Knowledge Bases for Amazon Bedrock now supports advanced RAG capabilities
News
This article announces new advanced capabilities for Knowledge Bases in Amazon Bedrock, Amazon's retrieval-augmented generation (RAG) service. The key new features are:
- Custom chunking: Users can write their own chunking code as a Lambda function to break down long documents for better knowledge retrieval
- Built-in chunking options like semantic and hierarchical chunking
- Smart parsing to extract information from complex data like tables in PDFs
- Query reformulation to break down queries into sub-queries, retrieve relevant information, and combine the results
These new capabilities improve the accuracy and relevance of knowledge retrieval, enabling highly accurate knowledge resources for enterprise use cases.
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
Dec 2
2024
2024
Amazon Bedrock Knowledge Bases now supports RAG evaluation (Preview)
Jul 11
2024
2024
Amazon Bedrock Knowledge Bases now supports advanced parsing, chunking, and query reformulation giving greater control of accuracy in RAG based applications
Jul 10
2024
2024
Knowledge Bases for Amazon Bedrock now supports additional data sources (preview)
Nov 22
2024
2024
Amazon Bedrock Knowledge Bases now supports binary vector embeddings to build RAG applications
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.