Sync to ingest your data sources into the knowledge base - Amazon Bedrock

Sync to ingest your data sources into the knowledge base

After you create your knowledge base, you ingest the data sources into the knowledge base so that they're indexed and able to be queried. Ingestion converts the raw data in your data source into vector embeddings. It also associates the raw text and any relevant metadata that you set up for filtering to augment the querying process. Before you begin ingestion, check that your data source fulfills the following conditions:

  • The Amazon S3 bucket for the data source is in the same region as the knowledge base.

  • The files are in supported formats. For more information, see Set up a vector index for your knowledge base in a supported vector store.

  • The files don't exceed the maximum file size of 50 MB. For more information, see Knowledge base quotas.

  • If your data source contains metadata files, check the following conditions to ensure that the metadata files aren't ignored:

    • Each .metadata.json file shares the same name as the source file that it's associated with.

    • If the vector index for your knowledge base is in an Amazon OpenSearch Serverless vector store, check that the vector index is configured with the faiss engine. If the vector index is configured with the nmslib engine, you'll have to do one of the following:

    • If the vector index for your knowledge base is in an Amazon Aurora database cluster, check that the table for your index contains a column for each metadata property in your metadata files before starting ingestion.

Note

Each time you add, modify, or remove files from the S3 bucket for a data source, you must sync the data source so that it is re-indexed to the knowledge base. Syncing is incremental, so Amazon Bedrock only processes the objects in your S3 bucket that have been added, modified, or deleted since the last sync.

To learn how to ingest your data sources into your knowledge base, Select the tab corresponding to your method of choice and follow the steps.

Console
To ingest your data sources

  1. Open the Amazon Bedrock console at https://console.aws.amazon.com/bedrock/.

  2. From the left navigation pane, select Knowledge base and choose your knowledge base.

  3. In the Data source section, select Sync to begin data ingestion.

  4. When data ingestion completes, a green success banner appears if it is successful.

  5. You can choose a data source to view its Sync history. Select View warnings to see why a data ingestion job failed.

API

To ingest a data source into the vector store you configured for your knowledge base, send a StartIngestionJob request with a Agents for Amazon Bedrock build-time endpoint. Specify the knowledgeBaseId and dataSourceId.

Use the ingestionJobId returned in the response in a GetIngestionJob request with a Agents for Amazon Bedrock build-time endpoint to track the status of the ingestion job. In addition, specify the knowledgeBaseId and dataSourceId.

  • When the ingestion job finishes, the status in the response is COMPLETE.

  • The statistics object in the response returns information about whether ingestion was successful or not for documents in the data source.

You can also see information for all ingestion jobs for a data source by sending a ListIngestionJobs request with a Agents for Amazon Bedrock build-time endpoint. Specify the dataSourceId and the knowledgeBaseId of the knowledge base that the data is being ingested to.

  • Filter for results by specifying a status to search for in the filters object.

  • Sort by the time that the job was started or the status of a job by specifying the sortBy object. You can sort in ascending or descending order.

  • Set the maximum number of results to return in a response in the maxResults field. If there are more results than the number you set, the response returns a nextToken that you can send in another ListIngestionJobs request to see the next batch of jobs.