
},
"name": {
"description": "The name of the vector database.",
"title": "name",
"type": "string"
},
"organizationId": {
"description": "The ID of the DataRobot organization this vector database belongs to.",
"title": "organizationId",
"type": "string"
},
"parentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the direct parent vector database.It is generated when a vector database is created from another vector database.For the root (parent), ID is 'None'.",
"title": "parentId"
},
"percentage": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Vector database progress percentage.",
"title": "percentage"
},
"playgroundsCount": {
"description": "The number of playgrounds that use this vector database.",
"title": "playgroundsCount",
"type": "integer"
},
"separators": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"description": "The text chunking separators that the vector database uses.",
"title": "separators"
},
"size": {
"description": "The size of the vector database (in bytes).",
"title": "size",
"type": "integer"
},
"skippedChunksCount": {
"description": "The number of text chunks skipped during vector database creation.",
"title": "skippedChunksCount",
"type": "integer"
},
"source": {
"description": "The source of the vector database.",
"enum": [
"DataRobot",
"External",
"Pinecone",
"Elasticsearch"
],
"title": "VectorDatabaseSource",
"type": "string"
},
"tenantId": {
"description": "The ID of the DataRobot tenant this vector database belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case the vector database is linked to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this vector database.",
"title": "userName",
"type": "string"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model vector database (in case of using a custom model vector database).",
"title": "validationId"
},
"version": {
"description": "The version of the vector database linked to a certain family ID.",
"title": "version",
"type": "integer"
}
},
"required": [
"id",
"name",
"size",
"useCaseId",
"datasetId",
"embeddingModel",
"embeddingValidationId",
"embeddingRegisteredModelId",
"chunkSize",
"chunkingMethod",
"chunkOverlapPercentage",
"chunksCount",
"skippedChunksCount",
"customChunking",
"separators",
"isSeparatorRegex",
"creationDate",
"creationUserId",
"organizationId",
"tenantId",
"lastUpdateDate",
"executionStatus",
"errorMessage",
"errorResolution",
"source",
"validationId",
"parentId",
"familyId",
"addedDatasetIds",
"version",
"playgroundsCount",
"datasetName",
"userName",
"addedDatasetNames"
],
"title": "VectorDatabaseResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 202 | Accepted | Connected vector database update job successfully accepted. Follow the Location header to poll for job execution status. |
VectorDatabaseResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Retrieve vector database latest version by vector database ID¶
Operation path: GET /api/v2/genai/vectorDatabases/{vectorDatabaseId}/latestVersion/
Authentication requirements: BearerAuth
Retrieve the latest vector database within the family associated with this vector database.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| vectorDatabaseId | path | string | true | The ID of the vector database to retrieve the latest version. |
| completedOnly | query | boolean | false | If true, only retrieve the vector databases that have finished building. The default is false. |
Example responses¶
200 Response
{
"description": "API response object for a single vector database.",
"properties": {
"addedDatasetIds": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset IDs that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetIds"
},
"addedDatasetNames": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset names that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetNames"
},
"addedMetadataDatasetPairs": {
"anyOf": [
{
"items": {
"description": "Pair of metadata dataset and dataset added to the vector database.",
"properties": {
"datasetId": {
"description": "The ID of the dataset added to the vector database.",
"title": "datasetId",
"type": "string"
},
"datasetName": {
"description": "The name of the dataset added to the vector database.",
"title": "datasetName",
"type": "string"
},
"metadataDatasetId": {
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId",
"type": "string"
},
"metadataDatasetName": {
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName",
"type": "string"
}
},
"required": [
"metadataDatasetId",
"datasetId",
"metadataDatasetName",
"datasetName"
],
"title": "MetadataDatasetPairApiFormatted",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "Pairs of metadata dataset and dataset added to the vector database.",
"title": "addedMetadataDatasetPairs"
},
"chunkOverlapPercentage": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage that the vector database uses.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the text chunk (measured in tokens) that the vector database uses.",
"title": "chunkSize"
},
"chunkingLengthFunction": {
"anyOf": [
{
"description": "Supported length functions for text splitters.",
"enum": [
"tokenizer_length_function",
"approximate_token_count"
],
"title": "ChunkingLengthFunctionNames",
"type": "string"
},
{
"type": "null"
}
],
"default": "approximate_token_count",
"description": "The length function to use for the text splitter."
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method the vector database uses."
},
"chunksCount": {
"description": "The number of text chunks in the vector database.",
"title": "chunksCount",
"type": "integer"
},
"creationDate": {
"description": "The creation date of the vector database (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationDuration": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The duration of the vector database creation.",
"title": "creationDuration"
},
"creationUserId": {
"description": "The ID of the user that created this vector database.",
"title": "creationUserId",
"type": "string"
},
"customChunking": {
"description": "Whether the vector database uses custom chunking.",
"title": "customChunking",
"type": "boolean"
},
"datasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset the vector database was built from.",
"title": "datasetId"
},
"datasetName": {
"description": "The name of the dataset this vector database was built from.",
"title": "datasetName",
"type": "string"
},
"deploymentStatus": {
"anyOf": [
{
"description": "Sort order values for listing vector databases.",
"enum": [
"Created",
"Assembling",
"Registered",
"Deployed"
],
"title": "VectorDatabaseDeploymentStatuses",
"type": "string"
},
{
"type": "null"
}
],
"description": "How far along in the deployment process this vector database is."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model the vector database uses.",
"title": "embeddingModel"
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model embedding (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the vector database creation error (in case of a creation error).",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database creation error (in case of a creation error).",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"externalVectorDatabaseConnection": {
"anyOf": [
{
"discriminator": {
"mapping": {
"elasticsearch": "#/components/schemas/ElasticsearchConnection",
"pinecone": "#/components/schemas/PineconeConnection"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnection",
"type": "object"
},
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnection",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The external vector database connection to use.",
"title": "externalVectorDatabaseConnection"
},
"familyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "An ID associated with a family of vector databases, that is, a parent and all descendant vector databases. All vector databases that are descendants of the same root parent share a family ID.The family ID is equal to the vector database ID of the root parent.Like this each vector database knows it's direct parent and the root parent.",
"title": "familyId"
},
"id": {
"description": "The ID of the vector database.",
"title": "id",
"type": "string"
},
"isSeparatorRegex": {
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"metadataColumns": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of metadata columns in the vector database.",
"title": "metadataColumns"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId"
},
"metadataDatasetName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName"
},
"name": {
"description": "The name of the vector database.",
"title": "name",
"type": "string"
},
"organizationId": {
"description": "The ID of the DataRobot organization this vector database belongs to.",
"title": "organizationId",
"type": "string"
},
"parentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the direct parent vector database.It is generated when a vector database is created from another vector database.For the root (parent), ID is 'None'.",
"title": "parentId"
},
"percentage": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Vector database progress percentage.",
"title": "percentage"
},
"playgroundsCount": {
"description": "The number of playgrounds that use this vector database.",
"title": "playgroundsCount",
"type": "integer"
},
"separators": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"description": "The text chunking separators that the vector database uses.",
"title": "separators"
},
"size": {
"description": "The size of the vector database (in bytes).",
"title": "size",
"type": "integer"
},
"skippedChunksCount": {
"description": "The number of text chunks skipped during vector database creation.",
"title": "skippedChunksCount",
"type": "integer"
},
"source": {
"description": "The source of the vector database.",
"enum": [
"DataRobot",
"External",
"Pinecone",
"Elasticsearch"
],
"title": "VectorDatabaseSource",
"type": "string"
},
"tenantId": {
"description": "The ID of the DataRobot tenant this vector database belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case the vector database is linked to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this vector database.",
"title": "userName",
"type": "string"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model vector database (in case of using a custom model vector database).",
"title": "validationId"
},
"version": {
"description": "The version of the vector database linked to a certain family ID.",
"title": "version",
"type": "integer"
}
},
"required": [
"id",
"name",
"size",
"useCaseId",
"datasetId",
"embeddingModel",
"embeddingValidationId",
"embeddingRegisteredModelId",
"chunkSize",
"chunkingMethod",
"chunkOverlapPercentage",
"chunksCount",
"skippedChunksCount",
"customChunking",
"separators",
"isSeparatorRegex",
"creationDate",
"creationUserId",
"organizationId",
"tenantId",
"lastUpdateDate",
"executionStatus",
"errorMessage",
"errorResolution",
"source",
"validationId",
"parentId",
"familyId",
"addedDatasetIds",
"version",
"playgroundsCount",
"datasetName",
"userName",
"addedDatasetNames"
],
"title": "VectorDatabaseResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Latest vector database version successfully retrieved. | VectorDatabaseResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
List supported languages by vector database ID¶
Operation path: GET /api/v2/genai/vectorDatabases/{vectorDatabaseId}/supportedSyntheticDatasetGenerationLanguages/
Authentication requirements: BearerAuth
List the languages for synthetic dataset generation that are supported by this vector database.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| vectorDatabaseId | path | string | true | The ID of the vector database to retrieve supported languages. |
Example responses¶
200 Response
{
"description": "API response object for \"List supported languages for Synthetic Dataset generation\".",
"properties": {
"recommendedLanguage": {
"description": "The recommended language.",
"title": "recommendedLanguage",
"type": "string"
},
"supportedLanguages": {
"description": "The list of supported languages.",
"items": {
"type": "string"
},
"title": "supportedLanguages",
"type": "array"
}
},
"required": [
"recommendedLanguage",
"supportedLanguages"
],
"title": "SupportedLanguagesResponse",
"type": "object"
}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Supported languages successfully retrieved. | SupportedLanguagesResponse |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Retrieve text chunks and embeddings by vector database ID¶
Operation path: GET /api/v2/genai/vectorDatabases/{vectorDatabaseId}/textAndEmbeddings/
Authentication requirements: BearerAuth
Retrieve the text chunk and embeddings asset for an existing vector database.
