Retrieval-Augmented Generation with vector search, document chunking, semantic caching, and metadata filtering - all powered by Valkey.
6 guides from getting started to production monitoring for RAG pipelines
Set up a RAG pipeline with Valkey for document storage and retrieval
Cache RAG responses by meaning to reduce LLM calls and latency
Use FT.CREATE and FT.SEARCH for document retrieval with embeddings
TTL strategies, selective invalidation, and freshness guarantees
ElastiCache deployment, sharding, and high-availability patterns
Track cache hit rates, latency, memory usage, and index health
Interactive RAG pipeline demo - add documents, search by meaning, see caching in action
All cookbooks and demo code for RAG pipelines with Valkey.