AWS Nova Multimodal Embeddings Now Generally Available in GovCloud (US-West)

Amazon Nova Multimodal Embeddings is now generally available in AWS GovCloud (US-West), providing a state-of-the-art solution for agentic RAG and semantic search. This model uniquely unifies text, documents, images, video, and audio into a single embedding space, simplifying cross-modal retrieval and eliminating the need for multiple specialized models. It enables developers to build sophisticated applications that can search diverse content types with leading accuracy. The service supports inputs up to 8K tokens and 30-second video/audio segments, offering multiple output embedding dimensions and both synchronous and asynchronous API options.