Developer documentation > API reference > Python API client > Generative AI > Vector databases

Vector Databases¶

CustomModelVectorDatabaseValidation¶

class datarobot.models.genai.vector_database.CustomModelVectorDatabaseValidation

Validation record checking the ability of the deployment to serve as a vector database.

Variables

Attribute	Type	Description
`id`	`str`	The ID of the validation.
`prompt_column_name`	`str`	The column name the deployed model expect as the input.
`target_column_name`	`str`	The target name deployed model will output.
`deployment_id`	`str`	ID of the deployment.
`model_id`	`str`	ID of the underlying deployment model. Can be found from the API as Deployment.model[“id”].
`validation_status`	`str`	Can be TESTING, FAILED and PASSED. Only PASSED allowed for use.
`deployment_access_data`	`dict`, optional	The data that will be used for accessing the deployment prediction server. This field is only available for deployments that pass validation. Dict fields are as follows:- prediction_api_url - The URL for the deployment prediction server. - datarobot_key - The first of two auth headers for the prediction server. - authorization_header - The second of two auth headers for the prediction server. - input_type - The input type the model expects, either JSON or CSV. - model_type - The target type of the deployed custom model.
`tenant_id`	`str`	The creating user’s tenant ID.
`name`	`str`	The display name of the validated custom model.
`creation_date`	`str`	The creation date of the validation (ISO 8601 formatted).
`user_id`	`str`	The ID of the creating user.
`error_message`	`Optional[str]`	Additional information for the errored validation.
`deployment_name`	`Optional[str]`	The name of the validated deployment.
`user_name`	`Optional[str]`	The name of the creating user.
`use_case_id`	`Optional[str]`	The ID of the Use Case associated with the validation.

SupportedEmbeddings¶

class datarobot.models.genai.vector_database.SupportedEmbeddings

All supported embedding models including the recommended default model.

Variables

Attribute	Type	Description
`embedding_models`	`list[EmbeddingModel]`	All supported embedding models.
`default_embedding_model`	`str`	Name of the default recommended text embedding model. Currently supported options are listed in VectorDatabaseEmbeddingModel but the values can differ with different platform versions.
`custom_model_embedding_validations`	`List[str]`	External embedding custom models that have been validated
`openai_embedding_validations`	`List[str]`	External OpenAI compatible embedding models that have been validated

SupportedCustomModelEmbedding¶

class datarobot.models.genai.vector_database.SupportedCustomModelEmbedding

SupportedOpenAIEmbeddingModel¶

class datarobot.models.genai.vector_database.SupportedOpenAIEmbeddingModel

SupportedTextChunkings¶

class datarobot.models.genai.vector_database.SupportedTextChunkings

Supported text chunking configurations which includes a set of recommended chunking parameters for each supported embedding model.

Variables

Attribute	Type	Description
`text_chunking_configs`		All supported text chunking configurations.

VectorDatabase¶

class datarobot.models.genai.vector_database.VectorDatabase

Metadata for a DataRobot vector database accessible to the user.

Variables

Attribute	Type	Description
`id`	`str`	Vector database ID.
`name`	`str`	Vector database name.
`size`	`int`	Size of the vector database assets in bytes.
`use_case_id`	`str`	Linked use case ID.
`dataset_id`	`str`	ID of the dataset used for creation.
`embedding_model`	`str`	Name of the text embedding model. Currently supported options are listed in VectorDatabaseEmbeddingModel but the values can differ with different platform versions.
`chunking_method`	`str` or `None`	Name of the method to split dataset documents. Currently supported options are listed in VectorDatabaseChunkingMethod but the values can differ with different platform versions.
`chunk_size`	`int` or `None`	Size of each text chunk in number of tokens.
`chunk_overlap_percentage`	`int` or `None`	Overlap percentage between chunks.
`chunks_count`	`int`	Total number of text chunks.
`custom_chunking`	`bool`	Determines if the chunking is custom. With custom chunking, dataset rows are not split into chunks automatically;instead, the user provides the chunks.
`separators`	`list[string]` or `None`	Separators for document splitting.
`creation_date`	`str`	Date when the database was created.
`creation_user_id`	`str`	The ID of the creating user.
`organization_id`	`str`	The creating user’s organization ID.
`tenant_id`	`str`	The creating user’s tenant ID.
`last_update_date`	`str`	Last update date for the database.
`execution_status`	`str`	Database execution status. Currently supported options are listed in VectorDatabaseExecutionStatus but the values can differ with different platform versions.
`playgrounds_count`	`int`	Number of using playgrounds.
`dataset_name`	`str`	Name of the used dataset.
`user_name`	`str`	Name of the creating user.
`source`	`str`	Source of the vector database. Currently supported options are listed in VectorDatabaseSource but the values can differ with different platform versions.
`validation_id`	`Optional[str]`	ID of custom model vector database validation. Only filled for external vector databases.
`error_message`	`Optional[str]`	Additional information for errored vector database.
`embedding_validation_id`	`Optional[str]`	ID of the custom embedding validation, if any.
`is_separator_regex`	`bool`	Whether the separators should be treated as regular expressions.
`external_vector_database_connection`	`Optional[dict]`	Parameters defining the external vector database connection to use.
`metadata_dataset_id`	`Optional[str]`	The ID of the dataset used to add additional metadata to the vector database.
`metadata_dataset_name`	`Optional[str]`	The name of the dataset used to add additional metadata to the vector database.
`metadata_combination_strategy`	`Optional[VectorDatabaseMetadataCombinationStrategy]`	The strategy used to combine metadata when there is duplication between the dataset and the metadata dataset.
`added_metadata_dataset_pairs`	`Optional[List[Dict[str`, `str]]`	Pairs of dataset_id and metadata_dataset_id that have been added to the vector database.

