AgentsforBedrock / Client / start_ingestion_job

start_ingestion_job

AgentsforBedrock.Client.start_ingestion_job(**kwargs)

Begins a data ingestion job. Data sources are ingested into your knowledge base so that Large Language Models (LLMs) can use your data.

See also: AWS API Documentation

Request Syntax

response = client.start_ingestion_job(
    knowledgeBaseId='string',
    dataSourceId='string',
    clientToken='string',
    description='string'
)
Parameters:

  • knowledgeBaseId (string) –

    [REQUIRED]

    The unique identifier of the knowledge base for the data ingestion job.

  • dataSourceId (string) –

    [REQUIRED]

    The unique identifier of the data source you want to ingest into your knowledge base.

  • 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.

  • description (string) – A description of the data ingestion job.

Return type:

dict

Returns:

Response Syntax

{
    'ingestionJob': {
        'knowledgeBaseId': 'string',
        'dataSourceId': 'string',
        'ingestionJobId': 'string',
        'description': 'string',
        'status': 'STARTING'|'IN_PROGRESS'|'COMPLETE'|'FAILED'|'STOPPING'|'STOPPED',
        'statistics': {
            'numberOfDocumentsScanned': 123,
            'numberOfMetadataDocumentsScanned': 123,
            'numberOfNewDocumentsIndexed': 123,
            'numberOfModifiedDocumentsIndexed': 123,
            'numberOfMetadataDocumentsModified': 123,
            'numberOfDocumentsDeleted': 123,
            'numberOfDocumentsFailed': 123,
            'numberOfDocumentsSkipped': 123
        },
        'failureReasons': [
            'string',
        ],
        'startedAt': datetime(2015, 1, 1),
        'updatedAt': datetime(2015, 1, 1),
        'textReadyAt': datetime(2015, 1, 1)
    }
}

Response Structure

  • (dict) –

    • ingestionJob (dict) –

      Contains information about the data ingestion job.

      • knowledgeBaseId (string) –

        The unique identifier of the knowledge for the data ingestion job.

      • dataSourceId (string) –

        The unique identifier of the data source for the data ingestion job.

      • ingestionJobId (string) –

        The unique identifier of the data ingestion job.

      • description (string) –

        The description of the data ingestion job.

      • status (string) –

        The status of the data ingestion job.

      • statistics (dict) –

        Contains statistics about the data ingestion job.

        • numberOfDocumentsScanned (integer) –

          The total number of source documents that were scanned. Includes new, updated, and unchanged documents.

        • numberOfMetadataDocumentsScanned (integer) –

          The total number of metadata files that were scanned. Includes new, updated, and unchanged files.

        • numberOfNewDocumentsIndexed (integer) –

          The number of new source documents in the data source that were successfully indexed.

        • numberOfModifiedDocumentsIndexed (integer) –

          The number of modified source documents in the data source that were successfully indexed.

        • numberOfMetadataDocumentsModified (integer) –

          The number of metadata files that were updated or deleted.

        • numberOfDocumentsDeleted (integer) –

          The number of source documents that were deleted.

        • numberOfDocumentsFailed (integer) –

          The number of source documents that failed to be ingested.

        • numberOfDocumentsSkipped (integer) –

          The number of source documents that were skipped during ingestion.

      • failureReasons (list) –

        A list of reasons that the data ingestion job failed.

        • (string) –

      • startedAt (datetime) –

        The time the data ingestion job started.

        If you stop a data ingestion job, the startedAt time is the time the job was started before the job was stopped.

      • updatedAt (datetime) –

        The time the data ingestion job was last updated.

        If you stop a data ingestion job, the updatedAt time is the time the job was stopped.

      • textReadyAt (datetime) –

        The time at which all text content in the data ingestion job finished extraction and became available to query.

        This time isn’t returned until text extraction is complete for all the documents in the job.

Exceptions