Archives
/
dr-doc-search
mirror of https://github.com/namuan/dr-doc-search
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

feat: #5 Add support for huggingface embedding and allow user to select a different embedding provider from OpenAI

Browse Source
doc-sources
namuan 1 year ago
parent 5d598d44ca
commit a80bfe3dcc
4 changed files with 538 additions and 6 deletions
Show Stats Download Patch File Download Diff File

518
poetry.lock generated
Unescape Escape View File

@ -170,7 +170,7 @@ unicode-backport = ["unicodedata2"]
name = "click"
version = "8.1.3"
description = "Composable command line interface toolkit"
category = "dev"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
@ -390,7 +390,7 @@ files = [
name = "filelock"
version = "3.9.0"
description = "A platform independent file lock."
category = "dev"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
@ -642,6 +642,37 @@ colorama = ">=0.4"
[package.extras]
async = ["aiofiles (>=0.7,<1.0)"]
[[package]]
name = "huggingface-hub"
version = "0.11.1"
description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
category = "main"
optional = false
python-versions = ">=3.7.0"
files = [
{file = "huggingface_hub-0.11.1-py3-none-any.whl", hash = "sha256:11eed7aab4fa4d1fb532f2aea3379ef4998d9f6bc24a330834dfedd3dac7f441"},
{file = "huggingface_hub-0.11.1.tar.gz", hash = "sha256:8b9ebf9bbb1782f6f0419ec490973a6487c6c4ed84293a8a325d34c4f898f53f"},
]
[package.dependencies]
filelock = "*"
packaging = ">=20.9"
pyyaml = ">=5.1"
requests = "*"
tqdm = "*"
typing-extensions = ">=3.7.4.3"
[package.extras]
all = ["InquirerPy (==0.3.4)", "Jinja2", "black (==22.3)", "flake8 (>=3.8.3)", "flake8-bugbear", "isort (>=5.5.4)", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
cli = ["InquirerPy (==0.3.4)"]
dev = ["InquirerPy (==0.3.4)", "Jinja2", "black (==22.3)", "flake8 (>=3.8.3)", "flake8-bugbear", "isort (>=5.5.4)", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
quality = ["black (==22.3)", "flake8 (>=3.8.3)", "flake8-bugbear", "isort (>=5.5.4)", "mypy (==0.982)"]
tensorflow = ["graphviz", "pydot", "tensorflow"]
testing = ["InquirerPy (==0.3.4)", "Jinja2", "isort (>=5.5.4)", "jedi", "pytest", "pytest-cov", "pytest-env", "soundfile"]
torch = ["torch"]
typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
[[package]]
name = "identify"
version = "2.5.12"
@ -737,6 +768,18 @@ MarkupSafe = ">=2.0"
[package.extras]
i18n = ["Babel (>=2.7)"]
[[package]]
name = "joblib"
version = "1.2.0"
description = "Lightweight pipelining with Python functions"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
{file = "joblib-1.2.0-py3-none-any.whl", hash = "sha256:091138ed78f800342968c523bdde947e7a305b8594b910a0fea2ab83c3c6d385"},
{file = "joblib-1.2.0.tar.gz", hash = "sha256:e1cee4a79e4af22881164f218d4311f60074197fb707e082e803b61f6d137018"},
]
[[package]]
name = "langchain"
version = "0.0.57"
@ -1036,6 +1079,32 @@ files = [
{file = "mypy_extensions-0.4.3.tar.gz", hash = "sha256:2d82818f5bb3e369420cb3c4060a7970edba416647068eb4c5343488a6c604a8"},
]
[[package]]
name = "nltk"
version = "3.8.1"
description = "Natural Language Toolkit"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
{file = "nltk-3.8.1-py3-none-any.whl", hash = "sha256:fd5c9109f976fa86bcadba8f91e47f5e9293bd034474752e92a520f81c93dda5"},
