Amazon Bedrock Knowledge Bases now provides auto-generated query filters for improved retrieval

Posted on: Dec 1, 2024

Amazon Bedrock Knowledge Bases offers fully-managed, end-to-end Retrieval-Augmented Generation (RAG) workflows to create highly accurate, low latency, secure, and custom GenAI applications by incorporating contextual information from your data sources. Today, we are launching automatically-generated query filters which improves retrieval accuracy by ensuring the documents retrieved are relevant to the query. This feature extends the existing capability of manual metadata filtering, by allowing customers to narrow down search results without the need to manually construct complex filter expressions.

RAG applications process user queries by searching across a large set of documents. However, in many situations you may need to retrieve documents with specific attributes and/or content. With automatic generated query filters enabled, you can receive filtered search results which are based on the document’s metadata without the need to manually construct complex filter expressions. For example, for a query like "How to file a claim in Washington", the state as "Washington" will be automatically applied as a filter to retrieve only those documents pertaining to the particular state.

The capability is available in US East (N. Virginia), US West (Oregon), Asia Pacific (Tokyo), Asia Pacific (Seoul), Europe (Frankfurt), Europe (Zurich) and AWS GovCloud (US-West). To learn more, visit the documentation.