MinishLab/vicinity

Lightweight Nearest Neighbors with Flexible Backends

52
/ 100
Established

Provides a unified Python API across seven pluggable ANN backends (FAISS, HNSW, Annoy, Usearch, PyNNDescent, Voyager) with configurable distance metrics and index types, eliminating vendor lock-in for vector search. Includes built-in evaluation metrics for benchmarking queries-per-second and recall, plus HuggingFace Hub integration for sharing vector stores alongside metadata like embedding models.

334 stars and 62,743 monthly downloads. Available on PyPI.

Maintenance 6 / 25
Adoption 20 / 25
Maturity 18 / 25
Community 8 / 25

How are scores calculated?

Stars

334

Forks

10

Language

Python

License

MIT

Last pushed

Dec 30, 2025

Monthly downloads

62,743

Commits (30d)

0

Dependencies

3

Get this data via API

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

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