{file = "nltk-3.8.1.zip", hash = "sha256:1834da3d0682cba4f2cede2f9aad6b0fafb6461ba451db0efb6f9c39798d64d3"},
]
[package.dependencies]
click = "*"
joblib = "*"
regex = ">=2021.8.3"
tqdm = "*"
[package.extras]
all = ["matplotlib", "numpy", "pyparsing", "python-crfsuite", "requests", "scikit-learn", "scipy", "twython"]
corenlp = ["requests"]
machine-learning = ["numpy", "python-crfsuite", "scikit-learn", "scipy"]
plot = ["matplotlib"]
tgrep = ["pyparsing"]
twitter = ["twython"]
[[package]]
name = "nodeenv"
version = "1.7.0"
@ -1089,6 +1158,71 @@ files = [
{file = "numpy-1.24.1.tar.gz", hash = "sha256:2386da9a471cc00a1f47845e27d916d5ec5346ae9696e01a8a34760858fe9dd2"},
]
[[package]]
name = "nvidia-cublas-cu11"
version = "11.10.3.66"
description = "CUBLAS native runtime libraries"
category = "main"
optional = false
python-versions = ">=3"
files = [
{file = "nvidia_cublas_cu11-11.10.3.66-py3-none-manylinux1_x86_64.whl", hash = "sha256:d32e4d75f94ddfb93ea0a5dda08389bcc65d8916a25cb9f37ac89edaeed3bded"},
{file = "nvidia_cublas_cu11-11.10.3.66-py3-none-win_amd64.whl", hash = "sha256:8ac17ba6ade3ed56ab898a036f9ae0756f1e81052a317bf98f8c6d18dc3ae49e"},
]
[package.dependencies]
setuptools = "*"
wheel = "*"
[[package]]
name = "nvidia-cuda-nvrtc-cu11"
version = "11.7.99"
description = "NVRTC native runtime libraries"
category = "main"
optional = false
python-versions = ">=3"
files = [
{file = "nvidia_cuda_nvrtc_cu11-11.7.99-2-py3-none-manylinux1_x86_64.whl", hash = "sha256:9f1562822ea264b7e34ed5930567e89242d266448e936b85bc97a3370feabb03"},
{file = "nvidia_cuda_nvrtc_cu11-11.7.99-py3-none-manylinux1_x86_64.whl", hash = "sha256:f7d9610d9b7c331fa0da2d1b2858a4a8315e6d49765091d28711c8946e7425e7"},
{file = "nvidia_cuda_nvrtc_cu11-11.7.99-py3-none-win_amd64.whl", hash = "sha256:f2effeb1309bdd1b3854fc9b17eaf997808f8b25968ce0c7070945c4265d64a3"},
]
[package.dependencies]
setuptools = "*"
wheel = "*"
[[package]]
name = "nvidia-cuda-runtime-cu11"
version = "11.7.99"
description = "CUDA Runtime native Libraries"
category = "main"
optional = false
python-versions = ">=3"
files = [
{file = "nvidia_cuda_runtime_cu11-11.7.99-py3-none-manylinux1_x86_64.whl", hash = "sha256:cc768314ae58d2641f07eac350f40f99dcb35719c4faff4bc458a7cd2b119e31"},
{file = "nvidia_cuda_runtime_cu11-11.7.99-py3-none-win_amd64.whl", hash = "sha256:bc77fa59a7679310df9d5c70ab13c4e34c64ae2124dd1efd7e5474b71be125c7"},
]
[package.dependencies]
setuptools = "*"
wheel = "*"
[[package]]
name = "nvidia-cudnn-cu11"
version = "8.5.0.96"
description = "cuDNN runtime libraries"
category = "main"
optional = false
python-versions = ">=3"
files = [
{file = "nvidia_cudnn_cu11-8.5.0.96-2-py3-none-manylinux1_x86_64.whl", hash = "sha256:402f40adfc6f418f9dae9ab402e773cfed9beae52333f6d86ae3107a1b9527e7"},
{file = "nvidia_cudnn_cu11-8.5.0.96-py3-none-manylinux1_x86_64.whl", hash = "sha256:71f8111eb830879ff2836db3cccf03bbd735df9b0d17cd93761732ac50a8a108"},
]
[package.dependencies]
setuptools = "*"
wheel = "*"
[[package]]
name = "openai"
version = "0.25.0"
@ -1867,7 +2001,7 @@ docs = ["Sphinx (>=3.3,<4.0)", "sphinx-autobuild (>=2020.9.1,<2021.0.0)", "sphin
name = "regex"
version = "2022.10.31"
description = "Alternative regular expression module, to replace re."
