From 1dfaf80c75afa84b6d03a0013eb1fd94d0257226 Mon Sep 17 00:00:00 2001 From: Gustaf Rydholm Date: Fri, 5 Apr 2024 18:31:12 +0200 Subject: Update from faiss to qdrant --- poetry.lock | 325 ++++++++++++++++++++++++++++++++++++++++++++------- pyproject.toml | 3 +- rag/db/embeddings.py | 52 ++++++--- 3 files changed, 326 insertions(+), 54 deletions(-) diff --git a/poetry.lock b/poetry.lock index f96483b..69d37b1 100644 --- a/poetry.lock +++ b/poetry.lock @@ -612,44 +612,6 @@ files = [ [package.extras] tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich"] -[[package]] -name = "faiss-cpu" -version = "1.8.0" -description = "A library for efficient similarity search and clustering of dense vectors." -optional = false -python-versions = ">=3.8" -files = [ - {file = "faiss-cpu-1.8.0.tar.gz", hash = "sha256:3ee1549491728f37b65267c192a94661a907154a8ae0546ad50a564b8be0d82e"}, - {file = "faiss_cpu-1.8.0-cp310-cp310-macosx_10_14_x86_64.whl", hash = "sha256:134a064c7411acf7d1d863173a9d2605c5a59bd573639ab39a5ded5ca983b1b2"}, - {file = "faiss_cpu-1.8.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ba8e6202d561ac57394c9d691ff17f8fa6eb9a077913a993fce0a154ec0176f1"}, - {file = "faiss_cpu-1.8.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a66e9fa7b70556a39681f06e0652f4124c8ddb0a1924afe4f0e40b6924dc845b"}, - {file = "faiss_cpu-1.8.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:51aaef5a1255d0ea88ea7e52a2415f98c5dd2dd9cec10348d55136541eeec99f"}, - {file = "faiss_cpu-1.8.0-cp310-cp310-win_amd64.whl", hash = "sha256:38152761242870ec7019e0397cbd0ed0b0716562029ce41a71bb38448bd6d5bc"}, - {file = "faiss_cpu-1.8.0-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:c9e6ad94b86626be1a0faff3e53c4ca169eba88aa156d7e90c5a2e9ba30558fb"}, - {file = "faiss_cpu-1.8.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4601dbd81733bf1bc3bff690aac981289fb386dc8e60d0c4eec8a37ba6856d20"}, - {file = "faiss_cpu-1.8.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fa943d3b5e8c5c77cdd629d9c3c6f78d7da616e586fdd1b94aecbf2e5fa9ba06"}, - {file = "faiss_cpu-1.8.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b644b366c3b239b34fa3e08bf65bfc78a24eda1e1ea5b2b6d9be3e8fc73d8179"}, - {file = "faiss_cpu-1.8.0-cp311-cp311-win_amd64.whl", hash = "sha256:f85ecf3514850f93985be238351f5a70736133cfae784b372640aa17c6343a1b"}, - {file = "faiss_cpu-1.8.0-cp312-cp312-macosx_10_14_x86_64.whl", hash = "sha256:61abc0129a357ac00f17f5167f14dff41480de2cc852f306c3d4cd36b893ccbd"}, - {file = "faiss_cpu-1.8.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b788186d6eb94e6333e1aa8bb6c84b66e967458ecdd1cee22e16f04c43ee674c"}, - {file = "faiss_cpu-1.8.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5658d90a202c62e4a69c5b065785e9ddcaf6986cb395c16afed8dbe4c58c31a2"}, - {file = "faiss_cpu-1.8.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d460a372efce547e53d3c47d2c2a8a90b186ad245969048c10c1d7a1e5cf21b"}, - {file = "faiss_cpu-1.8.0-cp312-cp312-win_amd64.whl", hash = "sha256:9e6520324f0a6764dd267b3c32c76958bf2b1ec36752950f6fab31a7295980a0"}, - {file = "faiss_cpu-1.8.0-cp38-cp38-macosx_10_14_x86_64.whl", hash = "sha256:fc44be179d5b7f690484ef0d0caf817fea2698a5275a0c7fb6cbf406e5b2e4d1"}, - {file = "faiss_cpu-1.8.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:bbd6f0bc2e1424a12dc7e19d2cc95b53124867966b21110d26f909227e7ed1f1"}, - {file = "faiss_cpu-1.8.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:06e7add0c8a06ce8fb0443c38fcaf49c45fb74527ea633b819e56452608e64f5"}, - {file = "faiss_cpu-1.8.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b864e23c1817fa6cfe9bbec096fd7140d596002934f71aa89b196ffb1b9cd846"}, - {file = "faiss_cpu-1.8.0-cp38-cp38-win_amd64.whl", hash = "sha256:655433755845adbb6f0961e2f8980703640cb9faa96f1cd1ea190252149e0d0a"}, - {file = "faiss_cpu-1.8.0-cp39-cp39-macosx_10_14_x86_64.whl", hash = "sha256:e81fc376a3bcda213ffb395dda1018c953ce927c587731ad582f4e6c2b225363"}, - {file = "faiss_cpu-1.8.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:8c6fa6b7eaf558307b4ab118a236e8d1da79a8685222928e4dd52e277dba144a"}, - {file = "faiss_cpu-1.8.