Introducing multimodal retrieval for Amazon Bedrock Knowledge Bases

We are excited to announce the general availability of multimodal retrieval for Amazon Bedrock Knowledge Bases. This new capability adds native support for video and audio content, on top of text and images. With it you can build Retrieval Augmented Generation (RAG) applications that can search and retrieve information across text, images, audio, and video—all within a fully managed service.

Modern enterprises store valuable information in multiple formats. Product documentation includes diagrams and screenshots, training materials contain instructional videos, and customer insights are captured in recorded meetings. Until now, building artificial intelligence (AI) applications that could effectively search across these content types required complex custom infrastructure and significant engineering effort.

Previously, Bedrock Knowledge Bases used text-based embedding models for retrieval. While it supported text documents and images, images had to be processed using foundation models (FM) or Bedrock Data Automation to generate text descriptions—a text-first approach that lost ...