category = "dev"
category = "main"
optional = false
python-versions = ">=3.6"
files = [
@ -2002,6 +2136,88 @@ pygments = ">=2.6.0,<3.0.0"
[package.extras]
jupyter = ["ipywidgets (>=7.5.1,<8.0.0)"]
[[package]]
name = "scikit-learn"
version = "1.2.0"
description = "A set of python modules for machine learning and data mining"
category = "main"
optional = false
python-versions = ">=3.8"
files = [
{file = "scikit-learn-1.2.0.tar.gz", hash = "sha256:680b65b3caee469541385d2ca5b03ff70408f6c618c583948312f0d2125df680"},
{file = "scikit_learn-1.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1beaa631434d1f17a20b1eef5d842e58c195875d2bc11901a1a70b5fe544745b"},
{file = "scikit_learn-1.2.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:d395730f26d8fc752321f1953ddf72647c892d8bed74fad4d7c816ec9b602dfa"},
{file = "scikit_learn-1.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fd3480c982b9e616b9f76ad8587804d3f4e91b4e2a6752e7dafb8a2e1f541098"},
{file = "scikit_learn-1.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:184a42842a4e698ffa4d849b6019de50a77a0aa24d26afa28fa49c9190bb144b"},
{file = "scikit_learn-1.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:867023a044fdfe59e5014a7fec7a3086a8928f10b5dce9382eedf4135f6709a2"},
{file = "scikit_learn-1.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5546a8894a0616e92489ef995b39a0715829f3df96e801bb55cbf196be0d9649"},
{file = "scikit_learn-1.2.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:bc7073e025b62c1067cbfb76e69d08650c6b9d7a0e7afdfa20cb92d4afe516f6"},
{file = "scikit_learn-1.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fc0a72237f0c56780cf550df87201a702d3bdcbbb23c6ef7d54c19326fa23f19"},
{file = "scikit_learn-1.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4e1ea0bc1706da45589bcf2490cde6276490a1b88f9af208dbb396fdc3a0babf"},
{file = "scikit_learn-1.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:f17420a8e3f40129aeb7e0f5ee35822d6178617007bb8f69521a2cefc20d5f00"},
{file = "scikit_learn-1.2.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:25ba705ee1600ffc5df1dccd8fae129d7c6836e44ffcbb52d78536c9eaf8fcf9"},
{file = "scikit_learn-1.2.0-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:6b63ca2b0643d30fbf9d25d93017ed3fb8351f31175d82d104bfec60cba7bb87"},
{file = "scikit_learn-1.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83c772fa8c64776ad769fd764752c8452844307adcf10dee3adcc43988260f21"},
{file = "scikit_learn-1.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0834e4cec2a2e0d8978f39cb8fe1cad3be6c27a47927e1774bf5737ea65ec228"},
{file = "scikit_learn-1.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:da29d2e379c396a63af5ed4b671ad2005cd690ac373a23bee5a0f66504e05272"},
{file = "scikit_learn-1.2.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:23a88883ca60c571a06278e4726b3b51b3709cfa4c93cacbf5568b22ba960899"},
{file = "scikit_learn-1.2.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:40f3ff68c505cb9d1f3693397c73991875d609da905087e00e7b4477645ec67b"},
{file = "scikit_learn-1.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e9535e867281ae6987bb80620ba14cf1649e936bfe45f48727b978b7a2dbe835"},
{file = "scikit_learn-1.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:de897720173b26842e21bed54362f5294e282422116b61cd931d4f5d870b9855"},
