- Newest
- Most votes
- Most comments
Hello.
Even if you add a file to the data source, it will not be updated automatically, so you will need to synchronize using the steps in the document below.
Currently, if you want to automate it, you need to use Lambda to periodically run the start_ingestion_job() API, or use an S3 event trigger to configure Lambda to run when a file is uploaded to S3. I think it will be.
Additionally, the synchronization is incremental, so changes from the previous synchronization are incorporated.
https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base-ds-manage.html#kb-ds-update
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. Before you begin ingestion, check that your data source fulfills the following conditions:
Relevant content
- asked 9 months ago
- asked 7 months ago
- asked 9 months ago
- How do I troubleshoot permission errors that I get when I create a knowledge base in Amazon Bedrock?AWS OFFICIALUpdated 5 months ago
- AWS OFFICIALUpdated 3 years ago
- AWS OFFICIALUpdated 7 months ago
- AWS OFFICIALUpdated a year ago
I gave a similar answer regarding automation at this URL, so please check it. https://repost.aws/ja/questions/QUiHaWFYCCQHavhPhLadRr0Q/bedrock-knowledge-base-automate-datasource-synchronize
Agreed with Riku: what he describes is the most efficient way to update your KB when a new file is stored in S3 (or modified or deleted). Lambda Trigger is the way to go.
Thankyou, the answer makes sense, I was curious about this. Thanks again.
Riku That answers the question. Is it possible to simplify the need for Lambda? Bedrock could have a setting to refresh periodically or better yet resync upon any file changes in datastore.
Thoughts?
Cheers Bedrock Learner