{"id":13436222,"url":"https://github.com/FALCONN-LIB/FALCONN","last_synced_at":"2025-03-18T20:31:03.211Z","repository":{"id":41155680,"uuid":"47301041","full_name":"FALCONN-LIB/FALCONN","owner":"FALCONN-LIB","description":"FAst Lookups of Cosine and Other Nearest Neighbors (based on fast locality-sensitive hashing)","archived":false,"fork":false,"pushed_at":"2024-06-01T14:32:16.000Z","size":5165,"stargazers_count":1150,"open_issues_count":57,"forks_count":194,"subscribers_count":45,"default_branch":"master","last_synced_at":"2025-03-09T22:26:04.000Z","etag":null,"topics":["cosine-similarity","falconn","fast-lookups","locality-sensitive-hashing","lsh","nearest-neighbor-search","sketches"],"latest_commit_sha":null,"homepage":"http://falconn-lib.org/","language":"C","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/FALCONN-LIB.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2015-12-03T02:07:41.000Z","updated_at":"2025-03-06T07:47:20.000Z","dependencies_parsed_at":"2024-09-24T22:02:40.414Z","dependency_job_id":"db46d1db-586b-4923-b337-9b2ac0df5cd4","html_url":"https://github.com/FALCONN-LIB/FALCONN","commit_stats":null,"previous_names":[],"tags_count":6,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FALCONN-LIB%2FFALCONN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FALCONN-LIB%2FFALCONN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FALCONN-LIB%2FFALCONN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FALCONN-LIB%2FFALCONN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FALCONN-LIB","download_url":"https://codeload.github.com/FALCONN-LIB/FALCONN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243945541,"owners_count":20372896,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cosine-similarity","falconn","fast-lookups","locality-sensitive-hashing","lsh","nearest-neighbor-search","sketches"],"created_at":"2024-07-31T03:00:45.625Z","updated_at":"2025-03-18T20:31:03.178Z","avatar_url":"https://github.com/FALCONN-LIB.png","language":"C","readme":"### FALCONN - FAst Lookups of Cosine and Other Nearest Neighbors\n\nFALCONN is a library with algorithms for the nearest neighbor search problem. The algorithms in FALCONN are based on\n[Locality-Sensitive Hashing](https://en.wikipedia.org/wiki/Locality-sensitive_hashing) (LSH), which is a popular class of methods for nearest neighbor search in high-dimensional spaces.\nThe goal of FALCONN is to provide very efficient and well-tested implementations of LSH-based data structures.\n\nCurrently, FALCONN supports two LSH families for the [cosine similarity](https://en.wikipedia.org/wiki/Cosine_similarity): hyperplane LSH and cross polytope LSH.\nBoth hash families are implemented with multi-probe LSH in order to minimize memory usage.\nMoreover, FALCONN is optimized for both dense and sparse data.\nDespite being designed for the cosine similarity, FALCONN can often be used for nearest neighbor search under\nthe Euclidean distance or a maximum inner product search.\n\nFALCONN is written in C++ and consists of several modular core classes with a convenient wrapper around them.\nMany mathematical operations in FALCONN are vectorized through the [Eigen](http://eigen.tuxfamily.org/index.php?title=Main_Page) and [FFHT](https://github.com/FALCONN-LIB/FFHT) libraries.\nThe core classes of FALCONN rely on [templates](https://en.wikipedia.org/wiki/Andrei_Alexandrescu) in order to avoid runtime overhead.\n\n### How to use FALCONN\n\nWe provide a C++ interface for FALCONN as well as a [Python](https://www.python.org/) wrapper (that uses [NumPy](http://www.numpy.org/)). In the future, we plan to support more programming languages such as [Julia](http://julialang.org/). For C++, FALCONN is a header-only library and has no dependencies besides Eigen (which is also header-only),\nso FALCONN is easy to set up. For further details, please see our [documentation](https://github.com/falconn-lib/falconn/wiki).\n\n### How fast is FALCONN?\n\nOn data sets with about 1 million points in around 100 dimensions, FALCONN typically\nrequires a few milliseconds per query (running on a reasonably modern desktop CPU).\n\nFor more detailed results, see [ann-benchmarks](https://github.com/erikbern/ann-benchmarks) of [Erik Bernhardsson](https://erikbern.com/). Let us point out that FALCONN is especially competitive, when\nthe RAM budget is quite restrictive, which is not the regime the above benchmarks use.\n\n### Questions\n\nMaybe your question is already answered in our [Frequently Asked Questions](https://github.com/falconn-lib/falconn/wiki/FAQ).\nIf you have additional questions about using FALCONN, we would be happy to help. Please send an email to falconn.lib@gmail.com.\n\n### Authors\n\nFALCONN is mainly developed by [Ilya Razenshteyn](http://www.ilyaraz.org/) and [Ludwig Schmidt](http://people.csail.mit.edu/ludwigs/).\nFALCONN has grown out of a [research project](http://papers.nips.cc/paper/5893-practical-and-optimal-lsh-for-angular-distance) with our collaborators [Alexandr Andoni](http://www.mit.edu/~andoni/), [Piotr Indyk](https://people.csail.mit.edu/indyk/), and [Thijs Laarhoven](http://thijs.com/).\n\nMany of the ideas used in FALCONN were proposed in research papers over the past 20 years (see the [documentation](https://github.com/FALCONN-LIB/FALCONN/wiki/Bibliography)).\n\nIf you want to cite FALCONN in a publication, here is the bibliographic information of  our research paper [(bibtex)](http://papers.nips.cc/paper/5893-practical-and-optimal-lsh-for-angular-distance/bibtex):\n\n\u003e [Practical and Optimal LSH for Angular Distance](http://papers.nips.cc/paper/5893-practical-and-optimal-lsh-for-angular-distance)\n\u003e Alexandr Andoni, Piotr Indyk, Thijs Laarhoven, Ilya Razenshteyn, Ludwig Schmidt\n\u003e NIPS 2015\n\n### License\n\nFALCONN is available under the [MIT License](https://opensource.org/licenses/MIT) (see LICENSE.txt).\nNote that the third-party libraries in the `external/` folder are distributed under other open source licenses.\nThe Eigen library is licensed under the [MPL2](https://www.mozilla.org/en-US/MPL/2.0/).\nThe googletest and googlemock libraries are licensed under the [BSD 3-Clause License](https://opensource.org/licenses/BSD-3-Clause).\nThe pybind11 library is licensed under a [BSD-style license](https://github.com/pybind/pybind11/blob/master/LICENSE).\n","funding_links":[],"categories":["Uncategorized","Libraries and Tools","向量数据库、向量搜索、最近邻搜索","ANN search"],"sub_categories":["Uncategorized","2023","网络服务_其他"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FFALCONN-LIB%2FFALCONN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FFALCONN-LIB%2FFALCONN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FFALCONN-LIB%2FFALCONN/lists"}