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| vectorDatabaseId | path | string | true | The ID of the vector database to retrieve the assets for. |
| part | query | any | false | Retrieve the additional file for this addition number. |
Example responses¶
200 Response
{}
Responses¶
| Status | Meaning | Description | Schema |
|---|---|---|---|
| 200 | OK | Text and embeddings asset successfully retrieved. | Inline |
| 422 | Unprocessable Entity | Validation Error | HTTPValidationErrorResponse |
Response Schema¶
Schemas¶
ChunkingLengthFunctionNames
{
"description": "Supported length functions for text splitters.",
"enum": [
"tokenizer_length_function",
"approximate_token_count"
],
"title": "ChunkingLengthFunctionNames",
"type": "string"
}
ChunkingLengthFunctionNames
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ChunkingLengthFunctionNames | string | false | Supported length functions for text splitters. |
Enumerated Values¶
| Property | Value |
|---|---|
| ChunkingLengthFunctionNames | [tokenizer_length_function, approximate_token_count] |
ChunkingMethodNames
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
}
ChunkingMethodNames
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ChunkingMethodNames | string | false | Supported names of text chunking methods. |
Enumerated Values¶
| Property | Value |
|---|---|
| ChunkingMethodNames | [recursive, semantic] |
ChunkingMethodNamesTitle
{
"description": "Supported user-facing friendly ames of text chunking methods.",
"enum": [
"Recursive",
"Semantic"
],
"title": "ChunkingMethodNamesTitle",
"type": "string"
}
ChunkingMethodNamesTitle
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| ChunkingMethodNamesTitle | string | false | Supported user-facing friendly ames of text chunking methods. |
Enumerated Values¶
| Property | Value |
|---|---|
| ChunkingMethodNamesTitle | [Recursive, Semantic] |
ChunkingParameterTypes
{
"description": "Supported parameter data types for text chunking parameters.",
"enum": [
"int",
"list[str]",
"bool"
],
"title": "ChunkingParameterTypes",
"type": "string"
}
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
{
"description": "Chunking parameters for creating a vector database.",
"properties": {
"chunkOverlapPercentage": {
"anyOf": [
{
"maximum": 50,
"minimum": 0,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage to use for text chunking.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk size to use for text chunking (measured in tokens).",
"title": "chunkSize"
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method to use."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model to use. If omitted, DataRobot will choose the default embedding model automatically."
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom embedding model (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"isSeparatorRegex": {
"default": false,
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"separators": {
"anyOf": [
{
"items": {
"maxLength": 20,
"type": "string"
},
"maxItems": 9,
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of separators to use for text chunking.",
"title": "separators"
}
},
"title": "ChunkingParameters",
"type": "object"
}
ChunkingParameters
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chunkOverlapPercentage | any | false | The chunk overlap percentage to use for text chunking. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | integer | false | maximum: 50 minimum: 0 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chunkSize | any | false | The chunk size to use for text chunking (measured in tokens). |
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 |
|---|---|---|---|---|
| chunkingMethod | any | false | The text chunking method to use. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ChunkingMethodNames | false | Supported names of text chunking methods. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| embeddingModel | any | false | The name of the embedding model to use. If omitted, DataRobot will choose the default embedding model automatically. |
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 | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| embeddingRegisteredModelId | any | false | The ID of registered model (in case of using NIM registered model for embeddings). |
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 |
|---|---|---|---|---|
| embeddingValidationId | any | false | The validation ID of the custom embedding model (in case of using a custom model for embeddings). |
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 |
|---|---|---|---|---|
| isSeparatorRegex | boolean | false | Whether the text chunking separator uses a regular expression. | |
| separators | any | false | The list of separators to use for text chunking. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [string] | false | maxItems: 9 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
CreateCustomModelEmbeddingValidationRequest
{
"description": "The body of the \"Validate custom model\" request.",
"properties": {
"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": {
"description": "The name of the column the custom model uses for prompt text input.",
"maxLength": 5000,
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"maxLength": 5000,
"title": "targetColumnName",
"type": "string"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case to associate with the validated custom model.",
"title": "useCaseId"
}
},
"required": [
"deploymentId",
"promptColumnName",
"targetColumnName"
],
"title": "CreateCustomModelEmbeddingValidationRequest",
"type": "object"
}
CreateCustomModelEmbeddingValidationRequest
Properties¶
| 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 | 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 | 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 |
CreateCustomModelVectorDatabaseFromDeploymentRequest
{
"description": "The body of the \"Create vector database from custom model deployment\" request.",
"properties": {
"deploymentId": {
"description": "The ID of the custom model deployment.",
"title": "deploymentId",
"type": "string"
},
"modelId": {
"description": "The ID of the model in the custom model deployment.",
"title": "modelId",
"type": "string"
},
"name": {
"description": "The name of the vector database.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
},
"promptColumnName": {
"description": "The name of the column the custom model uses for prompt text input.",
"maxLength": 5000,
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"maxLength": 5000,
"title": "targetColumnName",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case to link the vector database to.",
"title": "useCaseId",
"type": "string"
}
},
"required": [
"name",
"useCaseId",
"promptColumnName",
"targetColumnName",
"deploymentId",
"modelId"
],
"title": "CreateCustomModelVectorDatabaseFromDeploymentRequest",
"type": "object"
}
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 minLength: 1 minLength: 1 |
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
{
"description": "The body of the \"Create vector database from validation ID\" request.",
"properties": {
"name": {
"description": "The name of the vector database.",
"maxLength": 5000,
"minLength": 1,
"title": "name",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case to link the vector database to.",
"title": "useCaseId",
"type": "string"
},
"validationId": {
"description": "The validation ID of the custom model validation.",
"title": "validationId",
"type": "string"
}
},
"required": [
"name",
"useCaseId",
"validationId"
],
"title": "CreateCustomModelVectorDatabaseFromValidationIdPayload",
"type": "object"
}
CreateCustomModelVectorDatabaseFromValidationIdPayload
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| name | string | true | maxLength: 5000 minLength: 1 minLength: 1 |
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. |
CreateCustomModelVectorDatabaseValidationRequest
{
"description": "The body of the \"Validate custom model\" request.",
"properties": {
"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": {
"description": "The name of the column the custom model uses for prompt text input.",
"maxLength": 5000,
"title": "promptColumnName",
"type": "string"
},
"targetColumnName": {
"description": "The name of the column the custom model uses for prediction output.",
"maxLength": 5000,
"title": "targetColumnName",
"type": "string"
},
"useCaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the use case to associate with the validated custom model.",
"title": "useCaseId"
}
},
"required": [
"deploymentId",
"promptColumnName",
"targetColumnName"
],
"title": "CreateCustomModelVectorDatabaseValidationRequest",
"type": "object"
}
CreateCustomModelVectorDatabaseValidationRequest
Properties¶
| 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 | 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 | 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 |
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. |
CreateVectorDatabaseCustomModelVersionRequest
{
"description": "The body of the \"Create custom model version\" request.",
"properties": {
"modelName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the custom model that this job will create.",
"title": "modelName"
},
"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"
},
"resources": {
"anyOf": [
{
"description": "The structure that describes resource settings for a custom model created from buzok.",
"properties": {
"maximumMemory": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum memory that can be allocated to the custom model.",
"title": "maximumMemory"
},
"networkEgressPolicy": {
"default": "Public",
"description": "Network egress policy for the custom model. Can be either Public or None.",
"maxLength": 5000,
"title": "networkEgressPolicy",
"type": "string"
},
"replicas": {
"default": 1,
"description": "A fixed number of replicas that will be created for the custom model.",
"title": "replicas",
"type": "integer"
},
"resourceBundleId": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "An identifier that represents a bundle of resources: Memory, CPU, GPU, etc. A list of available bundles can be obtained via the resource bundles endpoint.",
"title": "resourceBundleId"
}
},
"title": "CustomModelResourcesRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "The resources that the custom model will be provisioned with."
},
"targetColumnName": {
"default": "relevant",
"description": "The name of the column to use for prediction output in the custom model.",
"maxLength": 5000,
"title": "targetColumnName",
"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."
