GitHub - RyanCodrai/turbovec: A vector index built on TurboQuant, written in Rust with Python bindings
A vector index built on TurboQuant, written in Rust with Python bindings - RyanCodrai/turbovec
Open Source Library
Summary
hnswlib is an open‑source header‑only C++ library with Python bindings that provides fast approximate nearest neighbor search using the HNSW algorithm.
Highlights
- Header‑only C++ core (C++11) with official Python bindings; other languages via community wrappers
- Supports incremental index building, deletions, filtering, custom distance functions and multithreaded queries
- Low memory footprint and fast build times compared to similar libraries such as nmslib
- Python indices are picklable for easy serialization
- Recent updates added multi‑vector document search and epsilon search in C++
auto-generated
Context
Audience
Developers and researchers who need a lightweight, high performance ANN library for C++ or Python projects
DomainApproximate Nearest Neighbor Search
Formatsource code repository on GitHub with documentation and examples
Accessopen source, free to use under the Apache‑2.0 license
Source Overview
Hnswlib is an efficient, header-only C++ library with Python bindings for fast approximate nearest neighbor search using the HNSW algorithm.
It supports incremental index construction, element deletions, custom distance metrics, multi-threaded operation, and filtering, with a significantly lower memory footprint than similar libraries. Recent updates added multi-vector search (C++ only) and more robust management of inserted/deleted elements, while Python indices are picklable and can use L2, inner product, or cosine similarity.
Topics
Related
FAISSAnnoynmslibMilvusVespa
