AgentsforBedrockRuntime / Client / retrieve

retrieve#

AgentsforBedrockRuntime.Client.retrieve(**kwargs)#

Queries a knowledge base and retrieves information from it.

Request Syntax

response = client.retrieve(
    knowledgeBaseId='string',
    nextToken='string',
    retrievalConfiguration={
        'vectorSearchConfiguration': {
            'numberOfResults': 123,
            'overrideSearchType': 'HYBRID'|'SEMANTIC'
        }
    },
    retrievalQuery={
        'text': 'string'
    }
)

Parameters:

knowledgeBaseId (string) –
[REQUIRED]

The unique identifier of the knowledge base to query.
nextToken (string) – If there are more results than can fit in the response, the response returns a nextToken. Use this token in the nextToken field of another request to retrieve the next batch of results.
retrievalConfiguration (dict) –
Contains details about how the results should be returned.
- vectorSearchConfiguration (dict) – [REQUIRED]
  
  Contains details about how the results from the vector search should be returned.
  - numberOfResults (integer) –
    
    The number of results to return.
    
    Note
    The numberOfResults field is currently unsupported for RetrieveAndGenerate. Don’t include it in this field if you are sending a RetrieveAndGenerate request.
  - overrideSearchType (string) –
    
    By default, Amazon Bedrock decides a search strategy for you. If you’re using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available. For more information, see Test a knowledge base.
retrievalQuery (dict) –
[REQUIRED]

The query to send the knowledge base.
- text (string) – [REQUIRED]
  
  The text of the query made to the knowledge base.

Return type:

dict

Returns:

Response Syntax

{
    'nextToken': 'string',
    'retrievalResults': [
        {
            'content': {
                'text': 'string'
            },
            'location': {
                's3Location': {
                    'uri': 'string'
                },
                'type': 'S3'
            },
            'score': 123.0
        },
    ]
}

Response Structure

(dict) –
- nextToken (string) –
  
  If there are more results than can fit in the response, the response returns a nextToken. Use this token in the nextToken field of another request to retrieve the next batch of results.
- retrievalResults (list) –
  
  A list of results from querying the knowledge base.
  - (dict) –
    
    Details about a result from querying the knowledge base.
    - content (dict) –
      
      Contains a chunk of text from a data source in the knowledge base.
      - text (string) –
        
        The cited text from the data source.
    - location (dict) –
      
      Contains information about the location of the data source.
      - s3Location (dict) –
        
        Contains the S3 location of the data source.
        
        uri (string) –
        
        The S3 URI of the data source.
      - type (string) –
        
        The type of the location of the data source.
    - score (float) –
      
      The level of relevance of the result to the query.

Exceptions

AgentsforBedrockRuntime.Client.exceptions.ConflictException
AgentsforBedrockRuntime.Client.exceptions.ResourceNotFoundException
AgentsforBedrockRuntime.Client.exceptions.ValidationException
AgentsforBedrockRuntime.Client.exceptions.InternalServerException
AgentsforBedrockRuntime.Client.exceptions.DependencyFailedException
AgentsforBedrockRuntime.Client.exceptions.BadGatewayException
AgentsforBedrockRuntime.Client.exceptions.ThrottlingException
AgentsforBedrockRuntime.Client.exceptions.AccessDeniedException
AgentsforBedrockRuntime.Client.exceptions.ServiceQuotaExceededException