Amazon ElastiCache now supports real-time hybrid search with vector and full-text

Amazon Web Services has announced that ElastiCache now supports real-time hybrid search capabilities that combine vector similarity search with full-text search in a single query. The new feature allows applications to merge semantic meaning with exact keyword matching without requiring a separate search service, delivering more relevant results than either search method used independently. ElastiCache can now handle hybrid searches across billions of embeddings from major AI providers including Amazon Bedrock, Amazon SageMaker, Anthropic, and OpenAI, with latency as low as microseconds and up to 99% recall rates. The service makes data searchable immediately upon write completion, ensuring applications always search against the most current vectors and text. Developers can leverage the hybrid search functionality to build AI agent memory systems and Retrieval-Augmented Generation (RAG) implementations that retrieve relevant context through both exact terms and semantic meaning, potentially improving generative AI responses while reducing token costs. E-commerce and streaming platforms can use the technology to surface relevant product matches regardless of whether users search by exact product names or descriptions. The hybrid search feature is now available across all commercial AWS Regions, AWS GovCloud regions, and China Regions for node-based clusters running ElastiCache version 9.0 for Valkey. AWS claims that ElastiCache for Valkey delivers the lowest latency vector search with the highest throughput and best price-performance at 95%+ recall rates among popular vector databases on the AWS platform.