Vespa is an open-source AI search platform purpose-built for large-scale retrieval-augmented generation (RAG), semantic search, recommendation, and personalization workloads. The platform combines vector, tensor, text, and structured data in a single distributed engine, supporting hybrid search with real-time ML ranking and approximate nearest-neighbor search at massive scale. Vespa is used in production by organizations including Spotify, Yahoo, Perplexity, and Vinted, and is available as a managed cloud service (Vespa Cloud) as well as open source.