}
},
"title": "CreateVectorDatabaseCustomModelVersionRequest",
"type": "object"
}
CreateVectorDatabaseCustomModelVersionRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| modelName | any | false | The name of the custom model that this job will create. |
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 |
|---|---|---|---|---|
| promptColumnName | string | false | maxLength: 5000 |
The name of the column to use for prompt text input in the custom model. |
| resources | any | false | The resources that the custom model will be provisioned with. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CustomModelResourcesRequest | false | The structure that describes resource settings for a custom model created from buzok. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| targetColumnName | string | false | maxLength: 5000 |
The name of the column to use for prediction output in the custom model. |
| 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 |
CreateVectorDatabaseDeploymentRequest
{
"description": "The body of the \"Create vector database deployment\" request.",
"properties": {
"credentialId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the credential to access the connected vector database.",
"title": "credentialId"
},
"defaultPredictionServerId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of a prediction server for the new deployment to use. Cannot be used with predictionEnvironmentId.",
"title": "defaultPredictionServerId"
},
"modelName": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the custom model that this job will create.",
"title": "modelName"
},
"predictionEnvironmentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the prediction environment for the new deployment to use. Cannot be used with defaultPredictionServerId.",
"title": "predictionEnvironmentId"
},
"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"
},
"resources": {
"anyOf": [
{
"description": "The structure that describes resource settings for a custom model created from buzok.",
"properties": {
"maximumMemory": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum memory that can be allocated to the custom model.",
"title": "maximumMemory"
},
"networkEgressPolicy": {
"default": "Public",
"description": "Network egress policy for the custom model. Can be either Public or None.",
"maxLength": 5000,
"title": "networkEgressPolicy",
"type": "string"
},
"replicas": {
"default": 1,
"description": "A fixed number of replicas that will be created for the custom model.",
"title": "replicas",
"type": "integer"
},
"resourceBundleId": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "An identifier that represents a bundle of resources: Memory, CPU, GPU, etc. A list of available bundles can be obtained via the resource bundles endpoint.",
"title": "resourceBundleId"
}
},
"title": "CustomModelResourcesRequest",
"type": "object"
},
{
"type": "null"
}
],
"description": "The resources that the custom model will be provisioned with."
},
"targetColumnName": {
"default": "relevant",
"description": "The name of the column to use for prediction output in the custom model.",
"maxLength": 5000,
"title": "targetColumnName",
"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."
}
},
"title": "CreateVectorDatabaseDeploymentRequest",
"type": "object"
}
CreateVectorDatabaseDeploymentRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| credentialId | any | false | The ID of the credential to access the connected vector database. |
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 |
|---|---|---|---|---|
| defaultPredictionServerId | any | false | The ID of a prediction server for the new deployment to use. Cannot be used with predictionEnvironmentId. |
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 |
|---|---|---|---|---|
| modelName | any | false | The name of the custom model that this job will create. |
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 |
|---|---|---|---|---|
| predictionEnvironmentId | any | false | The ID of the prediction environment for the new deployment to use. Cannot be used with defaultPredictionServerId. |
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 | string | false | maxLength: 5000 |
The name of the column to use for prompt text input in the custom model. |
| resources | any | false | The resources that the custom model will be provisioned with. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | CustomModelResourcesRequest | false | The structure that describes resource settings for a custom model created from buzok. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| targetColumnName | string | false | maxLength: 5000 |
The name of the column to use for prediction output in the custom model. |
| 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 |
CreateVectorDatabaseDeploymentResponse
{
"description": "The response to the \"Create vector database deployment\" request.",
"properties": {
"jobId": {
"description": "The ID of the job that will create the new vector database deployment.",
"format": "uuid4",
"title": "jobId",
"type": "string"
}
},
"required": [
"jobId"
],
"title": "CreateVectorDatabaseDeploymentResponse",
"type": "object"
}
CreateVectorDatabaseDeploymentResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| jobId | string(uuid4) | true | The ID of the job that will create the new vector database deployment. |
CreateVectorDatabaseRequest
{
"description": "The body of the \"Create vector database\" request.",
"properties": {
"chunkingParameters": {
"anyOf": [
{
"description": "Chunking parameters for creating a vector database.",
"properties": {
"chunkOverlapPercentage": {
"anyOf": [
{
"maximum": 50,
"minimum": 0,
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage to use for text chunking.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk size to use for text chunking (measured in tokens).",
"title": "chunkSize"
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method to use."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model to use. If omitted, DataRobot will choose the default embedding model automatically."
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom embedding model (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"isSeparatorRegex": {
"default": false,
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"separators": {
"anyOf": [
{
"items": {
"maxLength": 20,
"type": "string"
},
"maxItems": 9,
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of separators to use for text chunking.",
"title": "separators"
}
},
"title": "ChunkingParameters",
"type": "object"
},
{
"type": "null"
}
],
"description": "The text chunking parameters to use for building the vector database."
},
"datasetId": {
"description": "The ID of the dataset to use for building the vector database.",
"title": "datasetId",
"type": "string"
},
"externalVectorDatabaseConnection": {
"anyOf": [
{
"discriminator": {
"mapping": {
"elasticsearch": "#/components/schemas/ElasticsearchConnectionRequest",
"pinecone": "#/components/schemas/PineconeConnectionRequest"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnectionRequest",
"type": "object"
},
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnectionRequest",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The external vector database connection to use.",
"title": "externalVectorDatabaseConnection"
},
"metadataCombinationStrategy": {
"description": "Strategy to use when the dataset and the metadata file have duplicate columns.",
"enum": [
"replace",
"merge"
],
"title": "MetadataCombinationStrategy",
"type": "string"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset to add metadata for building the vector database.",
"title": "metadataDatasetId"
},
"name": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the vector database.",
"title": "name"
},
"parentVectorDatabaseId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the parent vector database used as base for the re-building.",
"title": "parentVectorDatabaseId"
},
"updateDeployments": {
"default": false,
"description": "Whether to update the deployments that use the parent vector database.Can only be set to `true` if parent_vector_database_id is provided.",
"title": "updateDeployments",
"type": "boolean"
},
"updateLlmBlueprints": {
"default": false,
"description": "Whether to update the LLM blueprints that use the parent vector database.Can only be set to `true` if parent_vector_database_id is provided.",
"title": "updateLlmBlueprints",
"type": "boolean"
},
"useCaseId": {
"description": "The ID of the use case to link the vector database to.",
"title": "useCaseId",
"type": "string"
}
},
"required": [
"datasetId",
"useCaseId"
],
"title": "CreateVectorDatabaseRequest",
"type": "object"
}
CreateVectorDatabaseRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chunkingParameters | any | false | The text chunking parameters to use for building the vector database. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ChunkingParameters | false | Chunking parameters for creating a vector database. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| datasetId | string | true | The ID of the dataset to use for building the vector database. | |
| externalVectorDatabaseConnection | any | false | The external vector database connection to use. |
anyOf - discriminator: type
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | any | false | none |
oneOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »» anonymous | PineconeConnectionRequest | false | Pinecone vector database connection. |
xor
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »» anonymous | ElasticsearchConnectionRequest | false | Elasticsearch vector database connection. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| metadataCombinationStrategy | MetadataCombinationStrategy | false | The strategy to use when the dataset and the metadata file have duplicate columns. | |
| metadataDatasetId | any | false | The ID of the dataset to add metadata for building the vector database. |
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 | The name of the vector database. |
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 |
|---|---|---|---|---|
| parentVectorDatabaseId | any | false | The ID of the parent vector database used as base for the re-building. |
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 |
|---|---|---|---|---|
| updateDeployments | boolean | false | Whether to update the deployments that use the parent vector database.Can only be set to true if parent_vector_database_id is provided. |
|
| updateLlmBlueprints | boolean | false | Whether to update the LLM blueprints that use the parent vector database.Can only be set to true if parent_vector_database_id is provided. |
|
| useCaseId | string | true | The ID of the use case to link the vector database to. |
CustomEmbeddingModelNames
{
"description": "Model names for custom embedding models.",
"enum": [
"custom-embeddings/default"
],
"title": "CustomEmbeddingModelNames",
"type": "string"
}
CustomEmbeddingModelNames
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| CustomEmbeddingModelNames | string | false | Model names for custom embedding models. |
Enumerated Values¶
| Property | Value |
|---|---|
| CustomEmbeddingModelNames | custom-embeddings/default |
CustomModelEmbeddingValidationResponse
{
"description": "API response object for a single custom model embedding validation.",
"properties": {
"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": "CustomModelEmbeddingValidationResponse",
"type": "object"
}
CustomModelEmbeddingValidationResponse
Properties¶
| 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. |
CustomModelResourcesRequest
{
"description": "The structure that describes resource settings for a custom model created from buzok.",
"properties": {
"maximumMemory": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum memory that can be allocated to the custom model.",
"title": "maximumMemory"
},
"networkEgressPolicy": {
"default": "Public",
"description": "Network egress policy for the custom model. Can be either Public or None.",
"maxLength": 5000,
"title": "networkEgressPolicy",
"type": "string"
},
"replicas": {
"default": 1,
"description": "A fixed number of replicas that will be created for the custom model.",
"title": "replicas",
"type": "integer"
},
"resourceBundleId": {
"anyOf": [
{
"maxLength": 5000,
"type": "string"
