{"library":"hnswlib","type":"library","category":null,"description":"Hnswlib is a lightweight, header-only C++ library with Python bindings designed for fast Approximate Nearest Neighbor (ANN) search. It implements the Hierarchical Navigable Small Worlds (HNSW) algorithm, enabling efficient similarity search in high-dimensional vector spaces. The library supports dynamic updates (insertion and deletion of elements) and various distance metrics like L2, Inner Product, and Cosine similarity. Its current stable release on PyPI is 0.8.0, with version 0.9.0 recently released on GitHub, and it maintains a relatively active release cadence.","language":"python","status":"active","version":"0.8.0","tags":["vector database","similarity search","nearest neighbors","ann","embedding"],"last_verified":"Sat May 23","install":[{"cmd":"pip install hnswlib","imports":["import hnswlib\nimport numpy as np\n\nindex = hnswlib.Index(space='l2', dim=128)"]}],"homepage":null,"github":"https://github.com/yurymalkov/hnsw","docs":null,"changelog":null,"pypi":"https://pypi.org/project/hnswlib/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":0,"avg_install_s":null,"avg_import_s":null,"wheel_type":null},"url":"https://checklist.day/v1/registry/hnswlib/compatibility"}}