ToolsSeptember 10, 2026via AWS Machine Learning Blog
Video and image search in Amazon Bedrock Knowledge Base using Marengo 3.0
Why it matters
A managed embedding service for multimodal content lands in a major cloud platform, lowering the friction for teams building retrieval systems over media. Practitioners can now deploy semantic video/image search without custom infrastructure.
Key signals
- TwelveLabs Marengo Embed 3.0 now GA in Amazon Bedrock Knowledge Bases
- Enables natural language search across video, image, and audio content
- Fully managed service — no custom embedding pipelines required
- Integrated into Bedrock's retrieval-augmented generation (RAG) workflow
- Supports semantic queries against multimodal media at scale
- Supports video, image, and audio content indexing
- Fully managed semantic search across multimodal media
- Published: September 10, 2026
- AWS blog tutorial provided
The hook
Amazon Bedrock now indexes video, images, and audio with semantic search — without building your own pipeline.
TwelveLabs Marengo Embed 3.0 is now generally available as an embedding model in Amazon Bedrock Knowledge Bases, bringing fully managed natural language search to video, image, and audio content. This walkthrough shows how to build a knowledge base powered by Marengo 3.0 and run semantic queries aga…