},
{
"type": "null"
}
],
"description": "An identifier that represents a bundle of resources: Memory, CPU, GPU, etc. A list of available bundles can be obtained via the resource bundles endpoint.",
"title": "resourceBundleId"
}
},
"title": "CustomModelResourcesRequest",
"type": "object"
}
CustomModelResourcesRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| maximumMemory | any | false | The maximum memory that can be allocated to the custom model. |
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 |
|---|---|---|---|---|
| networkEgressPolicy | string | false | maxLength: 5000 |
Network egress policy for the custom model. Can be either Public or None. |
| replicas | integer | false | A fixed number of replicas that will be created for the custom model. | |
| resourceBundleId | any | false | An identifier that represents a bundle of resources: Memory, CPU, GPU, etc. A list of available bundles can be obtained via the resource bundles endpoint. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | maxLength: 5000 |
none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
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] |
CustomModelVectorDatabaseValidationResponse
{
"description": "API response object for a single custom model vector database validation.",
"properties": {
"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": "CustomModelVectorDatabaseValidationResponse",
"type": "object"
}
CustomModelVectorDatabaseValidationResponse
Properties¶
| 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. |
DatasetLanguages
{
"description": "The names of dataset languages.",
"enum": [
"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"
],
"title": "DatasetLanguages",
"type": "string"
}
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] |
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] |
DistanceMetric
{
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
}
DistanceMetric
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| DistanceMetric | string | false | Distance strategies for vector databases. |
Enumerated Values¶
| Property | Value |
|---|---|
| DistanceMetric | [cosine, dot_product, euclidean, max_inner_product] |
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 |
EditVectorDatabaseRequest
{
"description": "The body of the \"Edit vector database\" request.",
"properties": {
"credentialId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The new ID of the credential to access a connected vector database.",
"title": "credentialId"
},
"name": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The new name of the vector database.",
"title": "name"
}
},
"title": "EditVectorDatabaseRequest",
"type": "object"
}
EditVectorDatabaseRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| credentialId | any | false | The new ID of the credential to access a connected vector database. |
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 | The new name of the vector database. |
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 |
ElasticsearchConnection
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnection",
"type": "object"
}
ElasticsearchConnection
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| cloudId | any | false | The cloud ID of the elastic search connection. |
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 |
|---|---|---|---|---|
| credentialId | string | true | The ID of the credential used to connect to the external vector database. | |
| credentialUserId | any | false | The ID of the user supplying the credential used to connect to the external vector database. |
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 |
|---|---|---|---|---|
| distanceMetric | DistanceMetric | false | The distance strategy to use for building the vector database. | |
| type | string | false | The type of the external vector database. | |
| url | any | false | The URL of the elastic search connection. |
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 |
ElasticsearchConnectionRequest
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnectionRequest",
"type": "object"
}
ElasticsearchConnectionRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| cloudId | any | false | The cloud ID of the elastic search connection. |
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 |
|---|---|---|---|---|
| credentialId | string | true | The ID of the credential used to connect to the external vector database. | |
| credentialUserId | any | false | The ID of the user supplying the credential used to connect to the external vector database. |
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 |
|---|---|---|---|---|
| distanceMetric | DistanceMetric | false | The distance strategy to use for building the vector database. | |
| type | string | false | The type of the external vector database. | |
| url | any | false | The URL of the elastic search connection. |
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 |
EmbeddingModel
{
"description": "API response object for a single embedding model.",
"properties": {
"description": {
"description": "The description of the embedding model.",
"title": "description",
"type": "string"
},
"embeddingModel": {
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
"languages": {
"description": "The list of languages the embedding models supports.",
"items": {
"description": "The names of dataset languages.",
"enum": [
"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"
],
"title": "DatasetLanguages",
"type": "string"
},
"title": "languages",
"type": "array"
},
"maxSequenceLength": {
"description": "The maximum input token sequence length that the embedding model can accept.",
"title": "maxSequenceLength",
"type": "integer"
}
},
"required": [
"embeddingModel",
"description",
"maxSequenceLength",
"languages"
],
"title": "EmbeddingModel",
"type": "object"
}
EmbeddingModel
Properties¶
| Name | Type | Required | Restrictions | 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
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
}
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, intfloat/multilingual-e5-small, sentence-transformers/all-MiniLM-L6-v2, jinaai/jina-embedding-t-en-v1, jinaai/jina-embedding-s-en-v2, cl-nagoya/sup-simcse-ja-base] |
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] |
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 |
ListCustomModelEmbeddingValidationResponse
{
"description": "Paginated list of custom model embedding 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 embedding validation.",
"properties": {
"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": "CustomModelEmbeddingValidationResponse",
"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": "ListCustomModelEmbeddingValidationResponse",
"type": "object"
}
ListCustomModelEmbeddingValidationResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [CustomModelEmbeddingValidationResponse] | 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] |
ListCustomModelVectorDatabaseValidationsResponse
{
"description": "Paginated list of custom model vector database 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 vector database validation.",
"properties": {
"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": "CustomModelVectorDatabaseValidationResponse",
"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": "ListCustomModelVectorDatabaseValidationsResponse",
"type": "object"
}
ListCustomModelVectorDatabaseValidationsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [CustomModelVectorDatabaseValidationResponse] | 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. |
ListVectorDatabaseSortQueryParam
{
"description": "Sort order values for listing vector databases.",
"enum": [
"name",
"-name",
"creationUserId",
"-creationUserId",
"creationDate",
"-creationDate",
"embeddingModel",
"-embeddingModel",
"datasetId",
"-datasetId",
"chunkingMethod",
"-chunkingMethod",
"chunksCount",
"-chunksCount",
"size",
"-size",
"userName",
"-userName",
"datasetName",
"-datasetName",
"playgroundsCount",
"-playgroundsCount",
"source",
"-source"
],
"title": "ListVectorDatabaseSortQueryParam",
"type": "string"
}
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
{
"description": "Paginated list of vector databases.",
"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 vector database.",
"properties": {
"addedDatasetIds": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset IDs that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetIds"
},
"addedDatasetNames": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset names that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetNames"
},
"addedMetadataDatasetPairs": {
"anyOf": [
{
"items": {
"description": "Pair of metadata dataset and dataset added to the vector database.",
"properties": {
"datasetId": {
"description": "The ID of the dataset added to the vector database.",
"title": "datasetId",
"type": "string"
},
"datasetName": {
"description": "The name of the dataset added to the vector database.",
"title": "datasetName",
"type": "string"
},
"metadataDatasetId": {
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId",
"type": "string"
},
"metadataDatasetName": {
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName",
"type": "string"
}
},
"required": [
"metadataDatasetId",
"datasetId",
"metadataDatasetName",
"datasetName"
],
"title": "MetadataDatasetPairApiFormatted",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "Pairs of metadata dataset and dataset added to the vector database.",
"title": "addedMetadataDatasetPairs"
},
"chunkOverlapPercentage": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage that the vector database uses.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the text chunk (measured in tokens) that the vector database uses.",
"title": "chunkSize"
},
"chunkingLengthFunction": {
"anyOf": [
{
"description": "Supported length functions for text splitters.",
"enum": [
"tokenizer_length_function",
"approximate_token_count"
],
"title": "ChunkingLengthFunctionNames",
"type": "string"
},
{
"type": "null"
}
],
"default": "approximate_token_count",
"description": "The length function to use for the text splitter."
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method the vector database uses."
},
"chunksCount": {
"description": "The number of text chunks in the vector database.",
"title": "chunksCount",
"type": "integer"
},
"creationDate": {
"description": "The creation date of the vector database (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationDuration": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The duration of the vector database creation.",
"title": "creationDuration"
},
"creationUserId": {
"description": "The ID of the user that created this vector database.",
"title": "creationUserId",
"type": "string"
},
"customChunking": {
"description": "Whether the vector database uses custom chunking.",
"title": "customChunking",
"type": "boolean"
},
"datasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset the vector database was built from.",
"title": "datasetId"
},
"datasetName": {
"description": "The name of the dataset this vector database was built from.",
"title": "datasetName",
"type": "string"
},
"deploymentStatus": {
"anyOf": [
{
"description": "Sort order values for listing vector databases.",
"enum": [
"Created",
"Assembling",
"Registered",
"Deployed"
],
"title": "VectorDatabaseDeploymentStatuses",
"type": "string"
},
{
"type": "null"
}
],
"description": "How far along in the deployment process this vector database is."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model the vector database uses.",
"title": "embeddingModel"
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model embedding (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the vector database creation error (in case of a creation error).",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database creation error (in case of a creation error).",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"externalVectorDatabaseConnection": {
"anyOf": [
{
"discriminator": {
"mapping": {
"elasticsearch": "#/components/schemas/ElasticsearchConnection",
"pinecone": "#/components/schemas/PineconeConnection"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnection",
"type": "object"
},
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnection",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The external vector database connection to use.",
