XiangpengHao/pq-vector

Vector search using only Parquet and DataFusion

28
/ 100
Experimental

This tool helps developers perform efficient vector similarity searches on large datasets. It takes a Parquet file containing vector embeddings as input, adds an embedded index to it, and allows for fast retrieval of the most similar vectors to a given query. This is ideal for backend or data engineers building applications that require real-time similarity search.

Use this if you are a Rust developer working with DataFusion and need to implement fast, scalable vector search directly on Parquet files without managing separate index services.

Not ideal if you need a high-level API for vector search and are not comfortable with Rust or DataFusion, or if your vectors are not stored in Parquet files.

vector-search data-engineering backend-development database-indexing
No License No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 3 / 25
Community 7 / 25

How are scores calculated?

Stars

54

Forks

3

Language

Rust

License

Last pushed

Feb 11, 2026

Commits (30d)

0

Get this data via API

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

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