{file = "scikit_learn-1.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:ceb0008f345188aa236e49c973dc160b9ed504a3abd7b321a0ecabcb669be0bd"},
]
[package.dependencies]
joblib = ">=1.1.1"
numpy = ">=1.17.3"
scipy = ">=1.3.2"
threadpoolctl = ">=2.0.0"
[package.extras]
benchmark = ["matplotlib (>=3.1.3)", "memory-profiler (>=0.57.0)", "pandas (>=1.0.5)"]
docs = ["Pillow (>=7.1.2)", "matplotlib (>=3.1.3)", "memory-profiler (>=0.57.0)", "numpydoc (>=1.2.0)", "pandas (>=1.0.5)", "plotly (>=5.10.0)", "pooch (>=1.6.0)", "scikit-image (>=0.16.2)", "seaborn (>=0.9.0)", "sphinx (>=4.0.1)", "sphinx-gallery (>=0.7.0)", "sphinx-prompt (>=1.3.0)", "sphinxext-opengraph (>=0.4.2)"]
examples = ["matplotlib (>=3.1.3)", "pandas (>=1.0.5)", "plotly (>=5.10.0)", "pooch (>=1.6.0)", "scikit-image (>=0.16.2)", "seaborn (>=0.9.0)"]
tests = ["black (>=22.3.0)", "flake8 (>=3.8.2)", "matplotlib (>=3.1.3)", "mypy (>=0.961)", "numpydoc (>=1.2.0)", "pandas (>=1.0.5)", "pooch (>=1.6.0)", "pyamg (>=4.0.0)", "pytest (>=5.3.1)", "pytest-cov (>=2.9.0)", "scikit-image (>=0.16.2)"]
[[package]]
name = "scipy"
version = "1.9.3"
description = "Fundamental algorithms for scientific computing in Python"
category = "main"
optional = false
python-versions = ">=3.8"
files = [
{file = "scipy-1.9.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1884b66a54887e21addf9c16fb588720a8309a57b2e258ae1c7986d4444d3bc0"},
{file = "scipy-1.9.3-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:83b89e9586c62e787f5012e8475fbb12185bafb996a03257e9675cd73d3736dd"},
{file = "scipy-1.9.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1a72d885fa44247f92743fc20732ae55564ff2a519e8302fb7e18717c5355a8b"},
{file = "scipy-1.9.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d01e1dd7b15bd2449c8bfc6b7cc67d630700ed655654f0dfcf121600bad205c9"},
{file = "scipy-1.9.3-cp310-cp310-win_amd64.whl", hash = "sha256:68239b6aa6f9c593da8be1509a05cb7f9efe98b80f43a5861cd24c7557e98523"},
{file = "scipy-1.9.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b41bc822679ad1c9a5f023bc93f6d0543129ca0f37c1ce294dd9d386f0a21096"},
{file = "scipy-1.9.3-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:90453d2b93ea82a9f434e4e1cba043e779ff67b92f7a0e85d05d286a3625df3c"},
{file = "scipy-1.9.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83c06e62a390a9167da60bedd4575a14c1f58ca9dfde59830fc42e5197283dab"},
{file = "scipy-1.9.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:abaf921531b5aeaafced90157db505e10345e45038c39e5d9b6c7922d68085cb"},
{file = "scipy-1.9.3-cp311-cp311-win_amd64.whl", hash = "sha256:06d2e1b4c491dc7d8eacea139a1b0b295f74e1a1a0f704c375028f8320d16e31"},
{file = "scipy-1.9.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:5a04cd7d0d3eff6ea4719371cbc44df31411862b9646db617c99718ff68d4840"},
{file = "scipy-1.9.3-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:545c83ffb518094d8c9d83cce216c0c32f8c04aaf28b92cc8283eda0685162d5"},
{file = "scipy-1.9.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0d54222d7a3ba6022fdf5773931b5d7c56efe41ede7f7128c7b1637700409108"},
{file = "scipy-1.9.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cff3a5295234037e39500d35316a4c5794739433528310e117b8a9a0c76d20fc"},
{file = "scipy-1.9.3-cp38-cp38-win_amd64.whl", hash = "sha256:2318bef588acc7a574f5bfdff9c172d0b1bf2c8143d9582e05f878e580a3781e"},