"title": "externalVectorDatabaseConnection"
},
"familyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "An ID associated with a family of vector databases, that is, a parent and all descendant vector databases. All vector databases that are descendants of the same root parent share a family ID.The family ID is equal to the vector database ID of the root parent.Like this each vector database knows it's direct parent and the root parent.",
"title": "familyId"
},
"id": {
"description": "The ID of the vector database.",
"title": "id",
"type": "string"
},
"isSeparatorRegex": {
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"metadataColumns": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of metadata columns in the vector database.",
"title": "metadataColumns"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId"
},
"metadataDatasetName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName"
},
"name": {
"description": "The name of the vector database.",
"title": "name",
"type": "string"
},
"organizationId": {
"description": "The ID of the DataRobot organization this vector database belongs to.",
"title": "organizationId",
"type": "string"
},
"parentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the direct parent vector database.It is generated when a vector database is created from another vector database.For the root (parent), ID is 'None'.",
"title": "parentId"
},
"percentage": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Vector database progress percentage.",
"title": "percentage"
},
"playgroundsCount": {
"description": "The number of playgrounds that use this vector database.",
"title": "playgroundsCount",
"type": "integer"
},
"separators": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"description": "The text chunking separators that the vector database uses.",
"title": "separators"
},
"size": {
"description": "The size of the vector database (in bytes).",
"title": "size",
"type": "integer"
},
"skippedChunksCount": {
"description": "The number of text chunks skipped during vector database creation.",
"title": "skippedChunksCount",
"type": "integer"
},
"source": {
"description": "The source of the vector database.",
"enum": [
"DataRobot",
"External",
"Pinecone",
"Elasticsearch"
],
"title": "VectorDatabaseSource",
"type": "string"
},
"tenantId": {
"description": "The ID of the DataRobot tenant this vector database belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case the vector database is linked to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this vector database.",
"title": "userName",
"type": "string"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model vector database (in case of using a custom model vector database).",
"title": "validationId"
},
"version": {
"description": "The version of the vector database linked to a certain family ID.",
"title": "version",
"type": "integer"
}
},
"required": [
"id",
"name",
"size",
"useCaseId",
"datasetId",
"embeddingModel",
"embeddingValidationId",
"embeddingRegisteredModelId",
"chunkSize",
"chunkingMethod",
"chunkOverlapPercentage",
"chunksCount",
"skippedChunksCount",
"customChunking",
"separators",
"isSeparatorRegex",
"creationDate",
"creationUserId",
"organizationId",
"tenantId",
"lastUpdateDate",
"executionStatus",
"errorMessage",
"errorResolution",
"source",
"validationId",
"parentId",
"familyId",
"addedDatasetIds",
"version",
"playgroundsCount",
"datasetName",
"userName",
"addedDatasetNames"
],
"title": "VectorDatabaseResponse",
"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": "ListVectorDatabasesResponse",
"type": "object"
}
ListVectorDatabasesResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| count | integer | true | The number of records on this page. | |
| data | [VectorDatabaseResponse] | 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. |
MetadataCombinationStrategy
{
"description": "Strategy to use when the dataset and the metadata file have duplicate columns.",
"enum": [
"replace",
"merge"
],
"title": "MetadataCombinationStrategy",
"type": "string"
}
MetadataCombinationStrategy
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| MetadataCombinationStrategy | string | false | Strategy to use when the dataset and the metadata file have duplicate columns. |
Enumerated Values¶
| Property | Value |
|---|---|
| MetadataCombinationStrategy | [replace, merge] |
MetadataDatasetPairApiFormatted
{
"description": "Pair of metadata dataset and dataset added to the vector database.",
"properties": {
"datasetId": {
"description": "The ID of the dataset added to the vector database.",
"title": "datasetId",
"type": "string"
},
"datasetName": {
"description": "The name of the dataset added to the vector database.",
"title": "datasetName",
"type": "string"
},
"metadataDatasetId": {
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId",
"type": "string"
},
"metadataDatasetName": {
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName",
"type": "string"
}
},
"required": [
"metadataDatasetId",
"datasetId",
"metadataDatasetName",
"datasetName"
],
"title": "MetadataDatasetPairApiFormatted",
"type": "object"
}
MetadataDatasetPairApiFormatted
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| datasetId | string | true | The ID of the dataset added to the vector database. | |
| datasetName | string | true | The name of the dataset added to the vector database. | |
| metadataDatasetId | string | true | The ID of the dataset used to add metadata to the vector database. | |
| metadataDatasetName | string | true | The name of the dataset used to add metadata to the vector database. |
PineconeCloud
{
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
}
PineconeCloud
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| PineconeCloud | string | false | Supported cloud providers for Pinecone. |
Enumerated Values¶
| Property | Value |
|---|---|
| PineconeCloud | [aws, gcp, azure] |
PineconeConnection
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnection",
"type": "object"
}
PineconeConnection
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| cloud | PineconeCloud | true | The cloud provider to create the index. | |
| credentialId | string | true | The ID of the credential used to connect to the external vector database. | |
| credentialUserId | any | false | The ID of the user supplying the credential used to connect to the external vector database. |
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 |
|---|---|---|---|---|
| distanceMetric | DistanceMetric | false | The distance strategy to use for building the vector database. | |
| region | string | true | maxLength: 5000 minLength: 1 minLength: 1 |
The region to create the index. |
| type | string | false | The type of the external vector database. |
PineconeConnectionRequest
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnectionRequest",
"type": "object"
}
PineconeConnectionRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| cloud | PineconeCloud | true | The cloud provider to create the index. | |
| credentialId | string | true | The ID of the credential used to connect to the external vector database. | |
| credentialUserId | any | false | The ID of the user supplying the credential used to connect to the external vector database. |
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 |
|---|---|---|---|---|
| distanceMetric | DistanceMetric | false | The distance strategy to use for building the vector database. | |
| region | string | true | maxLength: 5000 minLength: 1 minLength: 1 |
The region to create the index. |
| type | string | false | The type of the external vector database. |
SupportedCustomModelEmbeddings
{
"description": "API response object for a single custom embedding model.",
"properties": {
"id": {
"description": "The validation ID of the custom embedding model.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the custom embedding model.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "SupportedCustomModelEmbeddings",
"type": "object"
}
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. |
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] |
SupportedEmbeddingsResponse
{
"description": "API response object for \"List supported embeddings\".",
"properties": {
"customModelEmbeddingValidations": {
"description": "The list of validated custom embedding models.",
"items": {
"description": "API response object for a single custom embedding model.",
"properties": {
"id": {
"description": "The validation ID of the custom embedding model.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the custom embedding model.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name"
],
"title": "SupportedCustomModelEmbeddings",
"type": "object"
},
"title": "customModelEmbeddingValidations",
"type": "array"
},
"defaultEmbeddingModel": {
"description": "The name of the default embedding model.",
"title": "defaultEmbeddingModel",
"type": "string"
},
"embeddingModels": {
"description": "The list of embeddings models.",
"items": {
"description": "API response object for a single embedding model.",
"properties": {
"description": {
"description": "The description of the embedding model.",
"title": "description",
"type": "string"
},
"embeddingModel": {
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
"languages": {
"description": "The list of languages the embedding models supports.",
"items": {
"description": "The names of dataset languages.",
"enum": [
"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"
],
"title": "DatasetLanguages",
"type": "string"
},
"title": "languages",
"type": "array"
},
"maxSequenceLength": {
"description": "The maximum input token sequence length that the embedding model can accept.",
"title": "maxSequenceLength",
"type": "integer"
}
},
"required": [
"embeddingModel",
"description",
"maxSequenceLength",
"languages"
],
"title": "EmbeddingModel",
"type": "object"
},
"title": "embeddingModels",
"type": "array"
},
"nimEmbeddingModels": {
"description": "The list of NIM registered models.",
"items": {
"description": "API response object for a single registered NIM embedding model.",
"properties": {
"description": {
"description": "The description of the registered NIM model.",
"title": "description",
"type": "string"
},
"id": {
"description": "The validation ID of the registered NIM model.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the registered NIM model.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name",
"description"
],
"title": "SupportedNIMModelEmbeddings",
"type": "object"
},
"title": "nimEmbeddingModels",
"type": "array"
}
},
"required": [
"embeddingModels",
"defaultEmbeddingModel"
],
"title": "SupportedEmbeddingsResponse",
"type": "object"
}
SupportedEmbeddingsResponse
Properties¶
| Name | Type | Required | Restrictions | 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. | |
| nimEmbeddingModels | [SupportedNIMModelEmbeddings] | false | The list of NIM registered models. |
SupportedLanguagesResponse
{
"description": "API response object for \"List supported languages for Synthetic Dataset generation\".",
"properties": {
"recommendedLanguage": {
"description": "The recommended language.",
"title": "recommendedLanguage",
"type": "string"
},
"supportedLanguages": {
"description": "The list of supported languages.",
"items": {
"type": "string"
},
"title": "supportedLanguages",
"type": "array"
}
},
"required": [
"recommendedLanguage",
"supportedLanguages"
],
"title": "SupportedLanguagesResponse",
"type": "object"
}
SupportedLanguagesResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| recommendedLanguage | string | true | The recommended language. | |
| supportedLanguages | [string] | true | The list of supported languages. |
SupportedNIMModelEmbeddings
{
"description": "API response object for a single registered NIM embedding model.",
"properties": {
"description": {
"description": "The description of the registered NIM model.",
"title": "description",
"type": "string"
},
"id": {
"description": "The validation ID of the registered NIM model.",
"title": "id",
"type": "string"
},
"name": {
"description": "The name of the registered NIM model.",
"title": "name",
"type": "string"
}
},
"required": [
"id",
"name",
"description"
],
"title": "SupportedNIMModelEmbeddings",
"type": "object"
}
SupportedNIMModelEmbeddings
