Amazon Bedrock Knowledge Bases now provides auto-generated query filters for improved retrieval
News
Amazon Bedrock Knowledge Bases has launched a new feature of auto-generated query filters for Retrieval-Augmented Generation (RAG) workflows, enhancing document retrieval accuracy.
- Automatically generates filters based on query context without manual filter construction
- Helps narrow search results by applying relevant metadata filters
- Example: A query about filing a claim in Washington will automatically filter for Washington-related documents
- Improves retrieval precision for GenAI applications
- Available in multiple AWS regions including US East, US West, Asia Pacific, Europe, and AWS GovCloud
This feature simplifies complex search filtering and enhances the relevance of retrieved documents in RAG applications.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Apr 8
2024
2024
Amazon Bedrock Knowledge Bases now supports metadata filtering to improve retrieval accuracy
Dec 4
2024
2024
Amazon Bedrock Knowledge Bases now supports structured data retrieval
Jul 10
2024
2024
Knowledge Bases for Amazon Bedrock now supports additional data sources (preview)
Mar 1
2024
2024
Amazon Bedrock Knowledge Bases now supports hybrid search
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.