---
title: "PUT /knowledgebases/{knowledgeBaseId}/datasources/{dataSourceId}/ingestionjobs/"
method: PUT
path: "/knowledgebases/{knowledgeBaseId}/datasources/{dataSourceId}/ingestionjobs/"
---

# PUT /knowledgebases/{knowledgeBaseId}/datasources/{dataSourceId}/ingestionjobs/

`PUT /knowledgebases/{knowledgeBaseId}/datasources/{dataSourceId}/ingestionjobs/`

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

## Path parameters

- `knowledgeBaseId` string, required
- `dataSourceId` string, required

## Request body

- object
  - `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 <a href="https://docs.aws.amazon.com/AWSEC2/latest/APIReference/Run_Instance_Idempotency.html">Ensuring idempotency</a>.
  - `description` string — A description of the data ingestion job.

## Response `202`

Success

- StartIngestionJobResponse
  - `ingestionJob` object, required — Contains information about the data ingestion job.
    - `knowledgeBaseId` string, required — The unique identifier of the knowledge for the data ingestion job.
    - `dataSourceId` string, required — The unique identifier of the data source for the data ingestion job.
    - `ingestionJobId` string, required — The unique identifier of the data ingestion job.
    - `description` string — The description of the data ingestion job.
    - `status` 'STARTING' | 'IN_PROGRESS' | 'COMPLETE' | 'FAILED' | 'STOPPING' | 'STOPPED', required — The status of the data ingestion job.
    - `statistics` object — 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` FailureReason[] — A list of reasons that the data ingestion job failed.
    - `startedAt` string, date-time, required — <p>The time the data ingestion job started.</p> <p>If you stop a data ingestion job, the <code>startedAt</code> time is the time the job was started before the job was stopped.</p>
    - `updatedAt` string, date-time, required — <p>The time the data ingestion job was last updated.</p> <p>If you stop a data ingestion job, the <code>updatedAt</code> time is the time the job was stopped.</p>

## Other responses

- `480` — ThrottlingException
- `481` — AccessDeniedException
- `482` — ValidationException
- `483` — InternalServerException
- `484` — ResourceNotFoundException
- `485` — ConflictException
- `486` — ServiceQuotaExceededException

---

[API](https://skmtc.net/aws/apis/bedrock-agent.md) · [All operations](https://skmtc.net/aws/apis/bedrock-agent/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/aws/bedrock-agent/versions/a3b2356f17da/schema)