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| description | string | true | The description of the registered NIM model. | |
| id | string | true | The validation ID of the registered NIM model. | |
| name | string | true | The name of the registered NIM model. |
SupportedRetrievalSettingsResponse
{
"description": "API response object for \"Retrieve supported retrieval settings\".",
"properties": {
"settings": {
"description": "The list of retrieval settings.",
"items": {
"description": "API response object for a single vector database setting parameter.",
"properties": {
"default": {
"description": "The default value of the parameter.",
"title": "default"
},
"description": {
"description": "The description of the parameter.",
"title": "description",
"type": "string"
},
"enum": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of possible values for the parameter.",
"title": "enum"
},
"groupId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The identifier of the group the parameter belongs to.",
"title": "groupId"
},
"maximum": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the parameter.",
"title": "maximum"
},
"minimum": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the parameter.",
"title": "minimum"
},
"name": {
"description": "The name of the parameter.",
"title": "name",
"type": "string"
},
"settings": {
"anyOf": [
{
"items": "[Circular]",
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of available settings for the parameter.",
"title": "settings"
},
"title": {
"description": "The title of the parameter.",
"title": "title",
"type": "string"
},
"type": {
"anyOf": [
{
"description": "The types of vector database setting parameters.",
"enum": [
"string",
"integer",
"boolean",
"null",
"number",
"array"
],
"title": "VectorDatabaseSettingTypes",
"type": "string"
},
{
"items": {
"description": "The types of vector database setting parameters.",
"enum": [
"string",
"integer",
"boolean",
"null",
"number",
"array"
],
"title": "VectorDatabaseSettingTypes",
"type": "string"
},
"type": "array"
}
],
"description": "The type of the parameter.",
"title": "type"
}
},
"required": [
"name",
"type",
"description",
"title"
],
"title": "VectorDatabaseSettingParameter",
"type": "object"
},
"title": "settings",
"type": "array"
}
},
"required": [
"settings"
],
"title": "SupportedRetrievalSettingsResponse",
"type": "object"
}
SupportedRetrievalSettingsResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| settings | [VectorDatabaseSettingParameter] | true | The list of retrieval settings. |
SupportedTextChunkingResponse
{
"description": "API response for \"List text chunking methods\".",
"properties": {
"textChunkingConfigs": {
"description": "The list of text chunking configurations.",
"items": {
"description": "API response object for a single text chunking configuration.",
"properties": {
"defaultMethod": {
"description": "The name of the default text chunking method.",
"title": "defaultMethod",
"type": "string"
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"description": "Model names for custom embedding models.",
"enum": [
"custom-embeddings/default"
],
"title": "CustomEmbeddingModelNames",
"type": "string"
}
],
"description": "The name of the embedding model.",
"title": "embeddingModel"
},
"methods": {
"description": "The list of text chunking methods.",
"items": {
"description": "API response object for a single text chunking method.",
"properties": {
"chunkingMethod": {
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
"chunkingParameters": {
"description": "The list of text chunking parameters.",
"items": {
"description": "API response object for a single text chunking parameter.",
"properties": {
"default": {
"anyOf": [
{
"type": "integer"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "boolean"
}
],
"description": "The default value of the parameter.",
"title": "default"
},
"description": {
"description": "The description of the parameter.",
"title": "description",
"type": "string"
},
"max": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the parameter (inclusive).",
"title": "max"
},
"min": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the parameter (inclusive).",
"title": "min"
},
"name": {
"description": "The name of the parameter.",
"title": "name",
"type": "string"
},
"type": {
"description": "Supported parameter data types for text chunking parameters.",
"enum": [
"int",
"list[str]",
"bool"
],
"title": "ChunkingParameterTypes",
"type": "string"
}
},
"required": [
"name",
"type",
"min",
"max",
"description",
"default"
],
"title": "TextChunkingParameterFields",
"type": "object"
},
"title": "chunkingParameters",
"type": "array"
},
"description": {
"description": "The description of the text chunking method.",
"title": "description",
"type": "string"
},
"title": {
"description": "Supported user-facing friendly ames of text chunking methods.",
"enum": [
"Recursive",
"Semantic"
],
"title": "ChunkingMethodNamesTitle",
"type": "string"
}
},
"required": [
"chunkingMethod",
"title",
"chunkingParameters",
"description"
],
"title": "TextChunkingMethod",
"type": "object"
},
"title": "methods",
"type": "array"
}
},
"required": [
"embeddingModel",
"methods",
"defaultMethod"
],
"title": "TextChunkingConfig",
"type": "object"
},
"title": "textChunkingConfigs",
"type": "array"
}
},
"required": [
"textChunkingConfigs"
],
"title": "SupportedTextChunkingResponse",
"type": "object"
}
SupportedTextChunkingResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| textChunkingConfigs | [TextChunkingConfig] | true | The list of text chunking configurations. |
TextChunkingConfig
{
"description": "API response object for a single text chunking configuration.",
"properties": {
"defaultMethod": {
"description": "The name of the default text chunking method.",
"title": "defaultMethod",
"type": "string"
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"description": "Model names for custom embedding models.",
"enum": [
"custom-embeddings/default"
],
"title": "CustomEmbeddingModelNames",
"type": "string"
}
],
"description": "The name of the embedding model.",
"title": "embeddingModel"
},
"methods": {
"description": "The list of text chunking methods.",
"items": {
"description": "API response object for a single text chunking method.",
"properties": {
"chunkingMethod": {
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
"chunkingParameters": {
"description": "The list of text chunking parameters.",
"items": {
"description": "API response object for a single text chunking parameter.",
"properties": {
"default": {
"anyOf": [
{
"type": "integer"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "boolean"
}
],
"description": "The default value of the parameter.",
"title": "default"
},
"description": {
"description": "The description of the parameter.",
"title": "description",
"type": "string"
},
"max": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the parameter (inclusive).",
"title": "max"
},
"min": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the parameter (inclusive).",
"title": "min"
},
"name": {
"description": "The name of the parameter.",
"title": "name",
"type": "string"
},
"type": {
"description": "Supported parameter data types for text chunking parameters.",
"enum": [
"int",
"list[str]",
"bool"
],
"title": "ChunkingParameterTypes",
"type": "string"
}
},
"required": [
"name",
"type",
"min",
"max",
"description",
"default"
],
"title": "TextChunkingParameterFields",
"type": "object"
},
"title": "chunkingParameters",
"type": "array"
},
"description": {
"description": "The description of the text chunking method.",
"title": "description",
"type": "string"
},
"title": {
"description": "Supported user-facing friendly ames of text chunking methods.",
"enum": [
"Recursive",
"Semantic"
],
"title": "ChunkingMethodNamesTitle",
"type": "string"
}
},
"required": [
"chunkingMethod",
"title",
"chunkingParameters",
"description"
],
"title": "TextChunkingMethod",
"type": "object"
},
"title": "methods",
"type": "array"
}
},
"required": [
"embeddingModel",
"methods",
"defaultMethod"
],
"title": "TextChunkingConfig",
"type": "object"
}
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
{
"description": "API response object for a single text chunking method.",
"properties": {
"chunkingMethod": {
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
"chunkingParameters": {
"description": "The list of text chunking parameters.",
"items": {
"description": "API response object for a single text chunking parameter.",
"properties": {
"default": {
"anyOf": [
{
"type": "integer"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "boolean"
}
],
"description": "The default value of the parameter.",
"title": "default"
},
"description": {
"description": "The description of the parameter.",
"title": "description",
"type": "string"
},
"max": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the parameter (inclusive).",
"title": "max"
},
"min": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the parameter (inclusive).",
"title": "min"
},
"name": {
"description": "The name of the parameter.",
"title": "name",
"type": "string"
},
"type": {
"description": "Supported parameter data types for text chunking parameters.",
"enum": [
"int",
"list[str]",
"bool"
],
"title": "ChunkingParameterTypes",
"type": "string"
}
},
"required": [
"name",
"type",
"min",
"max",
"description",
"default"
],
"title": "TextChunkingParameterFields",
"type": "object"
},
"title": "chunkingParameters",
"type": "array"
},
"description": {
"description": "The description of the text chunking method.",
"title": "description",
"type": "string"
},
"title": {
"description": "Supported user-facing friendly ames of text chunking methods.",
"enum": [
"Recursive",
"Semantic"
],
"title": "ChunkingMethodNamesTitle",
"type": "string"
}
},
"required": [
"chunkingMethod",
"title",
"chunkingParameters",
"description"
],
"title": "TextChunkingMethod",
"type": "object"
}
TextChunkingMethod
Properties¶
| Name | Type | Required | Restrictions | 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. | |
| title | ChunkingMethodNamesTitle | true | User-friendly label for the text chunking method. |
TextChunkingParameterFields
{
"description": "API response object for a single text chunking parameter.",
"properties": {
"default": {
"anyOf": [
{
"type": "integer"
},
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "boolean"
}
],
"description": "The default value of the parameter.",
"title": "default"
},
"description": {
"description": "The description of the parameter.",
"title": "description",
"type": "string"
},
"max": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the parameter (inclusive).",
"title": "max"
},
"min": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the parameter (inclusive).",
"title": "min"
},
"name": {
"description": "The name of the parameter.",
"title": "name",
"type": "string"
},
"type": {
"description": "Supported parameter data types for text chunking parameters.",
"enum": [
"int",
"list[str]",
"bool"
],
"title": "ChunkingParameterTypes",
"type": "string"
}
},
"required": [
"name",
"type",
"min",
"max",
"description",
"default"
],
"title": "TextChunkingParameterFields",
"type": "object"
}
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 | Restrictions | Description |
|---|---|---|---|---|
| description | string | true | The description of the parameter. | |
| max | any | true | The maximum value of the parameter (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 |
|---|---|---|---|---|
| min | any | true | The minimum value of the parameter (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 |
|---|---|---|---|---|
| name | string | true | The name of the parameter. | |
| type | ChunkingParameterTypes | true | The data type of the parameter. |
UpdateConnectedVectorDatabaseRequest
{
"description": "The body of the \"Update connected vector database\" request.",
"properties": {
"datasetId": {
"description": "The ID of the dataset to use for building the vector database.",
"title": "datasetId",
"type": "string"
},
"metadataCombinationStrategy": {
"description": "Strategy to use when the dataset and the metadata file have duplicate columns.",
"enum": [
"replace",
"merge"
],
"title": "MetadataCombinationStrategy",
"type": "string"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset to add metadata for building the vector database.",
"title": "metadataDatasetId"
}
},
"required": [
"datasetId"
],