{file = "scipy-1.9.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d644a64e174c16cb4b2e41dfea6af722053e83d066da7343f333a54dae9bc31c"},
{file = "scipy-1.9.3-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:da8245491d73ed0a994ed9c2e380fd058ce2fa8a18da204681f2fe1f57f98f95"},
{file = "scipy-1.9.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4db5b30849606a95dcf519763dd3ab6fe9bd91df49eba517359e450a7d80ce2e"},
{file = "scipy-1.9.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c68db6b290cbd4049012990d7fe71a2abd9ffbe82c0056ebe0f01df8be5436b0"},
{file = "scipy-1.9.3-cp39-cp39-win_amd64.whl", hash = "sha256:5b88e6d91ad9d59478fafe92a7c757d00c59e3bdc3331be8ada76a4f8d683f58"},
{file = "scipy-1.9.3.tar.gz", hash = "sha256:fbc5c05c85c1a02be77b1ff591087c83bc44579c6d2bd9fb798bb64ea5e1a027"},
]
[package.dependencies]
numpy = ">=1.18.5,<1.26.0"
[package.extras]
dev = ["flake8", "mypy", "pycodestyle", "typing_extensions"]
doc = ["matplotlib (>2)", "numpydoc", "pydata-sphinx-theme (==0.9.0)", "sphinx (!=4.1.0)", "sphinx-panels (>=0.5.2)", "sphinx-tabs"]
test = ["asv", "gmpy2", "mpmath", "pytest", "pytest-cov", "pytest-xdist", "scikit-umfpack", "threadpoolctl"]
[[package]]
name = "semver"
version = "2.13.0"
@ -2014,6 +2230,76 @@ files = [
{file = "semver-2.13.0.tar.gz", hash = "sha256:fa0fe2722ee1c3f57eac478820c3a5ae2f624af8264cbdf9000c980ff7f75e3f"},
]
[[package]]
name = "sentence-transformers"
version = "2.2.2"
description = "Multilingual text embeddings"
category = "main"
optional = false
python-versions = ">=3.6.0"
files = [
{file = "sentence-transformers-2.2.2.tar.gz", hash = "sha256:dbc60163b27de21076c9a30d24b5b7b6fa05141d68cf2553fa9a77bf79a29136"},
]
[package.dependencies]
huggingface-hub = ">=0.4.0"
nltk = "*"
numpy = "*"
scikit-learn = "*"
scipy = "*"
sentencepiece = "*"
torch = ">=1.6.0"
torchvision = "*"
tqdm = "*"
transformers = ">=4.6.0,<5.0.0"
[[package]]
name = "sentencepiece"
version = "0.1.97"
description = "SentencePiece python wrapper"
category = "main"
optional = false
python-versions = "*"
files = [
{file = "sentencepiece-0.1.97-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:6f249c8f1852893be86eae66b19d522c5fb30bbad4fe2d1b07f06fdc86e1907e"},
{file = "sentencepiece-0.1.97-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:09e1bc53178de70c557a9ba4fece07364b4416ce3d36570726b3372b68aea135"},
{file = "sentencepiece-0.1.97-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:667193c57fb48b238be7e3d7636cfc8da56cb5bac5559d8f0b647334e1175be8"},
{file = "sentencepiece-0.1.97-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2780531985af79c6163f63d4f200fec8a28b70b6768d2c19f70d01568a4524e8"},
{file = "sentencepiece-0.1.97-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:205050670c53ef9015e2a98cce3934bfbcf0aafaa14caa0c618dd5667bc217ee"},
{file = "sentencepiece-0.1.97-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:28b183dadef8e8b6b4645c1c20692d7be0a13ecc3ec1a07b3885c8905516675f"},
{file = "sentencepiece-0.1.97-cp310-cp310-win32.whl", hash = "sha256:ee3c9dbd558d8d85bb1617087b86df6ea2b856a528669630ce6cedeb4353b823"},
{file = "sentencepiece-0.1.97-cp310-cp310-win_amd64.whl", hash = "sha256:f7dc55379e2f7dee86537180283db2e5f8418c6825fdd2fe436c724eb5604c05"},
{file = "sentencepiece-0.1.97-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:ba1b4154f9144c5a7528b00aff5cffaa1a896a1c6ca53ca78b6e74cd2dae5244"},
