DNA Insider
繁中
Back
Coverage· Unknown· Published Sep 10, 2026

Amazon Bedrock Knowledge Bases adds Marengo Embed 3.0 for multimodal search

Amazon Bedrock Knowledge Bases now offers TwelveLabs Marengo Embed 3.0 for natural-language search across video, image, audio, and text content. The AWS walkthrough covers Amazon S3 ingestion, configurable segmentation, semantic queries, and ranked media results; availability is listed in two AWS Regions with charges for storage, retrieval, and model invocation.

Coverage

DNA Brief

Signal Summary

Marengo Embed 3.0 is generally available in Amazon Bedrock Knowledge Bases and jointly encodes video, audio, images, and text into a 512-dimensional vector space. Managed Knowledge Bases handles storage, ingestion, embedding, reranking, and retrieval for MP4 and MOV videos, JPEG and PNG images, and audio tracks. The walkthrough demonstrates the setup with a 10-minute clip from the 2022 FIFA World Cup final.

Why It Matters

The integration moves multimodal indexing and retrieval into a managed Amazon Bedrock workflow, allowing applications to search video, images, and audio with natural-language queries instead of building separate media-search pipelines. The listed two-Region availability and separate storage, retrieval, and model-invocation charges define important deployment and cost constraints for adoption.

Evidence

Start with the primary evidence, then review supporting sources and context.

1 items

Primary Evidence

1
  • OfficialAWS Artificial IntelligenceDocumentOriginal

    Video and image search in Amazon Bedrock Knowledge Base using Marengo 3.0

    Eric Kim

    “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 against your media.”
Back to Live FeedExplore more signals