"title": "UpdateConnectedVectorDatabaseRequest",
"type": "object"
}
UpdateConnectedVectorDatabaseRequest
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| datasetId | string | true | The ID of the dataset to use for building the vector database. | |
| metadataCombinationStrategy | MetadataCombinationStrategy | false | The strategy to use when the dataset and the metadata file have duplicate columns. | |
| metadataDatasetId | any | false | The ID of the dataset to add metadata for building the vector database. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | string | false | none |
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 |
VectorDatabaseDeploymentStatuses
{
"description": "Sort order values for listing vector databases.",
"enum": [
"Created",
"Assembling",
"Registered",
"Deployed"
],
"title": "VectorDatabaseDeploymentStatuses",
"type": "string"
}
VectorDatabaseDeploymentStatuses
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| VectorDatabaseDeploymentStatuses | string | false | Sort order values for listing vector databases. |
Enumerated Values¶
| Property | Value |
|---|---|
| VectorDatabaseDeploymentStatuses | [Created, Assembling, Registered, Deployed] |
VectorDatabaseExportResponse
{
"description": "API response object for exporting a vector database.",
"properties": {
"exportDatasetId": {
"description": "The Data Registry dataset ID.",
"title": "exportDatasetId",
"type": "string"
},
"jobId": {
"description": "The ID of the export job.",
"format": "uuid4",
"title": "jobId",
"type": "string"
},
"vectorDatabaseId": {
"description": "The ID of the vector database.",
"title": "vectorDatabaseId",
"type": "string"
}
},
"required": [
"jobId",
"exportDatasetId",
"vectorDatabaseId"
],
"title": "VectorDatabaseExportResponse",
"type": "object"
}
VectorDatabaseExportResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| exportDatasetId | string | true | The Data Registry dataset ID. | |
| jobId | string(uuid4) | true | The ID of the export job. | |
| vectorDatabaseId | string | true | The ID of the vector database. |
VectorDatabaseResponse
{
"description": "API response object for a single vector database.",
"properties": {
"addedDatasetIds": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset IDs that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetIds"
},
"addedDatasetNames": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of dataset names that were added to the vector database in addition to the initial creation dataset.",
"title": "addedDatasetNames"
},
"addedMetadataDatasetPairs": {
"anyOf": [
{
"items": {
"description": "Pair of metadata dataset and dataset added to the vector database.",
"properties": {
"datasetId": {
"description": "The ID of the dataset added to the vector database.",
"title": "datasetId",
"type": "string"
},
"datasetName": {
"description": "The name of the dataset added to the vector database.",
"title": "datasetName",
"type": "string"
},
"metadataDatasetId": {
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId",
"type": "string"
},
"metadataDatasetName": {
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName",
"type": "string"
}
},
"required": [
"metadataDatasetId",
"datasetId",
"metadataDatasetName",
"datasetName"
],
"title": "MetadataDatasetPairApiFormatted",
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "Pairs of metadata dataset and dataset added to the vector database.",
"title": "addedMetadataDatasetPairs"
},
"chunkOverlapPercentage": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The chunk overlap percentage that the vector database uses.",
"title": "chunkOverlapPercentage"
},
"chunkSize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The size of the text chunk (measured in tokens) that the vector database uses.",
"title": "chunkSize"
},
"chunkingLengthFunction": {
"anyOf": [
{
"description": "Supported length functions for text splitters.",
"enum": [
"tokenizer_length_function",
"approximate_token_count"
],
"title": "ChunkingLengthFunctionNames",
"type": "string"
},
{
"type": "null"
}
],
"default": "approximate_token_count",
"description": "The length function to use for the text splitter."
},
"chunkingMethod": {
"anyOf": [
{
"description": "Supported names of text chunking methods.",
"enum": [
"recursive",
"semantic"
],
"title": "ChunkingMethodNames",
"type": "string"
},
{
"type": "null"
}
],
"description": "The text chunking method the vector database uses."
},
"chunksCount": {
"description": "The number of text chunks in the vector database.",
"title": "chunksCount",
"type": "integer"
},
"creationDate": {
"description": "The creation date of the vector database (ISO 8601 formatted).",
"format": "date-time",
"title": "creationDate",
"type": "string"
},
"creationDuration": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "The duration of the vector database creation.",
"title": "creationDuration"
},
"creationUserId": {
"description": "The ID of the user that created this vector database.",
"title": "creationUserId",
"type": "string"
},
"customChunking": {
"description": "Whether the vector database uses custom chunking.",
"title": "customChunking",
"type": "boolean"
},
"datasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset the vector database was built from.",
"title": "datasetId"
},
"datasetName": {
"description": "The name of the dataset this vector database was built from.",
"title": "datasetName",
"type": "string"
},
"deploymentStatus": {
"anyOf": [
{
"description": "Sort order values for listing vector databases.",
"enum": [
"Created",
"Assembling",
"Registered",
"Deployed"
],
"title": "VectorDatabaseDeploymentStatuses",
"type": "string"
},
{
"type": "null"
}
],
"description": "How far along in the deployment process this vector database is."
},
"embeddingModel": {
"anyOf": [
{
"description": "Embedding model names (matching the format of HuggingFace repositories).",
"enum": [
"intfloat/e5-large-v2",
"intfloat/e5-base-v2",
"intfloat/multilingual-e5-base",
"intfloat/multilingual-e5-small",
"sentence-transformers/all-MiniLM-L6-v2",
"jinaai/jina-embedding-t-en-v1",
"jinaai/jina-embedding-s-en-v2",
"cl-nagoya/sup-simcse-ja-base"
],
"title": "EmbeddingModelNames",
"type": "string"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the embedding model the vector database uses.",
"title": "embeddingModel"
},
"embeddingRegisteredModelId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of registered model (in case of using NIM registered model for embeddings).",
"title": "embeddingRegisteredModelId"
},
"embeddingValidationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model embedding (in case of using a custom model for embeddings).",
"title": "embeddingValidationId"
},
"errorMessage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The error message associated with the vector database creation error (in case of a creation error).",
"title": "errorMessage"
},
"errorResolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The suggested error resolution for the vector database creation error (in case of a creation error).",
"title": "errorResolution"
},
"executionStatus": {
"description": "Job and entity execution status.",
"enum": [
"NEW",
"RUNNING",
"COMPLETED",
"REQUIRES_USER_INPUT",
"SKIPPED",
"ERROR"
],
"title": "ExecutionStatus",
"type": "string"
},
"externalVectorDatabaseConnection": {
"anyOf": [
{
"discriminator": {
"mapping": {
"elasticsearch": "#/components/schemas/ElasticsearchConnection",
"pinecone": "#/components/schemas/PineconeConnection"
},
"propertyName": "type"
},
"oneOf": [
{
"description": "Pinecone vector database connection.",
"properties": {
"cloud": {
"description": "Supported cloud providers for Pinecone.",
"enum": [
"aws",
"gcp",
"azure"
],
"title": "PineconeCloud",
"type": "string"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"region": {
"description": "The region to create the index.",
"maxLength": 5000,
"minLength": 1,
"title": "region",
"type": "string"
},
"type": {
"const": "pinecone",
"default": "pinecone",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
}
},
"required": [
"credentialId",
"cloud",
"region"
],
"title": "PineconeConnection",
"type": "object"
},
{
"description": "Elasticsearch vector database connection.",
"properties": {
"cloudId": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The cloud ID of the elastic search connection.",
"title": "cloudId"
},
"credentialId": {
"description": "The ID of the credential used to connect to the external vector database.",
"title": "credentialId",
"type": "string"
},
"credentialUserId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the user supplying the credential used to connect to the external vector database.",
"title": "credentialUserId"
},
"distanceMetric": {
"description": "Distance strategies for vector databases.",
"enum": [
"cosine",
"dot_product",
"euclidean",
"max_inner_product"
],
"title": "DistanceMetric",
"type": "string"
},
"type": {
"const": "elasticsearch",
"default": "elasticsearch",
"description": "The type of the external vector database.",
"title": "type",
"type": "string"
},
"url": {
"anyOf": [
{
"maxLength": 5000,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"description": "The URL of the elastic search connection.",
"title": "url"
}
},
"required": [
"credentialId"
],
"title": "ElasticsearchConnection",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "The external vector database connection to use.",
"title": "externalVectorDatabaseConnection"
},
"familyId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "An ID associated with a family of vector databases, that is, a parent and all descendant vector databases. All vector databases that are descendants of the same root parent share a family ID.The family ID is equal to the vector database ID of the root parent.Like this each vector database knows it's direct parent and the root parent.",
"title": "familyId"
},
"id": {
"description": "The ID of the vector database.",
"title": "id",
"type": "string"
},
"isSeparatorRegex": {
"description": "Whether the text chunking separator uses a regular expression.",
"title": "isSeparatorRegex",
"type": "boolean"
},
"lastUpdateDate": {
"description": "The date of the most recent update of this playground (ISO 8601 formatted).",
"format": "date-time",
"title": "lastUpdateDate",
"type": "string"
},
"metadataColumns": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of metadata columns in the vector database.",
"title": "metadataColumns"
},
"metadataDatasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetId"
},
"metadataDatasetName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name of the dataset used to add metadata to the vector database.",
"title": "metadataDatasetName"
},
"name": {
"description": "The name of the vector database.",
"title": "name",
"type": "string"
},
"organizationId": {
"description": "The ID of the DataRobot organization this vector database belongs to.",
"title": "organizationId",
"type": "string"
},
"parentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The ID of the direct parent vector database.It is generated when a vector database is created from another vector database.For the root (parent), ID is 'None'.",
"title": "parentId"
},
"percentage": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Vector database progress percentage.",
"title": "percentage"
},
"playgroundsCount": {
"description": "The number of playgrounds that use this vector database.",
"title": "playgroundsCount",
"type": "integer"
},
"separators": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"description": "The text chunking separators that the vector database uses.",
"title": "separators"
},
"size": {
"description": "The size of the vector database (in bytes).",
"title": "size",
"type": "integer"
},
"skippedChunksCount": {
"description": "The number of text chunks skipped during vector database creation.",
"title": "skippedChunksCount",
"type": "integer"
},
"source": {
"description": "The source of the vector database.",
"enum": [
"DataRobot",
"External",
"Pinecone",
"Elasticsearch"
],
"title": "VectorDatabaseSource",
"type": "string"
},
"tenantId": {
"description": "The ID of the DataRobot tenant this vector database belongs to.",
"format": "uuid4",
"title": "tenantId",
"type": "string"
},
"useCaseId": {
"description": "The ID of the use case the vector database is linked to.",
"title": "useCaseId",
"type": "string"
},
"userName": {
