AgentsforBedrock / Client / get_knowledge_base_documents

get_knowledge_base_documents#

AgentsforBedrock.Client.get_knowledge_base_documents(**kwargs)#

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

Request Syntax

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

Parameters:

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 for which to retrieve information.
- (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 retrieved.
  - (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