get_supported_embeddings()¶

classmethod get_supported_embeddings()

Get all supported and the recommended embedding models.

Parameters

Parameter	Type	Description
`dataset_id`	`Optional[str]`	ID of a dataset for which the recommended model is returned based on the detected language of that dataset.
`use_case`	`Optional[UseCase`, `str]`	May be Use Case ID or the Use Case entity.

Returns

Returns	Description
supported_embeddings	The supported embedding models.

Return type: SupportedEmbeddings

submit_export_dataset_job()¶

method submit_export_dataset_job()

Submit the vector database dataset export job.

Returns

Returns	Description
result	The result of the vector database dataset export job containing the exported dataset id.

Return type: VectorDatabaseDatasetExportJob

get_supported_retrieval_settings()¶

classmethod get_supported_retrieval_settings()

Get supported retrieval settings.

Returns

Returns	Description
supported_retrieval_settings	The supported retriever settings.

Return type: SupportedRetrievalSettings

create()¶

classmethod create()

Create a new vector database.

Parameters

Parameter	Type	Description
`dataset_id`	`str`	ID of the dataset used for creation.
`chunking_parameters`	`ChunkingParameters`	Parameters defining how documents are split and embedded.
`use_case`	`Optional[Union[UseCase`, `str]]`, optional	Use case to link to the created vector database.
`name`	`Optional[str]`	Vector database name, by default None which leads to the default name ‘Vector Database for ’.
`parent_vector_database_id`	`Optional[str]`	ID of the parent vector database to base the update on.
`update_llm_blueprints`	`Optional[bool]`	Whether to update LLM blueprints related to the parent vector database.
`update_deployments`	`Optional[bool]`	Whether to update deployments related to the parent vector database.
`external_vector_database_connection`	`Optional[dict]`	Parameters defining the external vector database connection to use.
`metadata_dataset_id`	`Optional[str]`	The ID of the dataset used to provide additional metadata.
`metadata_combination_strategy`	`Optional[VectorDatabaseMetadataCombinationStrategy]`	Strategy used to combine the metadata columns if there are duplicates between the dataset and the metadata dataset.

Returns

Returns	Description
vector database	The created vector database with execution status ‘new’.

Return type: VectorDatabase

create_from_custom_model()¶

classmethod create_from_custom_model()

Create a new vector database from validated custom model deployment.

Parameters

Parameter	Type	Description
`name`	`str`	Vector database name.
`use_case`	`Optional[Union[UseCase`, `str]]`, optional	Use case to link to the created vector database.
`validation_id`	`Optional[str]`	ID of CustomModelVectorDatabaseValidation for the deployment. Alternatively, you can specify ALL the following fields.
`prompt_column_name`	`Optional[str]`	The column name the deployed model expect as the input.
`target_column_name`	`Optional[str]`	The target name deployed model will output.
`deployment_id`	`Optional[str]`	ID of the deployment.
`model_id`	`Optional[str]`	ID of the underlying deployment model. Can be found from the API as Deployment.model[“id”].

Returns

Returns	Description
vector database	The created vector database.

Return type: VectorDatabase

get()¶

classmethod get()

Retrieve a single vector database.