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:652f6812ef2e8b0f9b18209828c590bc618aca82e7f1c1b1888f52928258e406"}, - {file = "faiss_cpu-1.8.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:304da4e0d19044374b63a5b6467028572eac4bd3f32bc9e8783d800a03fb1f02"}, - {file = "faiss_cpu-1.8.0-cp39-cp39-win_amd64.whl", hash = "sha256:cb475d3f25f08c97ac64dfe026f113e2aeb9829b206b3b046256c3b40dd7eb62"}, -] - -[package.dependencies] -numpy = "*" - [[package]] name = "fastjsonschema" version = "2.19.1" @@ -832,6 +794,140 @@ files = [ docs = ["Sphinx", "furo"] test = ["objgraph", "psutil"] +[[package]] +name = "grpcio" +version = "1.62.1" +description = "HTTP/2-based RPC framework" +optional = false +python-versions = ">=3.7" +files = [ + {file = "grpcio-1.62.1-cp310-cp310-linux_armv7l.whl", hash = "sha256:179bee6f5ed7b5f618844f760b6acf7e910988de77a4f75b95bbfaa8106f3c1e"}, + {file = "grpcio-1.62.1-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:48611e4fa010e823ba2de8fd3f77c1322dd60cb0d180dc6630a7e157b205f7ea"}, + {file = "grpcio-1.62.1-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:b2a0e71b0a2158aa4bce48be9f8f9eb45cbd17c78c7443616d00abbe2a509f6d"}, + {file = "grpcio-1.62.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fbe80577c7880911d3ad65e5ecc997416c98f354efeba2f8d0f9112a67ed65a5"}, + {file = "grpcio-1.62.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:58f6c693d446964e3292425e1d16e21a97a48ba9172f2d0df9d7b640acb99243"}, + {file = "grpcio-1.62.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:77c339403db5a20ef4fed02e4d1a9a3d9866bf9c0afc77a42234677313ea22f3"}, + {file = "grpcio-1.62.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b5a4ea906db7dec694098435d84bf2854fe158eb3cd51e1107e571246d4d1d70"}, + {file = "grpcio-1.62.1-cp310-cp310-win32.whl", hash = "sha256:4187201a53f8561c015bc745b81a1b2d278967b8de35f3399b84b0695e281d5f"}, + {file = "grpcio-1.62.1-cp310-cp310-win_amd64.whl", hash = "sha256:844d1f3fb11bd1ed362d3fdc495d0770cfab75761836193af166fee113421d66"}, + {file = "grpcio-1.62.1-cp311-cp311-linux_armv7l.whl", hash = "sha256:833379943d1728a005e44103f17ecd73d058d37d95783eb8f0b28ddc1f54d7b2"}, + {file = "grpcio-1.62.1-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:c7fcc6a32e7b7b58f5a7d27530669337a5d587d4066060bcb9dee7a8c833dfb7"}, + {file = "grpcio-1.62.1-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:fa7d28eb4d50b7cbe75bb8b45ed0da9a1dc5b219a0af59449676a29c2eed9698"}, + {file = "grpcio-1.62.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:48f7135c3de2f298b833be8b4ae20cafe37091634e91f61f5a7eb3d61ec6f660"}, + {file = "grpcio-1.62.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:71f11fd63365ade276c9d4a7b7df5c136f9030e3457107e1791b3737a9b9ed6a"}, + {file = "grpcio-1.62.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:4b49fd8fe9f9ac23b78437da94c54aa7e9996fbb220bac024a67469ce5d0825f"}, + {file = "grpcio-1.62.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:482ae2ae78679ba9ed5752099b32e5fe580443b4f798e1b71df412abf43375db"}, + {file = "grpcio-1.62.1-cp311-cp311-win32.whl", hash = "sha256:1faa02530b6c7426404372515fe5ddf66e199c2ee613f88f025c6f3bd816450c"}, + {file = "grpcio-1.62.1-cp311-cp311-win_amd64.whl", hash = "sha256:5bd90b8c395f39bc82a5fb32a0173e220e3f401ff697840f4003e15b96d1befc"}, + {file = "grpcio-1.62.1-cp312-cp312-linux_armv7l.whl", hash = "sha256:b134d5d71b4e0837fff574c00e49176051a1c532d26c052a1e43231f252d813b"}, + {file = "grpcio-1.62.1-cp312-cp312-macosx_10_10_universal2.whl", hash = "sha256:d1f6c96573dc09d50dbcbd91dbf71d5cf97640c9427c32584010fbbd4c0e0037"}, + {file = "grpcio-1.62.1-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:359f821d4578f80f41909b9ee9b76fb249a21035a061a327f91c953493782c31"}, + {file = "grpcio-1.62.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a485f0c2010c696be269184bdb5ae72781344cb4e60db976c59d84dd6354fac9"}, + {file = "grpcio-1.62.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b50b09b4dc01767163d67e1532f948264167cd27f49e9377e3556c3cba1268e1"}, + {file = "grpcio-1.62.