Vector search for Amazon MemoryDB is now generally available

This article announces the general availability of vector search for Amazon MemoryDB, a new capability that enables storing, indexing, retrieving, and searching vectors to develop real-time machine learning (ML) and generative AI applications with in-memory performance and multi-AZ durability.

Specifically, the article covers:

• Use cases that benefit from vector search for MemoryDB, including real-time semantic search for retrieval-augmented generation (RAG), low-latency durable semantic caching, and real-time anomaly (fraud) detection
• Steps to get started with vector search for MemoryDB, such as creating a cluster, generating vector embeddings using Amazon Titan Embeddings model, creating a vector index, and searching the vector space
• New features and improvements available at general availability, including VECTOR_RANGE, SCORE, shared memory for vectors, and performance improvements at high filtering rates
• Availability of vector search for MemoryDB in all regions where MemoryDB is available