AgentsforBedrock / Client / delete_knowledge_base_documents

delete_knowledge_base_documents

AgentsforBedrock.Client.delete_knowledge_base_documents(**kwargs)

Deletes documents from a data source and syncs the changes to the knowledge base that is connected to it. For more information, see Ingest documents into a knowledge base in real-time in the Amazon Bedrock User Guide.

See also: AWS API Documentation

Request Syntax

response = client.delete_knowledge_base_documents(
    clientToken='string',
    dataSourceId='string',
    documentIdentifiers=[
        {
            'custom': {
                'id': 'string'
            },
            'dataSourceType': 'CUSTOM'|'S3',
            's3': {
                'uri': 'string'
            }
        },
    ],
    knowledgeBaseId='string'
)

Parameters:

• clientToken (string) –

  A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

  This field is autopopulated if not provided.

• dataSourceId (string) –

  [REQUIRED]

  The unique identifier of the data source that contains the documents.

• documentIdentifiers (list) –

  [REQUIRED]

  A list of objects, each of which contains information to identify a document to delete.

  • (dict) –

    Contains information that identifies the document.

    • custom (dict) –

      Contains information that identifies the document in a custom data source.

      • id (string) – [REQUIRED]

        The identifier of the document to ingest into a custom data source.

    • dataSourceType (string) – [REQUIRED]

      The type of data source connected to the knowledge base that contains the document.

    • s3 (dict) –

      Contains information that identifies the document in an S3 data source.

      • uri (string) – [REQUIRED]

        The location’s URI. For example, s3://my-bucket/chunk-processor/.

• knowledgeBaseId (string) –

  [REQUIRED]

  The unique identifier of the knowledge base that is connected to the data source.

Return type:

dict

Returns:

Response Syntax

{
    'documentDetails': [
        {
            'dataSourceId': 'string',
            'identifier': {
                'custom': {
                    'id': 'string'
                },
                'dataSourceType': 'CUSTOM'|'S3',
                's3': {
                    'uri': 'string'
                }
            },
            'knowledgeBaseId': 'string',
            'status': 'INDEXED'|'PARTIALLY_INDEXED'|'PENDING'|'FAILED'|'METADATA_PARTIALLY_INDEXED'|'METADATA_UPDATE_FAILED'|'IGNORED'|'NOT_FOUND'|'STARTING'|'IN_PROGRESS'|'DELETING'|'DELETE_IN_PROGRESS',
            'statusReason': 'string',
            'updatedAt': datetime(2015, 1, 1)
        },
    ]
}

Response Structure

• (dict) –

  • documentDetails (list) –

    A list of objects, each of which contains information about the documents that were deleted.

    • (dict) –

      Contains the details for a document that was ingested or deleted.

      • dataSourceId (string) –

        The identifier of the data source connected to the knowledge base that the document was ingested into or deleted from.

      • identifier (dict) –

        Contains information that identifies the document.

        • custom (dict) –

          Contains information that identifies the document in a custom data source.

          • id (string) –

            The identifier of the document to ingest into a custom data source.

        • dataSourceType (string) –

          The type of data source connected to the knowledge base that contains the document.

        • s3 (dict) –

          Contains information that identifies the document in an S3 data source.

          • uri (string) –

            The location’s URI. For example, s3://my-bucket/chunk-processor/.

      • knowledgeBaseId (string) –

        The identifier of the knowledge base that the document was ingested into or deleted from.

      • status (string) –

        The ingestion status of the document. The following statuses are possible:

        • STARTED – You submitted the ingestion job containing the document.

        • PENDING – The document is waiting to be ingested.

        • IN_PROGRESS – The document is being ingested.

        • INDEXED – The document was successfully indexed.

        • PARTIALLY_INDEXED – The document was partially indexed.

        • METADATA_PARTIALLY_INDEXED – You submitted metadata for an existing document and it was partially indexed.

        • METADATA_UPDATE_FAILED – You submitted a metadata update for an existing document but it failed.

        • FAILED – The document failed to be ingested.

        • NOT_FOUND – The document wasn’t found.

        • IGNORED – The document was ignored during ingestion.

        • DELETING – You submitted the delete job containing the document.

        • DELETE_IN_PROGRESS – The document is being deleted.

      • statusReason (string) –

        The reason for the status. Appears alongside the status IGNORED.

      • updatedAt (datetime) –

        The date and time at which the document was last updated.

Exceptions

• AgentsforBedrock.Client.exceptions.ThrottlingException

• AgentsforBedrock.Client.exceptions.AccessDeniedException

• AgentsforBedrock.Client.exceptions.ValidationException

• AgentsforBedrock.Client.exceptions.InternalServerException

• AgentsforBedrock.Client.exceptions.ResourceNotFoundException

• AgentsforBedrock.Client.exceptions.ServiceQuotaExceededException