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:3227c667dccbe38f2c4d943238b887bac588d97c104815aecc62d2fd976e014b"}, + {file = "grpcio-1.62.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:3952b581eb121324853ce2b191dae08badb75cd493cb4e0243368aa9e61cfd41"}, + {file = "grpcio-1.62.1-cp312-cp312-win32.whl", hash = "sha256:83a17b303425104d6329c10eb34bba186ffa67161e63fa6cdae7776ff76df73f"}, + {file = "grpcio-1.62.1-cp312-cp312-win_amd64.whl", hash = "sha256:6696ffe440333a19d8d128e88d440f91fb92c75a80ce4b44d55800e656a3ef1d"}, + {file = "grpcio-1.62.1-cp37-cp37m-linux_armv7l.whl", hash = "sha256:e3393b0823f938253370ebef033c9fd23d27f3eae8eb9a8f6264900c7ea3fb5a"}, + {file = "grpcio-1.62.1-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:83e7ccb85a74beaeae2634f10eb858a0ed1a63081172649ff4261f929bacfd22"}, + {file = "grpcio-1.62.1-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:882020c87999d54667a284c7ddf065b359bd00251fcd70279ac486776dbf84ec"}, + {file = "grpcio-1.62.1-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a10383035e864f386fe096fed5c47d27a2bf7173c56a6e26cffaaa5a361addb1"}, + {file = "grpcio-1.62.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:960edebedc6b9ada1ef58e1c71156f28689978188cd8cff3b646b57288a927d9"}, + {file = "grpcio-1.62.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:23e2e04b83f347d0aadde0c9b616f4726c3d76db04b438fd3904b289a725267f"}, + {file = "grpcio-1.62.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:978121758711916d34fe57c1f75b79cdfc73952f1481bb9583399331682d36f7"}, + {file = "grpcio-1.62.1-cp37-cp37m-win_amd64.whl", hash = "sha256:9084086190cc6d628f282e5615f987288b95457292e969b9205e45b442276407"}, + {file = "grpcio-1.62.1-cp38-cp38-linux_armv7l.whl", hash = "sha256:22bccdd7b23c420a27fd28540fb5dcbc97dc6be105f7698cb0e7d7a420d0e362"}, + {file = "grpcio-1.62.1-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:8999bf1b57172dbc7c3e4bb3c732658e918f5c333b2942243f10d0d653953ba9"}, + {file = "grpcio-1.62.1-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:d9e52558b8b8c2f4ac05ac86344a7417ccdd2b460a59616de49eb6933b07a0bd"}, + {file = "grpcio-1.62.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1714e7bc935780bc3de1b3fcbc7674209adf5208ff825799d579ffd6cd0bd505"}, + {file = "grpcio-1.62.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c8842ccbd8c0e253c1f189088228f9b433f7a93b7196b9e5b6f87dba393f5d5d"}, + {file = "grpcio-1.62.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:1f1e7b36bdff50103af95a80923bf1853f6823dd62f2d2a2524b66ed74103e49"}, + {file = "grpcio-1.62.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:bba97b8e8883a8038606480d6b6772289f4c907f6ba780fa1f7b7da7dfd76f06"}, + {file = "grpcio-1.62.1-cp38-cp38-win32.whl", hash = "sha256:a7f615270fe534548112a74e790cd9d4f5509d744dd718cd442bf016626c22e4"}, + {file = "grpcio-1.62.1-cp38-cp38-win_amd64.whl", hash = "sha256:e6c8c8693df718c5ecbc7babb12c69a4e3677fd11de8886f05ab22d4e6b1c43b"}, + {file = "grpcio-1.62.1-cp39-cp39-linux_armv7l.whl", hash = "sha256:73db2dc1b201d20ab7083e7041946910bb991e7e9761a0394bbc3c2632326483"}, + {file = "grpcio-1.62.1-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:407b26b7f7bbd4f4751dbc9767a1f0716f9fe72d3d7e96bb3ccfc4aace07c8de"}, + {file = "grpcio-1.62.1-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:f8de7c8cef9261a2d0a62edf2ccea3d741a523c6b8a6477a340a1f2e417658de"}, + {file = "grpcio-1.62.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9bd5c8a1af40ec305d001c60236308a67e25419003e9bb3ebfab5695a8d0b369"}, + {file = "grpcio-1.62.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:be0477cb31da67846a33b1a75c611f88bfbcd427fe17701b6317aefceee1b96f"}, + {file = "grpcio-1.62.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:60dcd824df166ba266ee0cfaf35a31406cd16ef602b49f5d4dfb21f014b0dedd"}, + {file = "grpcio-1.62.