Parameters

Parameter	Type	Description
`vector_database_id`	`str`	The ID of the vector database you want to retrieve.

Returns

Returns	Description
vector database	The requested vector database.

Return type: VectorDatabase

list()¶

classmethod list()

List all vector databases associated with a specific use case available to the user.

Parameters

Parameter	Type	Description
`use_case`	`Optional[UseCaseLike]`, optional	The returned vector databases are filtered to those associated with a specific Use Case or Cases if specified or can be inferred from the Context. Accepts either the entity or the ID.
`playground`	`Optional[Union[Playground`, `str]]`, optional	The returned vector databases are filtered to those associated with a specific playground if it is specified. Accepts either the entity or the ID.
`search`	`Optional[str]`	String for filtering vector databases. Vector databases that contain the string in name will be returned. If not specified, all vector databases will be returned.
`sort`	`Optional[str]`	Property to sort vector databases by. Prefix the attribute name with a dash to sort in descending order, e.g., sort=’-creationDate’. Currently supported options are listed in ListVectorDatabasesSortQueryParams but the values can differ with different platform versions. By default, the sort parameter is None which will result in vector databases being returned in order of creation time descending.
`completed_only`	`Optional[bool]`	A filter to retrieve only vector databases that have been successfully created. By default, all vector databases regardless of execution status are retrieved.

Returns

Returns	Description
vectorbases	A list of vector databases available to the user.

Return type: list[VectorDatabase]

update()¶

method update()

Update the vector database.

Parameters

Parameter	Type	Description
`name`	`Optional[str]`	The new name for the vector database.
`credential_id`	`Optional[str]`	The new credential id to access the connected vector database.

Returns

Returns	Description
vector database	The updated vector database.

Return type: VectorDatabase

update_connected()¶

method update_connected()

Update a connected vector database.

Parameters

Parameter	Type	Description
`dataset_id`	`str`	The ID of the dataset to add to the vector database.
`metadata_dataset_id`	`Optional[str]`	The ID of the dataset used to provide additional metadata.
`metadata_combination_strategy`	`Optional[VectorDatabaseMetadataCombinationStrategy]`	Strategy used to combine the metadata columns if there are duplicates between the dataset and the metadata dataset.

Returns

Returns	Description
vector database	The updated vector database.

Return type: VectorDatabase

delete()¶

method delete()

Delete the vector database.

Return type: None

get_supported_text_chunkings()¶

classmethod get_supported_text_chunkings()

Get all supported text chunking configurations which includes a set of recommended chunking parameters for each supported embedding model.

Returns

Returns	Description
supported_text_chunkings	The supported text chunking configurations.

Return type: SupportedTextChunkings

download_text_and_embeddings_asset()¶

method download_text_and_embeddings_asset()

Download a parquet file with text chunks and corresponding embeddings created by a vector database.

Parameters

Parameter	Type	Description
`file_path`	`Optional[str]`	File path to save the asset. By default, it saves in the current directory autogenerated by server name.
`part`	`Optional[int]`	Part of the text chunks to download. Connected vector databases have a part for each dataset that is added.

Return type: None

send_to_custom_model_workshop()¶

method send_to_custom_model_workshop()

Create a new CustomModelVersion for this vector database.

Parameters

Parameter	Type	Description
`maximum_memory`	`Optional[int]`	The maximum memory that will be allocated to this custom model.
`resource_bundle_id`	`Optional[str]`	The ID of a datarobot.models.resource_bundle.ResourceBundle that will be used by this custom model.
`replicas`	`Optional[int]`	A fixed number of replicas that will be deployed for this custom model.
`network_egress_policy`	`Optional[str]`	Determines whether the given custom model is isolated, or can access the public network. Values: [datarobot.NETWORK_EGRESS_POLICY.NONE, datarobot.NETWORK_EGRESS_POLICY.PUBLIC].

Return type: CustomModelVersion

deploy()¶

method deploy()

Create a new Custom Model for this vector database and deploy it on a new Deployment.

