Amazon announced the general availability of Amazon Nova Multimodal Embeddings in AWS GovCloud (US-West) for agentic RAG and semantic search.

Key Details

• Amazon Nova Multimodal Embeddings is now generally available in AWS GovCloud (US-West).
• It supports text, documents, images, video, and audio through a single unified embedding model.
• The model supports inputs of up to 8K tokens in length and video or audio segments up to 30 seconds.
• Offers multiple output embedding dimensions and supports both synchronous and asynchronous APIs.
• Users can access Nova Multimodal Embeddings through the Amazon Bedrock console in AWS GovCloud (US-West).

In This Story