Vespa.ai

Vespa.ai is the developer of Vespa, a platform for applications that leverage AI and data to deliver experiences to end users online in real-time, such as search, recommendation, personalization, and retrieval-augmented generation (RAG). Vespa automatically organizes data, inference, and logic to allow applications to work with any volume of data and concurrent queries. It is available both as a managed service and as open source. Vespa is architected for low latency and scale (>100K queries/second), making it the only practical solution for large systems such as Spotify and Yahoo.