Parameters

Parameter	Type	Description
`default_prediction_server_id`	`Optional[str]`	An identifier of a prediction server to be used as the default prediction server. When working with prediction environments, the default prediction server ID should not be provided.
`prediction_environment_id`	`Optional[str]`	An identifier of a prediction environment to be used for model deployment.
`credential_id`	`Optional[str]:`	The ID of credentials to access a connected vector database. Only needed for vector databases with an external source when the user does not have access to the credentials associated with this vector database.
`maximum_memory`	`Optional[int]`	The maximum memory that will be allocated to the new custom model.
`resource_bundle_id`	`Optional[str]`	The ID of a datarobot.models.resource_bundle.ResourceBundle that will be used by the new custom model.
`replicas`	`Optional[int]`	A fixed number of replicas that will be deployed for this custom model.
`network_egress_policy`	`Optional[str]`	Determines whether the given custom model is isolated, or can access the public network. Values: [datarobot.NETWORK_EGRESS_POLICY.NONE, datarobot.NETWORK_EGRESS_POLICY.PUBLIC].

Return type: Deployment

SupportedRetrievalSetting¶

class datarobot.models.genai.vector_database.SupportedRetrievalSetting

A single supported retrieval setting.

Variables

Attribute	Type	Description
`name`	`str`	The name of the setting.
`type`	`str` or `list[str]`	The type of the setting.
`description`	`str`	The description of the setting.
`title`	`str`	The title of the setting.
`default`	`str`, `int`, `bool`, or `None`	The default value of the setting.
`minimum`	`int` or `None`	The minimum value of the setting.
`maximum`	`int` or `None`	The maximum value of the setting.
`enum`	`list[str]` or `None`	The enum values of the setting.
`settings`	`list[SupportedRetrievalSetting]` or `None`	The supported retriever settings.
`group_id`	`str` or `None`	The group ID of the setting.

VectorDatabaseDatasetExportJob¶

class datarobot.models.genai.vector_database.VectorDatabaseDatasetExportJob

Response for the vector database dataset export job.

Variables

Attribute	Type	Description
`job_id`	`str`	ID of the export job.
`vector_database_id`	`str`	ID of the vector database.
`export_dataset_id`	`str`	ID of the exported dataset.

Citation¶

class datarobot.models.genai.chat_prompt.Citation

Citation for documents retrieved from a vector database.

Variables

Attribute	Type	Description
`text`	`str`	The text retrieved from a vector database.
`source`	`str` or `None`, optional	The source of the retrieved text.
`similarity_score`		The similarity score between the citation and the user prompt.
`metadata`	`dict` or `None`, optional	Additional metadata for the citation.

VectorDatabaseSettings¶

class datarobot.models.genai.llm_blueprint.VectorDatabaseSettings

Settings for a DataRobot GenAI vector database associated with an LLM blueprint.

Variables

Attribute	Type	Description
`max_documents_retrieved_per_prompt`	`int` or `None`, optional	The maximum number of documents to retrieve for each prompt.
`max_tokens`	`int` or `None`, optional	The maximum number of tokens to retrieve for each document.
`retriever`	`VectorDatabaseRetrievers`	The vector database retriever name.
`add_neighbor_chunks`		Whether to add neighboring documents to the retrieved documents.
`retrieval_mode`	`VectorDatabaseRetrievalMode`	The vector database retrieval mode.
`maximal_marginal_relevance_lambda`	`float`	The maximal marginal relevance lambda. Favors diversity (0.0) or similarity (1.0) of the retrieved documents.

ChunkingParameters¶

class datarobot.models.genai.vector_database.ChunkingParameters

Parameters defining how documents are split and embedded.

Variables

Attribute	Type	Description
`embedding_model`	`Optional[str]`	Name of the text embedding model. Currently supported options are listed in VectorDatabaseEmbeddingModel but the values can differ with different platform versions.
`chunking_method`	`str`	Name of the method to split dataset documents. Currently supported options are listed in VectorDatabaseChunkingMethod but the values can differ with different platform versions.
`chunk_size`	`int`	Size of each text chunk in number of tokens.
`chunk_overlap_percentage`	`int`	Overlap percentage between chunks.
`separators`	`list[str]`	Strings used to split documents into text chunks.
`embedding_validation`		Optional[CustomModelEmbeddingValidation, OpenAIEmbddingModelValidation, SupportedEmbeddingExternalModel, str] ID or object for embedding validation.
`custom_chunking`	`bool`	Determines if the chunking is custom. With custom chunking, dataset rows are not split into chunks automatically;instead, the user provides the chunks.

CustomModelEmbeddingValidation¶

class datarobot.models.genai.custom_model_embedding_validation.CustomModelEmbeddingValidation

Validation record checking the ability of the deployment to serve as a custom model embedding.

