GH Repository · vespa-engine
vespa
The AI search platform
- stars
- 7,084
- 30-day movement
- +31/day
- Related entries
- 60
- Connections
- 1
rubyjava/mavenvector-databasevespasearch-enginebig-datatensorserving-recommendationJavaaivectorjavavector-searchserverragmachine-learningsearch
Vespa is a search and serving platform combining full-text search, vector search, and machine learning inference. It is positioned as a backend for AI applications including retrieval-augmented generation, recommendation, and large-scale search serving.
You reach for it when you need one server that handles keyword search, vector retrieval, and ML-based ranking over big data in a single platform.
Use it to
- Build RAG pipelines with vector and text search
- Serve recommendation and ranking workloads
- Run vector database workloads
- Deploy large-scale search applications
- Apply machine-learned ranking over tensors
For Developers building search, recommendation, or RAG backends
- Role
- rag
- Language
- Java
- Licence
- Apache-2.0
- Forks
- 738
- Open issues
- 223
- Last push
- 2026-09-15
- Latest release
- v7.469.18 · 2021-09-22
topicssearch-enginevector-searchvector-databaseragmachine-learningjava