Amazon Bedrock now supports Rerank API to improve accuracy of RAG applications
News
Amazon Bedrock has introduced the Rerank API to enhance Retrieval-Augmented Generation (RAG) applications by improving document relevance and search accuracy.
- Reranker models can prioritize the most relevant documents for a given query
- Helps improve response accuracy in complex or ambiguous search scenarios
- Supported through Retrieve and RetrieveAndGenerate APIs in Knowledge Bases
- Currently supports Amazon Rerank 1.0 and Cohere Rerank 3.5 models
- Available in multiple regions including US West, Canada, Europe, and Asia Pacific
The new feature helps optimize context window usage and potentially reduce costs by ensuring the most relevant information is passed to foundation models for response generation.
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 1
2024
2024
New APIs in Amazon Bedrock to enhance RAG applications, now available
Dec 2
2024
2024
Amazon Bedrock Knowledge Bases now supports RAG evaluation (Preview)
Mar 20
2025
2025
Amazon Bedrock now supports RAG Evaluation (generally available)
Nov 20
2024
2024
Streamline RAG applications with intelligent metadata filtering using Amazon Bedrock
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.