rapidsai/cuvs-lucene

A Lucene codec for vector search and clustering on the GPU

46
/ 100
Emerging

This project integrates GPU-accelerated vector search into Apache Lucene. It allows developers building search applications to quickly find similar items based on their numerical representations (vectors), leveraging the power of NVIDIA GPUs. The result is faster and more efficient similarity searches for applications like recommendation engines or semantic search.

Use this if you are a Java developer building search applications with Apache Lucene and need to perform very fast vector similarity searches, especially with large datasets, using NVIDIA GPUs.

Not ideal if you are not working with Apache Lucene, do not have access to NVIDIA GPUs, or are looking for a standalone vector database solution.

search-engine-development information-retrieval vector-search GPU-acceleration Java-development
No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 15 / 25
Community 17 / 25

How are scores calculated?

Stars

7

Forks

11

Language

Java

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/rapidsai/cuvs-lucene"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.