{
    "info": {
        "author": "Matthijs Douze, Jeff Johnson, Herve Jegou, Lucas Hosseini",
        "author_email": "matthijs@fb.com",
        "bugtrack_url": null,
        "classifiers": [],
        "description": "Faiss is a library for efficient similarity search and clustering of dense\nvectors. It contains algorithms that search in sets of vectors of any size,\nup to ones that possibly do not fit in RAM. It also contains supporting\ncode for evaluation and parameter tuning. Faiss is written in C++ with\ncomplete wrappers for Python/numpy. Some of the most useful algorithms\nare implemented on the GPU. It is developed by Facebook AI Research.",
        "description_content_type": "",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/facebookresearch/faiss",
        "keywords": "search nearest neighbors",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "faiss-centos",
        "package_url": "https://pypi.org/project/faiss-centos/",
        "platform": "",
        "project_url": "https://pypi.org/project/faiss-centos/",
        "project_urls": {
            "Homepage": "https://github.com/facebookresearch/faiss"
        },
        "release_url": "https://pypi.org/project/faiss-centos/1.5.2/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "A library for efficient similarity search and clustering of dense vectors",
        "version": "1.5.2"
    },
    "last_serial": 5422882,
    "releases": {
        "1.5.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "725ba48a0b2750ccc63cf53174c3a029",
                    "sha256": "ab01589e1309daa806a1caa1a3500e6d1aca2bd01086d41a619ffed1d0b9b291"
                },
                "downloads": -1,
                "filename": "faiss_centos-1.5.2-py3.6.egg",
                "has_sig": false,
                "md5_digest": "725ba48a0b2750ccc63cf53174c3a029",
                "packagetype": "bdist_egg",
                "python_version": "3.6",
                "requires_python": null,
                "size": 1576854,
                "upload_time": "2019-06-19T22:23:17",
                "url": "https://files.pythonhosted.org/packages/f6/8b/ab69a201ea1b8be759ba16f172f92d1fb935a8f4a94f02fe52c7d8ec579f/faiss_centos-1.5.2-py3.6.egg"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "725ba48a0b2750ccc63cf53174c3a029",
                "sha256": "ab01589e1309daa806a1caa1a3500e6d1aca2bd01086d41a619ffed1d0b9b291"
            },
            "downloads": -1,
            "filename": "faiss_centos-1.5.2-py3.6.egg",
            "has_sig": false,
            "md5_digest": "725ba48a0b2750ccc63cf53174c3a029",
            "packagetype": "bdist_egg",
            "python_version": "3.6",
            "requires_python": null,
            "size": 1576854,
            "upload_time": "2019-06-19T22:23:17",
            "url": "https://files.pythonhosted.org/packages/f6/8b/ab69a201ea1b8be759ba16f172f92d1fb935a8f4a94f02fe52c7d8ec579f/faiss_centos-1.5.2-py3.6.egg"
        }
    ]
}