rapidsai/cuvs

cuVS - a library for vector search and clustering on the GPU

73
/ 100
Verified

cuVS helps data scientists and machine learning engineers perform ultra-fast similarity searches and clustering on large datasets. It takes high-dimensional numerical data (vectors or embeddings) and quickly finds the most similar items or groups them into clusters. This is crucial for tasks like building recommender systems, performing semantic search, or visualizing complex data patterns.

646 stars. Actively maintained with 74 commits in the last 30 days.

Use this if you need to rapidly find similar data points or group large collections of high-dimensional vectors for applications like semantic search, recommendation engines, or data analysis.

Not ideal if your data is not in a numerical vector format, or if you don't have access to GPU hardware for processing.

semantic-search recommender-systems data-mining machine-learning data-clustering
No Package No Dependents
Maintenance 22 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

646

Forks

164

Language

Cuda

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

74

Get this data via API

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

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