:doc:`AgentsforBedrock <../../bedrock-agent>` / Client / delete_knowledge_base_documents

*******************************
delete_knowledge_base_documents
*******************************



.. py:method:: 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 changes directly into a knowledge base <https://docs.aws.amazon.com/bedrock/latest/userguide/kb-direct-ingestion.html>`__ in the Amazon Bedrock User Guide.

  

  See also: `AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/bedrock-agent-2023-06-05/DeleteKnowledgeBaseDocuments>`_  


  **Request Syntax**
  ::

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

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

    

  
  :type dataSourceId: string
  :param dataSourceId: **[REQUIRED]** 

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

    

  
  :type clientToken: string
  :param clientToken: 

    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 <https://docs.aws.amazon.com/AWSEC2/latest/APIReference/Run_Instance_Idempotency.html>`__.

    This field is autopopulated if not provided.

  
  :type documentIdentifiers: list
  :param documentIdentifiers: **[REQUIRED]** 

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

    

  
    - *(dict) --* 

      Contains information that identifies the document.

      

    
      - **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/``.

          

        
      
      - **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.

          

        
      
    

  
  :rtype: dict
  :returns: 
    
    **Response Syntax**

    
    ::

      {
          'documentDetails': [
              {
                  'knowledgeBaseId': 'string',
                  'dataSourceId': 'string',
                  'status': 'INDEXED'|'PARTIALLY_INDEXED'|'PENDING'|'FAILED'|'METADATA_PARTIALLY_INDEXED'|'METADATA_UPDATE_FAILED'|'IGNORED'|'NOT_FOUND'|'STARTING'|'IN_PROGRESS'|'DELETING'|'DELETE_IN_PROGRESS',
                  'identifier': {
                      'dataSourceType': 'CUSTOM'|'S3',
                      's3': {
                          'uri': 'string'
                      },
                      'custom': {
                          'id': 'string'
                      }
                  },
                  '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.

          
          

          - **knowledgeBaseId** *(string) --* 

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

            
          

          - **dataSourceId** *(string) --* 

            The identifier of the data source connected to 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:

             

            
            * STARTING – 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.
            

            
          

          - **identifier** *(dict) --* 

            Contains information that identifies the document.

            
            

            - **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/``.

                
          
            

            - **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.

                
          
        
          

          - **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**
  
  *   :py:class:`AgentsforBedrock.Client.exceptions.ThrottlingException`

  
  *   :py:class:`AgentsforBedrock.Client.exceptions.AccessDeniedException`

  
  *   :py:class:`AgentsforBedrock.Client.exceptions.ValidationException`

  
  *   :py:class:`AgentsforBedrock.Client.exceptions.InternalServerException`

  
  *   :py:class:`AgentsforBedrock.Client.exceptions.ResourceNotFoundException`

  
  *   :py:class:`AgentsforBedrock.Client.exceptions.ServiceQuotaExceededException`

  