{file = "sentencepiece-0.1.97-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ac3d90aee5581e55d029d124ac11b6ae2fbae0817863b664b2f2302e966ababb"},
{file = "sentencepiece-0.1.97-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1c27400f1ac46518a01c87cb7703650e4e48728649feb115d2e3f1102a946a42"},
{file = "sentencepiece-0.1.97-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c6e12a166eba75994ca749aadc4a5056b91b31405f805d6de6e8914cc9741c60"},
{file = "sentencepiece-0.1.97-cp36-cp36m-win32.whl", hash = "sha256:ed85dff5c0a9b3dd1a414c7e1119f2a19e863fc3f81da525bf7f885ebc883de0"},
{file = "sentencepiece-0.1.97-cp36-cp36m-win_amd64.whl", hash = "sha256:91a19ab6f40ffbae6d6127119953d2c6a85e93d734953dbc8629fde0d21ace66"},
{file = "sentencepiece-0.1.97-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:bae580e4a35a9314ff49561ac7c06574fe6afc71b821ed6bb00534e571458156"},
{file = "sentencepiece-0.1.97-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4ad7262e7530c683b186672b5dd0082f82719a50a500a8cfbc4bbd7cde5bff8c"},
{file = "sentencepiece-0.1.97-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:620cee35279720016735a7c7103cddbd9b84fe5e2f098bd5e673834d69fee2b8"},
{file = "sentencepiece-0.1.97-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:93b921b59914c0ec6697e8c6d5e6b44d99d1298fb1a0af56980a79ade0540c19"},
{file = "sentencepiece-0.1.97-cp37-cp37m-win32.whl", hash = "sha256:9b9a4c44a31d5f47616e9568dcf31e029b0bfa776e0a252c0b59247881598b09"},
{file = "sentencepiece-0.1.97-cp37-cp37m-win_amd64.whl", hash = "sha256:f31533cdacced56219e239d3459a003ece35116920dd64b2309d4ad047b77644"},
{file = "sentencepiece-0.1.97-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:7d643c01d1cad13b9206a276bbe5bc1a468e3d7cf6a26bde7783f945277f859d"},
{file = "sentencepiece-0.1.97-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:542f1985b1ee279a92bef7740ec0781452372028ce01e15aa88df3228b197ba3"},
{file = "sentencepiece-0.1.97-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:93701da21fea906dd244bf88cdbe640385a89c45d3c1812b76dbadf8782cdbcd"},
{file = "sentencepiece-0.1.97-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a51514047b964047b7fadb480d88a5e0f72c02f6ca1ba96258fbbc6e79274a94"},
{file = "sentencepiece-0.1.97-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e3ae2e9b7a5b6f2aa64ec9240b0c185dabe597d0e787dc4344acfbaef1ffe0b2"},
{file = "sentencepiece-0.1.97-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:923ee4af16dbae1f2ab358ed09f8a0eb89e40a8198a8b343bf54181482342721"},
{file = "sentencepiece-0.1.97-cp38-cp38-win32.whl", hash = "sha256:fa6f2b88850b5fae3a05053658824cf9f147c8e3c3b40eb64539a976c83d8a24"},
{file = "sentencepiece-0.1.97-cp38-cp38-win_amd64.whl", hash = "sha256:5137ff0d0b1cc574751d178650ef800ff8d90bf21eb9f71e9567d4a0548940a5"},
{file = "sentencepiece-0.1.97-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:f92876271a10494671431ad955bff2d6f8ea59baaf957f5ae5946aff56dfcb90"},
{file = "sentencepiece-0.1.97-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:35c227b6d55e473033db7e0ecc51b1e99e6ed7607cc08602fb5768132543c81d"},
{file = "sentencepiece-0.1.97-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1706a8a8188f7b3d4b7922db9bb00c64c4e16ee68ab4caaae79f55b3e18748c7"},