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:973c49086cabab773525f6077f95e5a993bfc03ba8fc32e32f2c279497780585"}, + {file = "grpcio-1.62.1-cp39-cp39-win32.whl", hash = "sha256:12859468e8918d3bd243d213cd6fd6ab07208195dc140763c00dfe901ce1e1b4"}, + {file = "grpcio-1.62.1-cp39-cp39-win_amd64.whl", hash = "sha256:b7209117bbeebdfa5d898205cc55153a51285757902dd73c47de498ad4d11332"}, + {file = "grpcio-1.62.1.tar.gz", hash = "sha256:6c455e008fa86d9e9a9d85bb76da4277c0d7d9668a3bfa70dbe86e9f3c759947"}, +] + +[package.extras] +protobuf = ["grpcio-tools (>=1.62.1)"] + +[[package]] +name = "grpcio-tools" +version = "1.62.1" +description = "Protobuf code generator for gRPC" +optional = false +python-versions = ">=3.7" +files = [ + {file = "grpcio-tools-1.62.1.tar.gz", hash = "sha256:a4991e5ee8a97ab791296d3bf7e8700b1445635cc1828cc98df945ca1802d7f2"}, + {file = "grpcio_tools-1.62.1-cp310-cp310-linux_armv7l.whl", hash = "sha256:f2b404bcae7e2ef9b0b9803b2a95119eb7507e6dc80ea4a64a78be052c30cebc"}, + {file = "grpcio_tools-1.62.1-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:fdd987a580b4474769adfd40144486f54bcc73838d5ec5d3647a17883ea78e76"}, + {file = "grpcio_tools-1.62.1-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:07af1a6442e2313cff22af93c2c4dd37ae32b5239b38e0d99e2cbf93de65429f"}, + {file = "grpcio_tools-1.62.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:41384c9ee18e61ef20cad2774ef71bd8854b63efce263b5177aa06fccb84df1f"}, + {file = "grpcio_tools-1.62.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5c38006f7702d2ff52122e4c77a47348709374050c76216e84b30a9f06e45afa"}, + {file = "grpcio_tools-1.62.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:08fecc3c5b4e6dd3278f2b9d12837e423c7dcff551ca1e587018b4a0fc5f8019"}, + {file = "grpcio_tools-1.62.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a01e8dcd0f041f6fa6d815c54a2017d032950e310c41d514a8bc041e872c4d12"}, + {file = "grpcio_tools-1.62.1-cp310-cp310-win32.whl", hash = "sha256:dd933b8e0b3c13fe3543d58f849a6a5e0d7987688cb6801834278378c724f695"}, + {file = "grpcio_tools-1.62.1-cp310-cp310-win_amd64.whl", hash = "sha256:2b04844a9382f1bde4b4174e476e654ab3976168d2469cb4b29e352f4f35a5aa"}, + {file = "grpcio_tools-1.62.1-cp311-cp311-linux_armv7l.whl", hash = "sha256:024380536ba71a96cdf736f0954f6ad03f5da609c09edbcc2ca02fdd639e0eed"}, + {file = "grpcio_tools-1.62.1-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:21f14b99e0cd38ad56754cc0b62b2bf3cf75f9f7fc40647da54669e0da0726fe"}, + {file = "grpcio_tools-1.62.1-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:975ac5fb482c23f3608c16e06a43c8bab4d79c2e2564cdbc25cf753c6e998775"}, + {file = "grpcio_tools-1.62.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:50739aaab0c8076ad5957204e71f2e0c9876e11fd8338f7f09de12c2d75163c5"}, + {file = "grpcio_tools-1.62.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:598c54318f0326cf5020aa43fc95a15e933aba4a71943d3bff2677d2d21ddfa1"}, + {file = "grpcio_tools-1.62.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:f309bdb33a61f8e049480d41498ee2e525cfb5e959958b326abfdf552bf9b9cb"}, + {file = "grpcio_tools-1.62.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:f358effd3c11d66c150e0227f983d54a5cd30e14038566dadcf25f9f6844e6e8"}, + {file = "grpcio_tools-1.62.1-cp311-cp311-win32.whl", hash = "sha256:b76aead9b73f1650a091870fe4e9ed15ac4d8ed136f962042367255199c23594"}, + {file = "grpcio_tools-1.62.1-cp311-cp311-win_amd64.whl", hash = "sha256:d66a5d47eaa427039752fa0a83a425ff2a487b6a0ac30556fd3be2f3a27a0130"}, + {file = "grpcio_tools-1.62.1-cp312-cp312-linux_armv7l.whl", hash = "sha256:575535d039b97d63e6a9abee626d6c7cd47bd8cb73dd00a5c84a98254a2164a4"}, + {file = "grpcio_tools-1.62.1-cp312-cp312-macosx_10_10_universal2.whl", hash = "sha256:22644c90e43d1a888477899af917979e17364fdd6e9bbb92679cd6a54c4d36c3"}, + {file = "grpcio_tools-1.62.1-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:156d3e1b227c16e903003a56881dbe60e40f2b4bd66f0bc3b27c53e466e6384d"}, + {file = "grpcio_tools-1.62.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5ad7c5691625a85327e5b683443baf73ae790fd5afc938252041ed5cd665e377"}, + {file = "grpcio_tools-1.62.