Variables

Attribute	Type	Description
`id`	`str`	The ID of the validation.
`prompt_column_name`	`str`	The column name the deployed model expect as the input.
`target_column_name`	`str`	The target name that the deployed model will output.
`deployment_id`	`str`	The ID of the deployment.
`model_id`	`str`	The ID of the underlying deployed model, which can be found using Deployment.model[“id”].
`validation_status`	`str`	Can be TESTING, FAILED, or PASSED. Only PASSED is allowed for use.
`deployment_access_data`	`dict`, optional	The data that will be used for accessing the deployment prediction server. This field is only available for deployments that pass validation. Dict fields are as follows:- prediction_api_url - The URL for the deployment prediction server. - datarobot_key - The first of two auth headers for the prediction server. - authorization_header - The second of two auth headers for the prediction server. - input_type - The input type the model expects, either JSON or CSV. - model_type - The target type of the deployed custom model.
`tenant_id`	`str`	The creating user’s tenant ID.
`name`	`str`	The display name of the validated custom model.
`creation_date`	`str`	The creation date of the validation (ISO 8601 formatted).
`user_id`	`str`	The ID of the creating user.
`error_message`	`Optional[str]`	Additional information for the errored validation.
`deployment_name`	`Optional[str]`	The name of the validated deployment.
`user_name`	`Optional[str]`	The name of the creating user.
`use_case_id`	`Optional[str]`	The ID of the Use Case associated with the validation.
`prediction_timeout`	`int`	The timeout in seconds for the prediction API used in this custom model validation.

OpenAIEmbeddingModelValidation¶

class datarobot.models.genai.openai_embedding_model_validation.OpenAIEmbeddingModelValidation

create()¶

classmethod create()

Start the validation of the OpenAI-compatible embedding model.

Parameters

Parameter	Type	Description
`model`	`str`	The name of the validated OpenAI embeddings model.
`base_url`	`str`	Base URL to OpenAI-compatible deployment.
`credential_id`	`str`	The ID of credentials that hold token for OpenAI-compatible deployment.
`use_case`	`Union[UseCase`, `str]`	The Use Case to link the validation to, either UseCase or the Use Case ID.
`name`	`str`	The name of the validation.
`extra_body_params`	`list`	Parameters used as extra_body in request to OpenAI-compatible embeddings model.
`wait_for_completion`	`bool`	If set to True, the code will wait for the validation job to complete before returning results. If the job does not finish in 10 minutes, this method call raises a timeout error. If set to False, the code does not wait for the job to complete. Instead, OpenAIEmbeddingModelValidation.get can be used to poll for the status of the job using the validation ID returned by the method.

Return type: OpenAIEmbeddingModelValidation

get()¶

classmethod get()

Get the OpenAI-compatible embedding model validation record by ID.

Parameters

Parameter	Type	Description
`validation_id`	`str`	ID of OpenAIEmbeddingModelValidation to retrieve.

Return type: OpenAIEmbeddingModelValidation

list()¶

classmethod list()

List the validation records by field values.

Parameters

Parameter	Type	Description
`model`	`str`, optional	The name of embeddings model.
`use_cases`	`list[Union[UseCase`, `str]]`, optional	The returned validations are filtered to those associated with specific Use Cases if specified, either UseCase objects or the Use Case IDs.
`playground`	`Union[Playground`, `str]`, optional	The returned validations are filtered to those used in a specific playground if specified, either Playground or playground ID.
`completed_only`	`bool`	Whether to retrieve only completed validations.
`search`	`str`, optional	String for filtering validations. Validations that contain the string in name will be returned.
`sort`	`str`, optional	Property to sort validations by. Prefix the attribute name with a dash to sort in descending order, e.g., sort=’-name’. Currently supported options are listed in ListOpenAIEmbeddingValidationSortQueryParam but the values can differ with different platform versions. By default, the sort parameter is None which will result in validations being returned in order of creation time descending.

Return type: List[OpenAIEmbeddingModelValidation]

update()¶

method update()

Update a OpenAI-compatible embedding model validation.

Parameters

Parameter	Type	Description
`name`	`str`, optional	The new name of the validation.
`model`	`str`, optional	The new model within the deployment to validate.
`base_url`	`str`, optional	Base URL to OpenAI-compatible deployment.
`credential_id`	`str`, optional	The ID of credentials that hold token for OpenAI-compatible deployment.
`extra_body_params`	`list`, optional	Parameters used as extra_body in request to OpenAI-compatible embeddings model. If empty list is passed then all existing extra_body_params will be erased.

Return type: OpenAIEmbeddingModelValidation

delete()¶

method delete()

Delete the OpenAI-compatible embedding model validation.

Return type: None