To serve AI applications, search, and recommendations over large datasets with real-time model inference and high availability.
Vespa is an open-source platform for serving AI applications, search, and recommendations over large datasets. It enables real-time search, inference, and organization of vectors, tensors, text, and structured data at any scale. Users can build and run the entire engine from this `vespa-engine/vespa` repository or explore a hosted cloud version via `vespa.ai/free-trial`.
To serve AI applications, search, and recommendations over large datasets with real-time model inference and high availability.
It's for developers and organizations building large-scale, real-time AI applications, search engines, or recommendation systems.