{file = "sentencepiece-0.1.97-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ce61efc1862ccb18856c4aabbd930e13d5bfbb4b09b4f111081ac53a9dc62275"},
{file = "sentencepiece-0.1.97-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a78c03800ef9f02d320e0159f5768b15357f3e9ebea545c9c4ba7928ba8ba254"},
{file = "sentencepiece-0.1.97-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:753b8088fd685ee787d9f54c84275ab347de558c7c4ebc6accb4c35bf7776f20"},
{file = "sentencepiece-0.1.97-cp39-cp39-win32.whl", hash = "sha256:24306fd86031c17a1a6ae92671e76a350390a3140a65620bc2843dad7db24e2a"},
{file = "sentencepiece-0.1.97-cp39-cp39-win_amd64.whl", hash = "sha256:c6641d0b7acec61fde5881ea6ebe098c169557ac9aa3bdabdf124eab5a5592bb"},
{file = "sentencepiece-0.1.97.tar.gz", hash = "sha256:c901305e0a710bbcd296f66d79e96f744e6e175b29812bd5178318437d4e1f6c"},
]
[[package]]
name = "setuptools"
version = "65.6.3"
@ -2156,6 +2442,18 @@ files = [
[package.extras]
tests = ["pytest", "pytest-cov"]
[[package]]
name = "threadpoolctl"
version = "3.1.0"
description = "threadpoolctl"
category = "main"
optional = false
python-versions = ">=3.6"
files = [
{file = "threadpoolctl-3.1.0-py3-none-any.whl", hash = "sha256:8b99adda265feb6773280df41eece7b2e6561b772d21ffd52e372f999024907b"},
{file = "threadpoolctl-3.1.0.tar.gz", hash = "sha256:a335baacfaa4400ae1f0d8e3a58d6674d2f8828e3716bb2802c44955ad391380"},
]
[[package]]
name = "tokenize-rt"
version = "5.0.0"
@ -2168,6 +2466,57 @@ files = [
{file = "tokenize_rt-5.0.0.tar.gz", hash = "sha256:3160bc0c3e8491312d0485171dea861fc160a240f5f5766b72a1165408d10740"},
]
[[package]]
name = "tokenizers"
version = "0.13.2"
description = "Fast and Customizable Tokenizers"
category = "main"
optional = false
python-versions = "*"
files = [
{file = "tokenizers-0.13.2-cp310-cp310-macosx_10_11_x86_64.whl", hash = "sha256:a6f36b1b499233bb4443b5e57e20630c5e02fba61109632f5e00dab970440157"},
{file = "tokenizers-0.13.2-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:bc6983282ee74d638a4b6d149e5dadd8bc7ff1d0d6de663d69f099e0c6bddbeb"},
{file = "tokenizers-0.13.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:16756e6ab264b162f99c0c0a8d3d521328f428b33374c5ee161c0ebec42bf3c0"},
{file = "tokenizers-0.13.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b10db6e4b036c78212c6763cb56411566edcf2668c910baa1939afd50095ce48"},
{file = "tokenizers-0.13.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:238e879d1a0f4fddc2ce5b2d00f219125df08f8532e5f1f2ba9ad42f02b7da59"},
{file = "tokenizers-0.13.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47ef745dbf9f49281e900e9e72915356d69de3a4e4d8a475bda26bfdb5047736"},
{file = "tokenizers-0.13.2-cp310-cp310-win32.whl", hash = "sha256:96cedf83864bcc15a3ffd088a6f81a8a8f55b8b188eabd7a7f2a4469477036df"},
{file = "tokenizers-0.13.2-cp310-cp310-win_amd64.whl", hash = "sha256:eda77de40a0262690c666134baf19ec5c4f5b8bde213055911d9f5a718c506e1"},
{file = "tokenizers-0.13.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a689654fc745135cce4eea3b15e29c372c3e0b01717c6978b563de5c38af9811"},
{file = "tokenizers-0.13.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3606528c07cda0566cff6cbfbda2b167f923661be595feac95701ffcdcbdbb21"},
{file = "tokenizers-0.13.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:41291d0160946084cbd53c8ec3d029df3dc2af2673d46b25ff1a7f31a9d55d51"},
