Amazon Bedrock Knowledge Bases now supports hybrid search
Machine Learning Blog
This article discusses the new hybrid search feature in Knowledge Bases for Amazon Bedrock, which combines both keyword-based and semantic vector search. Specifically, the article covers:
- Overview of hybrid search and its benefits for retrieval-augmented generation (RAG) applications
- Use cases for hybrid search, such as open domain question answering, contextual chatbots, and personalized search
- How to use the hybrid search option via the Amazon Bedrock SDK and console
- Examples demonstrating the improved accuracy of responses when using hybrid search compared to semantic search alone
- Conclusion highlighting the advantages of hybrid search for handling diverse queries and content
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 10
2025
2025
Amazon Bedrock Knowledge Bases now supports hybrid search for Aurora PostgreSQL and MongoDB Atlas vector stores
Apr 8
2024
2024
Amazon Bedrock Knowledge Bases now supports metadata filtering to improve retrieval accuracy
Dec 2
2024
2024
Amazon Bedrock Knowledge Bases now provides auto-generated query filters for improved retrieval
Dec 4
2024
2024
Amazon Bedrock Knowledge Bases now supports structured data retrieval
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.