{"slug": "video-and-image-search-in-amazon-bedrock-knowledge-base-using-marengo-3-0", "title": "Video and image search in Amazon Bedrock Knowledge Base using Marengo 3.0", "summary": "Amazon Web Services announced the general availability of TwelveLabs Marengo Embed 3.0 as an embedding model in Amazon Bedrock Knowledge Bases, enabling natural language search across video, audio, and image content. Marengo Embed 3.0 is a multimodal embedding model that jointly encodes video, audio, images, and text into a 512-dimensional vector space, and Managed Knowledge Bases automatically generates these multimodal embeddings during ingestion. The walkthrough demonstrates the setup using a 10-minute clip of the 2022 FIFA World Cup final, with audio and video segmentation defaulting to 4 seconds.", "body_md": "## [Artificial Intelligence](/blogs/machine-learning/)\n\n# Video and image search in Amazon Bedrock Knowledge Base using Marengo 3.0\n\nToday we’re announcing the general availability of [TwelveLabs Marengo Embed 3.0](https://www.twelvelabs.io/blog/marengo-3-0) as an embedding model in Amazon Bedrock Knowledge Bases.\n\nVideo and media assets remain largely unsearchable by meaning. Teams in media, sports analytics, education, security, and retail need to find specific moments in hours of footage using natural language. An example query is “show me the penalty kick in the second half”. Building semantic search over video today requires stitching together a complex pipeline of transcription services, frame extraction pipelines, embedding models, vector databases, and synchronization logic.\n\nAmazon Bedrock Knowledge Bases is a fully managed Retrieval Augmented Generation (RAG) service that handles storage, ingestion, embedding, re-ranking, and retrieval. It supports video files (MP4, MOV), images (JPEG, PNG), and audio tracks, with native connectors for Amazon Simple Storage Service (Amazon S3), SharePoint, Confluence, and more.\n\nMarengo Embed 3.0 is a multimodal embedding model that jointly encodes video, audio, images, and text into a compact, storage-efficient 512-dimensional vector space.\n\nWith Marengo Embed 3.0 now available as an embedding model option, natural language search through video, audio, and image content becomes a fully managed experience. Managed Knowledge Bases (Managed MKB) automatically generates multimodal embeddings, capturing visual, textual, speech, and audio signals into a unified vector representation.\n\n## Walkthrough\n\nThis walkthrough shows how to create a knowledge base (KB) powered by Marengo 3.0 using the Amazon Bedrock console. The scenario contains a 10-minute clip of the [2022 FIFA World Cup final](https://www.youtube.com/watch?v=RgqKdplLIk4&t=16s).\n\nWe ingest the video and run natural language queries against it.\n\n### Prerequisites\n\n- An active AWS account. If you don’t have one, see [Create an AWS Account](/resources/create-account/) .\n- Access to Amazon Bedrock with TwelveLabs Marengo Embed 3.0 enabled in a supported Region. For details, see [Model access](https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html) in the Amazon Bedrock documentation.\n- An Amazon S3 bucket to store your video and image files.\n- AWS Identity and Access Management (IAM) permissions for Amazon Bedrock and Amazon S3.\n\n### 1. Prepare your media assets\n\nFirst, upload video files to an Amazon S3 bucket. There’s no pre-processing required as Managed MKB handles segmentation, frame sampling, and transcription internally.\n\n### 2. Create a managed knowledge base\n\nIn the Amazon Bedrock console, navigate to **Knowledge Bases** and choose **Create Managed KB**.\n\nExpand the **Additional Configuration** pane and select **Amazon Bedrock embeddings model** for **Embeddings model**. **Amazon Titan Text** is selected by default. Choose the pen icon to edit the model choice.\n\nSelect **TwelveLabs/Marengo Embed 3.0** as shown in the following figure.\n\nNext, expand the **Data source** pane, select **Amazon S3** as **Data source type**, and configure the S3 URI of the bucket containing your video assets.\n\nIn the **Audio/video segmentation configuration** section under **Advanced configurations**, you can configure audio and video segmentation durations. The default is 4 seconds for both modalities.\n\nLeave the advanced parameters unchanged and choose **Create Knowledge Base** at the bottom right of the page.\n\n### 3. Sync and ingest your data\n\nAfter the KB has been created, choose **Sync** to start ingestion. Managed MKB automatically extracts frames, transcribes audio, generates Marengo Embed 3.0 embeddings for each segment, and writes vectors to the index.\n\n### 4. Run a semantic search\n\nYou can test your KB without leaving the console using the **Test** feature. Configure how many source chunks to retrieve, apply metadata filters, and run a query such as “show me the penalty kicks from this soccer match.”