"description": "The name of the user that created this vector database.",
"title": "userName",
"type": "string"
},
"validationId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The validation ID of the custom model vector database (in case of using a custom model vector database).",
"title": "validationId"
},
"version": {
"description": "The version of the vector database linked to a certain family ID.",
"title": "version",
"type": "integer"
}
},
"required": [
"id",
"name",
"size",
"useCaseId",
"datasetId",
"embeddingModel",
"embeddingValidationId",
"embeddingRegisteredModelId",
"chunkSize",
"chunkingMethod",
"chunkOverlapPercentage",
"chunksCount",
"skippedChunksCount",
"customChunking",
"separators",
"isSeparatorRegex",
"creationDate",
"creationUserId",
"organizationId",
"tenantId",
"lastUpdateDate",
"executionStatus",
"errorMessage",
"errorResolution",
"source",
"validationId",
"parentId",
"familyId",
"addedDatasetIds",
"version",
"playgroundsCount",
"datasetName",
"userName",
"addedDatasetNames"
],
"title": "VectorDatabaseResponse",
"type": "object"
}
VectorDatabaseResponse
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| addedDatasetIds | any | true | The list of dataset IDs that were added to the vector database in addition to the initial creation dataset. |
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 |
|---|---|---|---|---|
| addedDatasetNames | any | true | The list of dataset names that were added to the vector database in addition to the initial creation dataset. |
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 |
|---|---|---|---|---|
| addedMetadataDatasetPairs | any | false | Pairs of metadata dataset and dataset added to the vector database. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [MetadataDatasetPairApiFormatted] | false | [Pair of metadata dataset and dataset added to the vector database.] |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chunkOverlapPercentage | any | true | The chunk overlap percentage that the vector database uses. |
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 |
|---|---|---|---|---|
| chunkSize | any | true | The size of the text chunk (measured in tokens) that the vector database uses. |
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 |
|---|---|---|---|---|
| chunkingLengthFunction | any | false | The length function to use for the text splitter. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ChunkingLengthFunctionNames | false | Supported length functions for text splitters. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| chunkingMethod | any | true | The text chunking method the vector database uses. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | ChunkingMethodNames | false | Supported names of text chunking methods. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| 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). | |
| creationDuration | any | false | The duration of the vector database creation. |
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 |
|---|---|---|---|---|
| creationUserId | string | true | The ID of the user that created this vector database. | |
| customChunking | boolean | true | Whether the vector database uses custom chunking. | |
| datasetId | any | true | The ID of the dataset the vector database was built from. |
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 |
|---|---|---|---|---|
| datasetName | string | true | The name of the dataset this vector database was built from. | |
| deploymentStatus | any | false | How far along in the deployment process this vector database is. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | VectorDatabaseDeploymentStatuses | false | Sort order values for listing vector databases. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| embeddingModel | any | true | The name of the embedding model the vector database uses. |
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 | string | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| embeddingRegisteredModelId | any | true | The ID of registered model (in case of using NIM registered model for embeddings). |
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 |
|---|---|---|---|---|
| embeddingValidationId | any | true | The validation ID of the custom model embedding (in case of using a custom model for embeddings). |
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 | true | The error message associated with the vector database creation error (in case of a creation error). |
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 | true | The suggested error resolution for the vector database creation error (in case of a creation error). |
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 creation status of the vector database. | |
| externalVectorDatabaseConnection | any | false | The external vector database connection to use. |
anyOf - discriminator: type
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | any | false | none |
oneOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »» anonymous | PineconeConnection | false | Pinecone vector database connection. |
xor
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| »» anonymous | ElasticsearchConnection | false | Elasticsearch vector database connection. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| familyId | any | true | An ID associated with a family of vector databases, that is, a parent and all descendant vector databases. All vector databases that are descendants of the same root parent share a family ID.The family ID is equal to the vector database ID of the root parent.Like this each vector database knows it's direct parent and the root parent. |
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 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). | |
| metadataColumns | any | false | The list of metadata columns in the vector database. |
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 |
|---|---|---|---|---|
| metadataDatasetId | any | false | The ID of the dataset used to add metadata to the vector database. |
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 |
|---|---|---|---|---|
| metadataDatasetName | any | false | The name of the dataset used to add metadata to the vector database. |
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 | true | The name of the vector database. | |
| organizationId | string | true | The ID of the DataRobot organization this vector database belongs to. | |
| parentId | any | true | The ID of the direct parent vector database.It is generated when a vector database is created from another vector database.For the root (parent), ID is 'None'. |
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 |
|---|---|---|---|---|
| percentage | any | false | Vector database progress percentage. |
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 |
|---|---|---|---|---|
| playgroundsCount | integer | true | The number of playgrounds that use this vector database. | |
| separators | any | true | The text chunking separators that the vector database uses. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [any] | false | none |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| size | integer | true | The size of the vector database (in bytes). | |
| skippedChunksCount | integer | true | The number of text chunks skipped during vector database creation. | |
| 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 | any | true | The validation ID of the custom model vector database (in case of using a custom model vector database). |
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 |
|---|---|---|---|---|
| version | integer | true | The version of the vector database linked to a certain family ID. |
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] |
VectorDatabaseSettingParameter
{
"description": "API response object for a single vector database setting parameter.",
"properties": {
"default": {
"description": "The default value of the parameter.",
"title": "default"
},
"description": {
"description": "The description of the parameter.",
"title": "description",
"type": "string"
},
"enum": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of possible values for the parameter.",
"title": "enum"
},
"groupId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The identifier of the group the parameter belongs to.",
"title": "groupId"
},
"maximum": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The maximum value of the parameter.",
"title": "maximum"
},
"minimum": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "The minimum value of the parameter.",
"title": "minimum"
},
"name": {
"description": "The name of the parameter.",
"title": "name",
"type": "string"
},
"settings": {
"anyOf": [
{
"items": "[Circular]",
"type": "array"
},
{
"type": "null"
}
],
"description": "The list of available settings for the parameter.",
"title": "settings"
},
"title": {
"description": "The title of the parameter.",
"title": "title",
"type": "string"
},
"type": {
"anyOf": [
{
"description": "The types of vector database setting parameters.",
"enum": [
"string",
"integer",
"boolean",
"null",
"number",
"array"
],
"title": "VectorDatabaseSettingTypes",
"type": "string"
},
{
"items": {
"description": "The types of vector database setting parameters.",
"enum": [
"string",
"integer",
"boolean",
"null",
"number",
"array"
],
"title": "VectorDatabaseSettingTypes",
"type": "string"
},
"type": "array"
}
],
"description": "The type of the parameter.",
"title": "type"
}
},
"required": [
"name",
"type",
"description",
"title"
],
"title": "VectorDatabaseSettingParameter",
"type": "object"
}
VectorDatabaseSettingParameter
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| default | any | false | The default value of the parameter. | |
| description | string | true | The description of the parameter. | |
| enum | any | false | The list of possible values for the parameter. |
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 |
|---|---|---|---|---|
| groupId | any | false | The identifier of the group the parameter belongs to. |
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 |
|---|---|---|---|---|
| maximum | any | false | The maximum value of the parameter. |
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 |
|---|---|---|---|---|
| minimum | any | false | The minimum value of the parameter. |
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 |
|---|---|---|---|---|
| name | string | true | The name of the parameter. | |
| settings | any | false | The list of available settings for the parameter. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [VectorDatabaseSettingParameter] | false | [API response object for a single vector database setting parameter.] |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | null | false | none |
continued
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| title | string | true | The title of the parameter. | |
| type | any | true | The type of the parameter. |
anyOf
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | VectorDatabaseSettingTypes | false | The types of vector database setting parameters. |
or
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| » anonymous | [VectorDatabaseSettingTypes] | false | [The types of vector database setting parameters.] |
VectorDatabaseSettingTypes
{
"description": "The types of vector database setting parameters.",
"enum": [
"string",
"integer",
"boolean",
"null",
"number",
"array"
],
"title": "VectorDatabaseSettingTypes",
"type": "string"
}
VectorDatabaseSettingTypes
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| VectorDatabaseSettingTypes | string | false | The types of vector database setting parameters. |
Enumerated Values¶
| Property | Value |
|---|---|
| VectorDatabaseSettingTypes | [string, integer, boolean, null, number, array] |
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. |
VectorDatabaseSource
{
"description": "The source of the vector database.",
"enum": [
"DataRobot",
"External",
"Pinecone",
"Elasticsearch"
],
"title": "VectorDatabaseSource",
"type": "string"
}
VectorDatabaseSource
Properties¶
| Name | Type | Required | Restrictions | Description |
|---|---|---|---|---|
| VectorDatabaseSource | string | false | The source of the vector database. |
Enumerated Values¶
| Property | Value |
|---|---|
| VectorDatabaseSource | [DataRobot, External, Pinecone, Elasticsearch] |