SourceAmazon Nova Multimodal Embeddings is now available in AWS GovCloud (US-West)
Amazon Nova Multimodal Embeddings is now generally available in AWS GovCloud (US-West), providing a single model for cross-modal retrieval across text, documents, images, video, and audio.
Why it matters
Government organizations can reduce costs and complexity by replacing multiple specialized search models with one unified tool. This enables more efficient searching across diverse data types, such as financial documents and video archives.
The details
- Supports inputs up to 8K tokens and audio/video segments up to 30 seconds.
- Offers synchronous APIs for real-time use and asynchronous APIs for larger files.
- Allows organizations to adjust embedding dimensions to balance accuracy against storage costs.
Show entities and relationshipsHide entities and relationships
In this article
Key connections
Amazon owns Amazon Nova Multimodal Embeddings
Amazon developed and offers Amazon Nova Multimodal Embeddings.
Amazon owns AWS GovCloud (US-West)
Amazon operates the AWS GovCloud (US-West) cloud region.
Amazon Nova Multimodal Embeddings is related to AWS GovCloud (US-West)
Amazon Nova Multimodal Embeddings is generally available in AWS GovCloud (US-West).
Amazon Nova Multimodal Embeddings is related to Amazon Bedrock
Amazon Nova Multimodal Embeddings can be accessed via the Amazon Bedrock console in AWS GovCloud (US-West).
Amazon Nova Multimodal Embeddings uses Retrieval-Augmented Generation
Amazon Nova Multimodal Embeddings is designed for agentic RAG workflows.
Amazon Nova Multimodal Embeddings uses Semantic Search
Amazon Nova Multimodal Embeddings is designed for semantic search workloads.
Show 1 more connectionsShow fewer connections
Amazon Nova Multimodal Embeddings uses Cross-Modal Retrieval
Amazon Nova Multimodal Embeddings enables cross-modal retrieval across text, documents, images, video, and audio.
Related events
General Availability of Amazon Nova Multimodal Embeddings in AWS GovCloud (US-West)
Get the weekly recap
The stories like this one, picked and explained — once a week, straight to your inbox.