Home icon

Amazon Bedrock Knowledge Bases now supports hybrid search for Aurora PostgreSQL and MongoDB Atlas vector stores

News



Amazon Bedrock Knowledge Bases has expanded its hybrid search capabilities to include Aurora PostgreSQL and MongoDB Atlas vector stores, enhancing retrieval augmented generation (RAG) applications.

  • Hybrid search merges semantic and full-text search methods
  • Improves search result relevance by combining conceptual and keyword-based queries
  • Can be enabled through Knowledge Base APIs or Bedrock console
  • Aurora PostgreSQL hybrid search available in most AWS Regions
  • MongoDB Atlas hybrid search limited to US West (Oregon) and US East (N. Virginia) Regions

This feature allows more precise and contextually relevant search results by expanding the search scope across different query methods.



Go to article

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

Mar 1
2024
Amazon Bedrock Knowledge Bases now supports hybrid search
Mar 27
2025
Amazon Bedrock Knowledge Bases now supports Amazon Opensearch Managed Cluster for vector storage
Jul 9
2025
Query Amazon Aurora PostgreSQL using Amazon Bedrock Knowledge Bases structured data
Feb 12
2024
Knowledge Bases for Amazon Bedrock now supports Amazon Aurora PostgreSQL and Cohere embedding models

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.