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0e140bbc08eea8abf51c0274f45fb1e8350220e64758998d7f3c7f985a0b2496"}, + {file = "grpcio_tools-1.62.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:7444fcab861911525470d398e5638b70d5cbea3b4674a3de92b5c58c5c515d4d"}, + {file = "grpcio_tools-1.62.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e643cd14a5d1e59865cba68a5a6f0175d987f36c5f4cb0db80dee9ed60b4c174"}, + {file = "grpcio_tools-1.62.1-cp312-cp312-win32.whl", hash = "sha256:1344a773d2caa9bb7fbea7e879b84f33740c808c34a5bd2a2768e526117a6b44"}, + {file = "grpcio_tools-1.62.1-cp312-cp312-win_amd64.whl", hash = "sha256:2eea1db3748b2f37b4dce84d8e0c15d9bc811094807cabafe7b0ea47f424dfd5"}, + {file = "grpcio_tools-1.62.1-cp37-cp37m-linux_armv7l.whl", hash = "sha256:45d2e6cf04d27286b6f73e6e20ba3f0a1f6d8f5535e5dcb1356200419bb457f4"}, + {file = "grpcio_tools-1.62.1-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:46ae58e6926773e7315e9005f0f17aacedbc0895a8752bec087d24efa2f1fb21"}, + {file = "grpcio_tools-1.62.1-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:4c28086df31478023a36f45e50767872ab3aed2419afff09814cb61c88b77db4"}, + {file = "grpcio_tools-1.62.1-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a4fba5b339f4797548591036c9481e6895bf920fab7d3dc664d2697f8fb7c0bf"}, + {file = "grpcio_tools-1.62.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:23eb3d47f78f509fcd201749b1f1e44b76f447913f7fbb3b8bae20f109086295"}, + {file = "grpcio_tools-1.62.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:fd5d47707bd6bc2b707ece765c362d2a1d2e8f6cd92b04c99fab49a929f3610c"}, + {file = "grpcio_tools-1.62.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:d1924a6a943df7c73b9ef0048302327c75962b567451479710da729ead241228"}, + {file = "grpcio_tools-1.62.1-cp37-cp37m-win_amd64.whl", hash = "sha256:fe71ca30aabe42591e84ecb9694c0297dc699cc20c5b24d2cb267fb0fc01f947"}, + {file = "grpcio_tools-1.62.1-cp38-cp38-linux_armv7l.whl", hash = "sha256:1819fd055c1ae672d1d725ec75eefd1f700c18acba0ed9332202be31d69c401d"}, + {file = "grpcio_tools-1.62.1-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:5dbe1f7481dd14b6d477b4bace96d275090bc7636b9883975a08b802c94e7b78"}, + {file = "grpcio_tools-1.62.1-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:771c051c5ece27ad03e4f2e33624a925f0ad636c01757ab7dbb04a37964af4ba"}, + {file = "grpcio_tools-1.62.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:98209c438b38b6f1276dbc27b1c04e346a75bfaafe72a25a548f2dc5ce71d226"}, + {file = "grpcio_tools-1.62.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2152308e5321cb90fb45aaa84d03d6dedb19735a8779aaf36c624f97b831842d"}, + {file = "grpcio_tools-1.62.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:ed1f27dc2b2262c8b8d9036276619c1bb18791311c16ccbf1f31b660f2aad7cf"}, + {file = "grpcio_tools-1.62.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:2744947b6c5e907af21133431809ccca535a037356864e32c122efed8cb9de1f"}, + {file = "grpcio_tools-1.62.1-cp38-cp38-win32.whl", hash = "sha256:13b20e269d14ad629ff9a2c9a2450f3dbb119d5948de63b27ffe624fa7aea85a"}, + {file = "grpcio_tools-1.62.1-cp38-cp38-win_amd64.whl", hash = "sha256:999823758e9eacd0095863d06cd6d388be769f80c9abb65cdb11c4f2cfce3fea"}, + {file = "grpcio_tools-1.62.1-cp39-cp39-linux_armv7l.whl", hash = "sha256:941f8a5c31986053e75fa466bcfa743c2bf1b513b7978cf1f4ab4e96a8219d27"}, + {file = "grpcio_tools-1.62.1-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:b9c02c88c77ef6057c6cbeea8922d7c2424aabf46bfc40ddf42a32765ba91061"}, + {file = "grpcio_tools-1.62.1-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:6abd4eb3ccb444383a40156139acc3aaa73745d395139cb6bc8e2a3429e1e627"}, + {file = "grpcio_tools-1.62.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:449503213d142f8470b331a1c2f346f8457f16c7fe20f531bc2500e271f7c14c"}, + {file = "grpcio_tools-1.62.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9a11bcf609d00cfc9baed77ab308223cabc1f0b22a05774a26dd4c94c0c80f1f"}, + {file = "grpcio_tools-1.62.