erikbern /ann-benchmarks
Benchmarks of approximate nearest neighbor libraries in Python
★ 5,753⑂ 910👁 115⑃ 391● 250▤ 0
+0
日增长
5,753
stars
910
forks
115
watchers
391
prs
250
issues
0
releases
README
Status of ANN-Benchmarks ======================== At this point, ann-benchmarks is no longer actively maintained. Please consider submitting your work to different benchmarks, such as VIBE. Benchmarking nearest neighbors ============================== Doing fast searching of nearest neighbors in high dimensional spaces is an increasingly important problem with notably few empirical attempts at comparing approaches in an objective way, despite a clear need for such to drive optimization forward. This project contains tools to benchmark various implementations of approximate nearest neighbor (ANN) search for selected metrics. We have pre-generated datasets (in HDF5 format) and prepared Docker containers for each algorithm, as well as a test suite to verify function integrity. Evaluated ========= Annoy !https://img.shields.io/github/stars/spotify/annoy?style=social FLANN !https://img.shields.io/github/stars/flann-lib/flann?style=social scikit-learn: LSHForest, KDTree, BallTree Weaviate !https://img.shields.io/github/stars/weaviate/weaviate?style=social PANNS !https://img.shields.io/github/stars/ryanrhymes/panns?style=social NearPy !https://img.shields.io/github/stars/pixelogik/NearPy?style=social KGraph !https://img.shields.io/github/stars/aaalgo/kgraph?style=social NMSLIB (Non-Metric Space Library) !https://img.shields.io/github/stars/nmslib/nmslib?style=social: SWGraph, HNSW, BallTree, MPLSH hnswlib (a part of nmslib project) !https://img.shields.io/github/stars/nmslib/hnsw?style=social RPForest !https://img.shields.io/github/stars/lyst/rpforest?style=social FAISS !https://img.shields.io/github/stars/facebookresearch/faiss?style=social DolphinnPy !https://img.shields.io/github/stars/ipsarros/DolphinnPy?style=social Datasketch !https://img.shields.io/github/stars/ekzhu/datasketch?style=social nndescent !https://img.shields.io/github/stars/brj0/nndescent?style=social PyNNDescent !https://img.shields.io/github/stars/lmcinnes/pynndescent?style=social MRPT !https://img.shields.io/github/stars/teemupitkanen/mrpt?style=social NGT !https://img.shields.io/github/stars/yahoojapan/NGT?style=social: ONNG, PANNG, QG SPTAG !https://img.shields.io/github/stars/microsoft/SPTAG?style=social PUFFINN !https://img.shields.io/github/stars/puffinn/puffinn?style=social N2 !https://img.shields.io/github/stars/kakao/n2?style=social ScaNN Vearch !https://img.shields.io/github/stars/vearch/vearch?style=social Elasticsearch !https://img.shields.io/github/stars/elastic/elasticsearch?style=social: HNSW Elastiknn !https://img.shields.io/github/stars/alexklibisz/elastiknn?style=social ExpANN !https://img.shields.io/github/stars/jacketsj/expANN?style=social OpenSearch KNN !https://img.shields.io/github/stars/opensearch-project/k-NN?style=social DiskANN !https://img.shields.io/github/stars/microsoft/diskann?style=social: Vamana, Vamana-PQ Vespa !https://img.shields.io/github/stars/vespa-engine/vespa?style=social scipy: cKDTree vald !https://img.
Top issues
#4710X performance difference between multi-thread and single thread tests26 comments · 2017-12-29#209Support 'logit' scale for x-axis20 comments · 2021-01-10#335Algo updates17 comments · 2023-03-08#207knn-graph construction benchmark15 comments · 2020-12-27#523Unable to establish a connection with Milvus without relevant useful information.13 comments · 2024-05-20#377Suggestion: Box Plot Summary Charts12 comments · 2023-04-13#162Benchmarks for binary vectors?11 comments · 2020-05-29#36Which libraries support incremental item additions?9 comments · 2017-10-16