Announcing vector search for Amazon ElastiCache

AWS has announced general availability of vector search for Amazon ElastiCache, enabling efficient indexing and searching of vector embeddings with high performance.

• Supports vector embeddings from providers like Amazon Bedrock, SageMaker, Anthropic, and OpenAI
• Offers microsecond latency with up to 99% recall
• Key use cases include: • Semantic caching for large language models • Multi-turn conversational agents • Retrieval Augmented Generation (RAG) • Recommendation engines • Anomaly detection
• Available with Valkey version 8.2 in all AWS Regions at no additional cost
• Can be implemented via AWS Management Console, SDK, or CLI

The feature enables efficient vector search across multiple data modalities with low latency and high recall.