Vespa
The AI Search Platform for fast, accurate and large scale RAG
Vespa is an open-source AI search platform that supports vector, text, and structured data search at massive scale. It enables use cases like RAG, personalization, recommendation, and e-commerce navigation by combining hybrid search with distributed machine-learned model inference. The platform is designed to handle billions of data items with sub-100ms query latencies.
Vespa indexes vectors, tensors, text, and structured data and applies distributed machine-learned ranking at query time to deliver highly relevant results at any scale.
engineering teams building large-scale AI search, recommendation, or RAG applications
Background.
- Status
- launched
- Business model
- freemium
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.