mxngjxa/lshrs

Locality Sensitive Hashing (LSH) based recommendation system. Integrates with Redis and your own database.

43
/ 100
Emerging

This project helps quickly find items that are similar to each other, like finding similar products in an e-commerce catalog or related articles in a content library. You provide a collection of items, each with a numerical representation (vector embedding), and it stores a fingerprint of each. When you give it a new item's embedding, it quickly returns a list of similar item IDs. This is ideal for anyone managing large datasets where fast similarity search and recommendation are crucial.

Available on PyPI.

Use this if you need to build a recommendation system or similarity search engine for millions of items and require very fast lookups without exhaustive comparisons.

Not ideal if your dataset is very small, you need exact similarity matches, or your similarity metric is not well-suited for approximation.

recommendation-engines similarity-search information-retrieval content-discovery data-indexing
Maintenance 10 / 25
Adoption 5 / 25
Maturity 22 / 25
Community 6 / 25

How are scores calculated?

Stars

13

Forks

1

Language

Python

License

MIT

Last pushed

Feb 20, 2026

Commits (30d)

0

Dependencies

3

Get this data via API

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

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