AgentsforBedrock / Client / create_data_source

create_data_source

AgentsforBedrock.Client.create_data_source(**kwargs)

Create a new data source

See also: AWS API Documentation

Request Syntax

response = client.create_data_source(
    knowledgeBaseId='string',
    clientToken='string',
    name='string',
    description='string',
    dataSourceConfiguration={
        'type': 'S3',
        's3Configuration': {
            'bucketArn': 'string',
            'inclusionPrefixes': [
                'string',
            ]
        }
    },
    serverSideEncryptionConfiguration={
        'kmsKeyArn': 'string'
    },
    vectorIngestionConfiguration={
        'chunkingConfiguration': {
            'chunkingStrategy': 'FIXED_SIZE'|'NONE',
            'fixedSizeChunkingConfiguration': {
                'maxTokens': 123,
                'overlapPercentage': 123
            }
        }
    }
)

Parameters:

• knowledgeBaseId (string) –

  [REQUIRED]

  Identifier for a resource.

• clientToken (string) –

  Client specified token used for idempotency checks

  This field is autopopulated if not provided.

• name (string) –

  [REQUIRED]

  Name for a resource.

• description (string) – Description of the Resource.

• dataSourceConfiguration (dict) –

  [REQUIRED]

  Specifies a raw data source location to ingest.

  • type (string) – [REQUIRED]

    The type of the data source location.

  • s3Configuration (dict) –

    Configures an S3 data source location.

    • bucketArn (string) – [REQUIRED]

      A S3 bucket ARN

    • inclusionPrefixes (list) –

      A list of S3 prefixes.

      • (string) –

        Prefix for s3 object.

• serverSideEncryptionConfiguration (dict) –

  Server-side encryption configuration.

  • kmsKeyArn (string) –

    A KMS key ARN

• vectorIngestionConfiguration (dict) –

  Configures ingestion for a vector knowledge base

  • chunkingConfiguration (dict) –

    Configures chunking strategy

    • chunkingStrategy (string) – [REQUIRED]

      The type of chunking strategy

    • fixedSizeChunkingConfiguration (dict) –

      Configures fixed size chunking strategy

      • maxTokens (integer) – [REQUIRED]

        The maximum number of tokens per chunk.

      • overlapPercentage (integer) – [REQUIRED]

        The overlap percentage between adjacent chunks.

Return type:

dict

Returns:

Response Syntax

{
    'dataSource': {
        'knowledgeBaseId': 'string',
        'dataSourceId': 'string',
        'name': 'string',
        'status': 'AVAILABLE'|'DELETING',
        'description': 'string',
        'dataSourceConfiguration': {
            'type': 'S3',
            's3Configuration': {
                'bucketArn': 'string',
                'inclusionPrefixes': [
                    'string',
                ]
            }
        },
        'serverSideEncryptionConfiguration': {
            'kmsKeyArn': 'string'
        },
        'vectorIngestionConfiguration': {
            'chunkingConfiguration': {
                'chunkingStrategy': 'FIXED_SIZE'|'NONE',
                'fixedSizeChunkingConfiguration': {
                    'maxTokens': 123,
                    'overlapPercentage': 123
                }
            }
        },
        'createdAt': datetime(2015, 1, 1),
        'updatedAt': datetime(2015, 1, 1)
    }
}

Response Structure

• (dict) –

  • dataSource (dict) –

    Contains the information of a data source.

    • knowledgeBaseId (string) –

      Identifier for a resource.

    • dataSourceId (string) –

      Identifier for a resource.

    • name (string) –

      Name for a resource.

    • status (string) –

      The status of a data source.

    • description (string) –

      Description of the Resource.

    • dataSourceConfiguration (dict) –

      Specifies a raw data source location to ingest.

      • type (string) –

        The type of the data source location.

      • s3Configuration (dict) –

        Configures an S3 data source location.

        • bucketArn (string) –

          A S3 bucket ARN

        • inclusionPrefixes (list) –

          A list of S3 prefixes.

          • (string) –

            Prefix for s3 object.

    • serverSideEncryptionConfiguration (dict) –

      Server-side encryption configuration.

      • kmsKeyArn (string) –

        A KMS key ARN

    • vectorIngestionConfiguration (dict) –

      Configures ingestion for a vector knowledge base

      • chunkingConfiguration (dict) –

        Configures chunking strategy

        • chunkingStrategy (string) –

          The type of chunking strategy

        • fixedSizeChunkingConfiguration (dict) –

          Configures fixed size chunking strategy

          • maxTokens (integer) –

            The maximum number of tokens per chunk.

          • overlapPercentage (integer) –

            The overlap percentage between adjacent chunks.

    • createdAt (datetime) –

      Time Stamp.

    • updatedAt (datetime) –

      Time Stamp.

Exceptions

• AgentsforBedrock.Client.exceptions.ThrottlingException

• AgentsforBedrock.Client.exceptions.AccessDeniedException

• AgentsforBedrock.Client.exceptions.ValidationException

• AgentsforBedrock.Client.exceptions.InternalServerException

• AgentsforBedrock.Client.exceptions.ResourceNotFoundException

• AgentsforBedrock.Client.exceptions.ConflictException

• AgentsforBedrock.Client.exceptions.ServiceQuotaExceededException