stephantul/reach

Load embeddings and featurize your sentences.

56
/ 100
Established

Provides a lightweight, numpy-backed vector store optimized for RAG systems with sub-millisecond similarity search on 100K+ vectors. Integrates seamlessly with embedding models like model2vec, enabling quick disk serialization for ephemeral retrieval tasks without requiring persistent database infrastructure. Designed for scalability up to ~1M vectors before requiring heavier alternatives.

31 stars and 3,631 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

31

Forks

7

Language

Python

License

MIT

Last pushed

Oct 23, 2024

Monthly downloads

3,631

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/stephantul/reach"

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