Announcing vector search for Amazon ElastiCache

Vector search for Amazon ElastiCache is now generally available. Customers can now use ElastiCache to index, search, and update billions of high-dimensional vector embeddings from popular providers like Amazon Bedrock, Amazon SageMaker, Anthropic, and OpenAI with latency as low as microseconds and up to 99% recall.

Key use cases include semantic caching for large language models (LLMs) and multi-turn conversational agents, which significantly reduce latency and cost by caching semantically similar queries. Vector search for ElastiCache also powers agentic AI systems with Retrieval Augmented Generation (RAG) to ensure highly relevant results and consistently low latency across multiple retrieval steps. Additional use cases include recommendation engines, anomaly detection, and other applications that require efficient search across multiple data modalities.

Vector search for ElastiCache is available with Valkey version 8.2 on node-based clusters in all AWS Regions at no additional cost. To get started, create a Valkey 8.2 cluster using the AWS Management Console, AWS Software Development Kit (SDK), or AWS Command Line Interface (CLI). You can also use vector search on your existing clusters by upgrading from any version of Valkey or Redis OSS to Valkey 8.2 in a few clicks with no downtime. To learn more about vector search for ElastiCache for Valkey read this blog and for a list of supported commands see the ElastiCache documentation.