\n\nThe response returns ranked results with metadata including chunk start time, chunk end time, source URI, and embedding type, so you can extract the relevant sections as needed.\n\nIn this example, the top results identify moments where penalty kicks were attempted.\n\n### 5. Clean up\n\nTo clean up your resources, complete the following steps:\n\n1. On the Amazon Bedrock console, choose **Knowledge Bases** .\n2. Select your knowledge base and note both the IAM service role name and the Amazon Resource Name (ARN) of the S3 Vector index.\n3. Choose **Delete** and confirm.\n4. On the IAM console, find the role created earlier during knowledge base creation.\n5. Select and delete the role.\n6. On the Amazon S3 console, find your S3 bucket.\n7. Select and delete the files that you uploaded for this tutorial.\n\n## Integrate with your application\n\nYou can use the Amazon Bedrock Retrieve API to power downstream applications. Copy the invocation code from the Details page as a starting point.\n\nThe following architecture shows how multimodal content flows from Amazon S3 through Managed Knowledge Bases with Marengo 3.0 for embedding and indexing. Downstream, applications query the knowledge base through the Boto SDK Retrieve API or as an Amazon Bedrock Gateway target in Amazon Bedrock AgentCore.\n\n## Conclusion\n\nWith the general availability of Marengo 3.0 in Amazon Bedrock Knowledge Bases, you can now unlock the full value of your video, audio, and image assets through natural language search, without building or managing complex infrastructure. Point your data source, sync, and search.\n\nThe business impact spans industries:\n\n- **Sports analytics:** Find specific plays, formations, or player actions across entire seasons of footage.\n- **Media and entertainment:** Media asset management, semantic search through media archive or streaming service content.\n- **Security and safety:** Search security camera footage for specific incidents or activities.\n- **Education and training:** Locate lecture segments by concept, not only keywords.\n- **Retail:** Search product demo videos for feature demonstrations.\n\n### Availability and pricing\n\nManaged Knowledge Bases for Amazon Bedrock with Marengo Embed 3.0 is available in the US East (N. Virginia) AWS Region (us-east-1) and the US West (N. California) Region (us-west-1). For a complete list of supported models and Regions, see [Supported models by AWS Region in Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-regions.html).\n\nWith Managed Knowledge Bases for Amazon Bedrock, you pay only for what you store and retrieve. Embeddings generation with Marengo Embed 3.0 is charged at the standard Amazon [Bedrock model invocation rate](/bedrock/pricing/).\n\nFor more information, see the [pricing documentation page](/bedrock/pricing/?nc1=h_ls).\n\n### Next steps\n\nGet started with fully managed multimodal retrieval:\n\n1. **Explore the documentation** : Review the[Amazon Bedrock Knowledge Bases documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base.html) and[Build a managed knowledge base](https://docs.aws.amazon.com/bedrock/latest/userguide/kb-build-managed.html) for additional technical details.\n2. **Experiment with code examples** : Check out the[Amazon Bedrock samples repository](https://github.com/aws-samples/amazon-bedrock-samples) for hands-on notebooks demonstrating multimodal retrieval.\n3. **Learn more about Marengo Embed 3.0** : Check out[Marengo 3.0 documentation](https://www.twelvelabs.io/blog/marengo-3-0) for deeper technical insights.", "url": "https://wpnews.pro/news/video-and-image-search-in-amazon-bedrock-knowledge-base-using-marengo-3-0", "canonical_source": "https://aws.amazon.com/blogs/machine-learning/video-and-image-search-in-amazon-bedrock-knowledge-base-using-marengo-3-0/", "published_at": "2026-09-10 21:15:39+00:00", "updated_at": "2026-09-10 21:41:57.932207+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-products", "ai-infrastructure", "computer-vision", "natural-language-processing"], "entities": ["Amazon Web Services", "Amazon Bedrock Knowledge Bases", "TwelveLabs", "Marengo Embed 3.0", "Amazon S3", "Amazon Titan Text", "2022 FIFA World Cup"], "alternates": {"html": "https://wpnews.pro/news/video-and-image-search-in-amazon-bedrock-knowledge-base-using-marengo-3-0", "markdown": "https://wpnews.pro/news/video-and-image-search-in-amazon-bedrock-knowledge-base-using-marengo-3-0.md", "text": "https://wpnews.pro/news/video-and-image-search-in-amazon-bedrock-knowledge-base-using-marengo-3-0.txt", "jsonld": "https://wpnews.pro/news/video-and-image-search-in-amazon-bedrock-knowledge-base-using-marengo-3-0.jsonld"}}