A fast and memory-efficient implementation of Hierarchical Navigable Small World (HNSW) graphs in C for approximate nearest neighbor search.
This project provides a lightweight and high-performance implementation of the HNSW (Hierarchical Navigable Small World) algorithm for approximate nearest neighbor (ANN) search.
HNSW is widely used in vector search, recommendation systems, and similarity search applications due to its excellent trade-off between accuracy and speed.
The HNSW algorithm was introduced by Yury Malkov and Dmitry Yashunin in their paper:
"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs" (2018)
This library is an independent C implementation inspired by their work.
