Vespa logo

Vespa

Performs low-latency computation over large data sets, stores and indexes data for efficient queries, selection and processing at serving time.

Made by Vespa

    What is Vespa?

    Vespa is an open-source engine that enables low-latency computation over large data sets. It stores and indexes data to facilitate fast queries, selection, and processing at serving time. Vespa is a comprehensive tool that combines the capabilities of a search engine and a vector database, supporting vector search, lexical search, and structured data search within a single query. Its integrated machine-learning model inference allows users to apply AI to make sense of their data in real-time. Vespa's proven scaling and high availability empower developers to create production-ready search applications at any scale, with a wide range of features

    Highlights

    • Supports vector search (ANN), lexical search, and search in structured data within the same query
    • Integrated machine-learned model inference for applying AI to data in real-time
    • Proven scaling and high availability for building production-ready search applications at any scale
    • Enables the creation of recommendation applications on top of the platform

    Social