ejaasaari/lorann

Approximate Nearest Neighbor search using reduced-rank regression, with extremely fast queries, tiny memory usage, and rapid indexing on modern vector embeddings.

46
/ 100
Emerging

This tool helps machine learning engineers and data scientists quickly find the most similar items within large datasets. You input a collection of high-dimensional numerical data, like image or text embeddings, and it rapidly returns the items most closely matching a specific query. It's designed for users working with modern AI models and large-scale data.

Available on PyPI.

Use this if you need extremely fast nearest neighbor searches on large, high-dimensional embedding datasets, while also minimizing memory usage.

Not ideal if your data is not numerical, low-dimensional, or if your primary concern is perfectly exact matches rather than speed and efficiency.

similarity-search embedding-retrieval data-indexing machine-learning-operations large-scale-data
Maintenance 6 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 7 / 25

How are scores calculated?

Stars

51

Forks

3

Language

C++

License

MIT

Last pushed

Dec 11, 2025

Commits (30d)

0

Dependencies

1

Get this data via API

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

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