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:5d7bdea33354b55acf40bb4dd3ba7324d6f1ef6b4a1a4da0807591f8c7e87b9a"}, + {file = "grpcio_tools-1.62.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d03b645852d605f43003020e78fe6d573cae6ee6b944193e36b8b317e7549a20"}, + {file = "grpcio_tools-1.62.1-cp39-cp39-win32.whl", hash = "sha256:52b185dfc3bf32e70929310367dbc66185afba60492a6a75a9b1141d407e160c"}, + {file = "grpcio_tools-1.62.1-cp39-cp39-win_amd64.whl", hash = "sha256:63a273b70896d3640b7a883eb4a080c3c263d91662d870a2e9c84b7bbd978e7b"}, +] + +[package.dependencies] +grpcio = ">=1.62.1" +protobuf = ">=4.21.6,<5.0dev" +setuptools = "*" + [[package]] name = "h11" version = "0.14.0" @@ -843,6 +939,32 @@ files = [ {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"}, ] +[[package]] +name = "h2" +version = "4.1.0" +description = "HTTP/2 State-Machine based protocol implementation" +optional = false +python-versions = ">=3.6.1" +files = [ + {file = "h2-4.1.0-py3-none-any.whl", hash = "sha256:03a46bcf682256c95b5fd9e9a99c1323584c3eec6440d379b9903d709476bc6d"}, + {file = "h2-4.1.0.tar.gz", hash = "sha256:a83aca08fbe7aacb79fec788c9c0bac936343560ed9ec18b82a13a12c28d2abb"}, +] + +[package.dependencies] +hpack = ">=4.0,<5" +hyperframe = ">=6.0,<7" + +[[package]] +name = "hpack" +version = "4.0.0" +description = "Pure-Python HPACK header compression" +optional = false +python-versions = ">=3.6.1" +files = [ + {file = "hpack-4.0.0-py3-none-any.whl", hash = "sha256:84a076fad3dc9a9f8063ccb8041ef100867b1878b25ef0ee63847a5d53818a6c"}, + {file = "hpack-4.0.0.tar.gz", hash = "sha256:fc41de0c63e687ebffde81187a948221294896f6bdc0ae2312708df339430095"}, +] + [[package]] name = "httpcore" version = "1.0.5" @@ -878,6 +1000,7 @@ files = [ [package.dependencies] anyio = "*" certifi = "*" +h2 = {version = ">=3,<5", optional = true, markers = "extra == \"http2\""} httpcore = "==1.*" idna = "*" sniffio = "*" @@ -888,6 +1011,17 @@ cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"] http2 = ["h2 (>=3,<5)"] socks = ["socksio (==1.*)"] +[[package]] +name = "hyperframe" +version = "6.0.1" +description = "HTTP/2 framing layer for Python" +optional = false +python-versions = ">=3.6.1" +files = [ + {file = "hyperframe-6.0.1-py3-none-any.whl", hash = "sha256:0ec6bafd80d8ad2195c4f03aacba3a8265e57bc4cff261e802bf39970ed02a15"}, + {file = "hyperframe-6.0.1.tar.gz", hash = "sha256:ae510046231dc8e9ecb1a6586f63d2347bf4c8905914aa84ba585ae85f28a914"}, +] + [[package]] name = "idna" version = "3.6" @@ -1436,6 +1570,24 @@ orjson = ">=3.9.14,<4.0.0" pydantic = ">=1,<3" requests = ">=2,<3" +[[package]] +name = "loguru" +version = "0.7.2" +description = "Python logging made (stupidly) simple" +optional = false +python-versions = ">=3.5" +files = [ + {file = "loguru-0.7.2-py3-none-any.whl", hash = "sha256:003d71e3d3ed35f0f8984898359d65b79e5b21943f78af86aa5491210429b8eb"}, + {file = "loguru-0.7.2.tar.gz", hash = "sha256:e671a53522515f34fd406340ee968cb9ecafbc4b36c679da03c18fd8d0bd51ac"}, +] + +[package.dependencies] +colorama = {version = ">=0.3.4", markers = "sys_platform == \"win32\""} +win32-setctime = {version = ">=1.0.0", markers = "sys_platform == \"win32\""} + +[package.extras] +dev = ["Sphinx (==7.2.5)", "colorama (==0.4.5)", "colorama (==0.4.6)", "exceptiongroup (==1.1.3)", "freezegun (==1.1.0)", "freezegun (==1.2.2)", "mypy (==v0.910)", "mypy (==v0.971)", "mypy (==v1.4.1)", "mypy (==v1.5.1)", "pre-commit (==3.4.0)", "pytest (==6.1.2)", "pytest (==7.4.0)", "pytest-cov (==2.12.1)", "pytest-cov (==4.1.0)", "pytest-mypy-plugins (==1.9.3)", "pytest-mypy-plugins (==3.0.0)", "sphinx-autobuild (==2021.3.14)", "sphinx-rtd-theme (==1.3.0)", "tox (==3.27.1)", "tox (==4.11.0)"] + [[package]] name = "markupsafe" version = "2.1.5" @@ -1963,6 +2115,25 @@ files = [ docs = ["furo (>=2023.9.10)", "proselint (>=0.13)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.25.2)"] test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)"] +[[package]] +name = "portalocker" +version = "2.8.2" +description = "Wraps the portalocker recipe for easy usage" +optional = false +python-versions = ">=3.8" +files = [ + {file = "portalocker-2.8.2-py3-none-any.whl", hash = "sha256:cfb86acc09b9aa7c3b43594e19be1345b9d16af3feb08bf92f23d4dce513a28e"}, + {file = "portalocker-2.8.2.tar.gz", hash = "sha256:2b035aa7828e46c58e9b31390ee1f169b98e1066ab10b9a6a861fe7e25ee4f33"}, +] + +[package.dependencies] +pywin32 = {version = ">=226", markers = "platform_system == \"Windows\""} + +[package.extras] +docs = ["sphinx (>=1.7.1)"] +redis = ["redis"] +tests = ["pytest (>=5.4.1)", "pytest-cov (>=2.8.1)", "pytest-mypy (>=0.8.0)", "pytest-timeout (>=2.1.0)", "redis", "sphinx (>=6.0.0)", "types-redis"] + [[package]] name = "prometheus-client" version = "0.20.0" @@ -1991,6 +2162,26 @@ files = [ [package.dependencies] wcwidth = "*" +[[package]] +name = "protobuf" +version = "4.25.3" +description = "" +optional = false +python-versions = ">=3.8" +files = [ + {file = "protobuf-4.25.3-cp310-abi3-win32.whl", hash = "sha256:d4198877797a83cbfe9bffa3803602bbe1625dc30d8a097365dbc762e5790faa"}, + {file = "protobuf-4.25.3-cp310-abi3-win_amd64.whl", hash = "sha256:209ba4cc916bab46f64e56b85b090607a676f66b473e6b762e6f1d9d591eb2e8"}, + {file = "protobuf-4.25.3-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:f1279ab38ecbfae7e456a108c5c0681e4956d5b1090027c1de0f934dfdb4b35c"}, + {file = "protobuf-4.25.3-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:e7cb0ae90dd83727f0c0718634ed56837bfeeee29a5f82a7514c03ee1364c019"}, + {file = "protobuf-4.25.3-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:7c8daa26095f82482307bc717364e7c13f4f1c99659be82890dcfc215194554d"}, + {file = "protobuf-4.25.3-cp38-cp38-win32.whl", hash = "sha256:f4f118245c4a087776e0a8408be33cf09f6c547442c00395fbfb116fac2f8ac2"}, + {file = "protobuf-4.25.3-cp38-cp38-win_amd64.whl", hash = "sha256:c053062984e61144385022e53678fbded7aea14ebb3e0305ae3592fb219ccfa4"}, + {file = "protobuf-4.25.3-cp39-cp39-win32.whl", hash = "sha256:19b270aeaa0099f16d3ca02628546b8baefe2955bbe23224aaf856134eccf1e4"}, + {file = "protobuf-4.25.3-cp39-cp39-win_amd64.whl", hash = "sha256:e3c97a1555fd6388f857770ff8b9703083de6bf1f9274a002a332d65fbb56c8c"}, + {file = "protobuf-4.25.3-py3-none-any.whl", hash = "sha256:f0700d54bcf45424477e46a9f0944155b46fb0639d69728739c0e47bab83f2b9"}, + {file = "protobuf-4.25.3.tar.gz", hash = "sha256:25b5d0b42fd000320bd7830b349e3b696435f3b329810427a6bcce6a5492cc5c"}, +] + [[package]] name = "psutil" version = "5.9.8" @@ -2462,6 +2653,32 @@ files = [ [package.dependencies] cffi = {version = "*", markers = "implementation_name == \"pypy\""} +[[package]] +name = "qdrant-client" +version = "1.8.2" +description = "Client library for the Qdrant vector search engine" +optional = false +python-versions = ">=3.8" +files = [ + {file = "qdrant_client-1.8.2-py3-none-any.whl", hash = "sha256:ee5341c0486d09e4346b0f5ef7781436e6d8cdbf1d5ecddfde7adb3647d353a8"}, + {file = "qdrant_client-1.8.2.tar.gz", hash = "sha256:65078d5328bc0393f42a46a31cd319a989b8285bf3958360acf1dffffdf4cc4e"}, +] + +[package.dependencies] +grpcio = ">=1.41.0" +grpcio-tools = ">=1.41.0" +httpx = {version = ">=0.20.0", extras = ["http2"]} +numpy = [ + {version = ">=1.21", markers = "python_version >= \"3.8\" and python_version < \"3.12\""}, + {version = ">=1.26", markers = "python_version >= \"3.12\""}, +] +portalocker = ">=2.7.0,<3.0.0" +pydantic = ">=1.10.8" +urllib3 = ">=1.26.14,<3" + +[package.extras] +fastembed = ["fastembed (==0.2.5)"] + [[package]] name = "referencing" version = "0.34.0" @@ -2647,6 +2864,22 @@ nativelib = ["pyobjc-framework-Cocoa", "pywin32"] objc = ["pyobjc-framework-Cocoa"] win32 = ["pywin32"] +[[package]] +name = "setuptools" +version = "69.2.0" +description = "Easily download, build, install, upgrade, and uninstall Python packages" +optional = false +python-versions = ">=3.8" +files = [ + {file = "setuptools-69.2.0-py3-none-any.whl", hash = "sha256:c21c49fb1042386df081cb5d86759792ab89efca84cf114889191cd09aacc80c"}, + {file = "setuptools-69.2.0.tar.gz", hash = "sha256:0ff4183f8f42cd8fa3acea16c45205521a4ef28f73c6391d8a25e92893134f2e"}, +] + +[package.extras] +docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "rst.linker (>=1.9)", "sphinx (<7.2.5)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier"] +testing = ["build[virtualenv]", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.9)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "mypy (==1.9)", "packaging (>=23.2)", "pip (>=19.1)", "pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy (>=0.9.1)", "pytest-perf", "pytest-ruff (>=0.2.1)", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"] +testing-integration = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "packaging (>=23.2)", "pytest", "pytest-enabler", "pytest-xdist", "tomli", "virtualenv (>=13.0.0)", "wheel"] + [[package]] name = "six" version = "1.16.0" @@ -3006,6 +3239,20 @@ docs = ["Sphinx (>=6.0)", "sphinx-rtd-theme (>=1.1.0)"] optional = ["python-socks", "wsaccel"] test = ["websockets"] +[[package]] +name = "win32-setctime" +version = "1.1.0" +description = "A small Python utility to set file creation time on Windows" +optional = false +python-versions = ">=3.5" +files = [ + {file = "win32_setctime-1.1.0-py3-none-any.whl", hash = "sha256:231db239e959c2fe7eb1d7dc129f11172354f98361c4fa2d6d2d7e278baa8aad"}, + {file = "win32_setctime-1.1.0.tar.gz", hash = "sha256:15cf5750465118d6929ae4de4eb46e8edae9a5634350c01ba582df868e932cb2"}, +] + +[package.extras] +dev = ["black (>=19.3b0)", "pytest (>=4.6.2)"] + [[package]] name = "yarl" version = "1.9.4" @@ -3112,4 +3359,4 @@ multidict = ">=4.0" [metadata] lock-version = "2.0" python-versions = "^3.11" -content-hash = "57c1306fe831e05a335b1316d25d3c58a81eb02d82f1fc63a0ba0e078171d30c" +content-hash = "bf113438d37b4b6d502d715f846d0cd289aeb8c14668b05780b4a0a583264d67" diff --git a/pyproject.toml b/pyproject.toml index 973e111..82e931d 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -9,13 +9,14 @@ readme = "README.md" python = "^3.11" ollama = "^0.1.8" langchain-community = "^0.0.31" -faiss-cpu = "^1.8.0" langchain = "^0.1.14" jupyterlab-vim = "^4.1.3" pypdf = "^4.1.0" numpy = "^1.26.4" psycopg = "^3.1.18" python-dotenv = "^1.0.1" +qdrant-client = "^1.8.2" +loguru = "^0.7.2" [build-system] diff --git a/rag/db/embeddings.py b/rag/db/embeddings.py index 1a97d16..4f61dcc 100644 --- a/rag/db/embeddings.py +++ b/rag/db/embeddings.py @@ -1,23 +1,47 @@ import os -from typing import Tuple +from dataclasses import dataclass +from typing import Dict, List +from uuid import uuid4 -import faiss -import numpy as np +from qdrant_client import QdrantClient +from qdrant_client.http.models import StrictFloat +from qdrant_client.models import Distance, VectorParams, PointStruct + + +@dataclass +class Point: + id: str + vector: List[StrictFloat] + payload: Dict[str, str] -# TODO: inner product distance metric? class Embeddings: def __init__(self): self.dim = int(os.environ["EMBEDDING_DIM"]) - self.index = faiss.IndexFlatL2(self.dim) - # TODO: load from file + self.collection_name = os.environ["QDRANT_COLLECTION_NAME"] + self.client = QdrantClient(url=os.environ["QDRANT_URL"]) + self.client.delete_collection( + collection_name=self.collection_name, + ) + self.client.create_collection( + collection_name=self.collection_name, + vectors_config=VectorParams(size=self.dim, distance=Distance.COSINE), + ) - def add(self, embeddings: np.ndarray): - # TODO: save to file - self.index.add(embeddings) + def add(self, points: List[Point]): + print(len(points)) + self.client.upload_points( + collection_name=self.collection_name, + points=[ + PointStruct(id=point.id, vector=point.vector, payload=point.payload) + for point in points + ], + parallel=4, + max_retries=3, + ) - def search( - self, query: np.ndarray, neighbors: int = 4 - ) -> Tuple[np.ndarray, np.ndarray]: - score, indices = self.index.search(query, neighbors) - return score, indices + def search(self, query: List[float], limit: int = 4): + hits = self.client.search( + collection_name=self.collection_name, query_vector=query, limit=limit + ) + return hits -- cgit v1.2.3-70-g09d2