Amazon Bedrock Knowledge Bases now processes multimodal data
News
Amazon Bedrock Knowledge Bases now supports processing multimodal data, enabling developers to build generative AI applications that can analyze both textual and visual information.
- Supports extraction of content from images, charts, diagrams, and tables
- Generates semantic embeddings from multimodal data sources
- Provides source attribution for visual data
- Offers two ways to get started:
- Amazon Bedrock Data Automation (Preview)
- Foundation Models like Claude 3.5 Sonnet
- Available in US West (Oregon) region for preview
This update enhances Retrieval-Augmented Generation (RAG) workflows by allowing more comprehensive data analysis and insight generation across different data types.
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
Jan 20
2026
2026
Introducing multimodal retrieval for Amazon Bedrock Knowledge Bases
Mar 3
2025
2025
Get insights from multimodal content with Amazon Bedrock Data Automation, now generally available
Jul 10
2024
2024
Knowledge Bases for Amazon Bedrock now supports additional data sources (preview)
May 28
2025
2025
Building a multimodal RAG based application using Amazon Bedrock Data Automation and Amazon Bedrock Knowledge Bases
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.