mantzaris/LMDiskANN.jl

Julia Implementation of Low Memory Disk ANN (LM-DiskANN)

31
/ 100
Emerging

This project helps developers working with large datasets of numerical feature vectors, such as image embeddings or text embeddings. It takes these vectors and builds an efficient index on disk, allowing for quick searches to find the most similar vectors without consuming too much RAM. Data scientists and machine learning engineers can use this to power tasks like recommendation engines or semantic search.

No commits in the last 6 months.

Use this if you need to quickly find similar data points within a very large collection of high-dimensional vectors, and your system has limited memory.

Not ideal if your dataset of vectors is small enough to fit comfortably in memory, as the disk-based operations might introduce unnecessary overhead.

vector search similarity search large-scale data machine learning infrastructure data science tooling
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

Julia

License

MIT

Last pushed

Jun 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/mantzaris/LMDiskANN.jl"

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