{file = "tokenizers-0.13.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7892325f9ca1cc5fca0333d5bfd96a19044ce9b092ce2df625652109a3de16b8"},
{file = "tokenizers-0.13.2-cp311-cp311-win32.whl", hash = "sha256:93714958d4ebe5362d3de7a6bd73dc86c36b5af5941ebef6c325ac900fa58865"},
{file = "tokenizers-0.13.2-cp37-cp37m-macosx_10_11_x86_64.whl", hash = "sha256:da521bfa94df6a08a6254bb8214ea04854bb9044d61063ae2529361688b5440a"},
{file = "tokenizers-0.13.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a739d4d973d422e1073989769723f3b6ad8b11e59e635a63de99aea4b2208188"},
{file = "tokenizers-0.13.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:cac01fc0b868e4d0a3aa7c5c53396da0a0a63136e81475d32fcf5c348fcb2866"},
{file = "tokenizers-0.13.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0901a5c6538d2d2dc752c6b4bde7dab170fddce559ec75662cfad03b3187c8f6"},
{file = "tokenizers-0.13.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ba9baa76b5a3eefa78b6cc351315a216232fd727ee5e3ce0f7c6885d9fb531b"},
{file = "tokenizers-0.13.2-cp37-cp37m-win32.whl", hash = "sha256:a537061ee18ba104b7f3daa735060c39db3a22c8a9595845c55b6c01d36c5e87"},
{file = "tokenizers-0.13.2-cp37-cp37m-win_amd64.whl", hash = "sha256:c82fb87b1cbfa984d8f05b2b3c3c73e428b216c1d4f0e286d0a3b27f521b32eb"},
{file = "tokenizers-0.13.2-cp38-cp38-macosx_10_11_x86_64.whl", hash = "sha256:ce298605a833ac7f81b8062d3102a42dcd9fa890493e8f756112c346339fe5c5"},
{file = "tokenizers-0.13.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a51b93932daba12ed07060935978a6779593a59709deab04a0d10e6fd5c29e60"},
{file = "tokenizers-0.13.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6969e5ea7ccb909ce7d6d4dfd009115dc72799b0362a2ea353267168667408c4"},
{file = "tokenizers-0.13.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:92f040c4d938ea64683526b45dfc81c580e3b35aaebe847e7eec374961231734"},
{file = "tokenizers-0.13.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4d3bc9f7d7f4c1aa84bb6b8d642a60272c8a2c987669e9bb0ac26daf0c6a9fc8"},
{file = "tokenizers-0.13.2-cp38-cp38-win32.whl", hash = "sha256:efbf189fb9cf29bd29e98c0437bdb9809f9de686a1e6c10e0b954410e9ca2142"},
{file = "tokenizers-0.13.2-cp38-cp38-win_amd64.whl", hash = "sha256:0b4cb2c60c094f31ea652f6cf9f349aae815f9243b860610c29a69ed0d7a88f8"},
{file = "tokenizers-0.13.2-cp39-cp39-macosx_10_11_x86_64.whl", hash = "sha256:b47d6212e7dd05784d7330b3b1e5a170809fa30e2b333ca5c93fba1463dec2b7"},
{file = "tokenizers-0.13.2-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:80a57501b61ec4f94fb7ce109e2b4a1a090352618efde87253b4ede6d458b605"},
{file = "tokenizers-0.13.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:61507a9953f6e7dc3c972cbc57ba94c80c8f7f686fbc0876afe70ea2b8cc8b04"},
{file = "tokenizers-0.13.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c09f4fa620e879debdd1ec299bb81e3c961fd8f64f0e460e64df0818d29d845c"},
{file = "tokenizers-0.13.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:66c892d85385b202893ac6bc47b13390909e205280e5df89a41086cfec76fedb"},
{file = "tokenizers-0.13.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b3e306b0941ad35087ae7083919a5c410a6b672be0343609d79a1171a364ce79"},
{file = "tokenizers-0.13.2-cp39-cp39-win32.whl", hash = "sha256:79189e7f706c74dbc6b753450757af172240916d6a12ed4526af5cc6d3ceca26"},
{file = "tokenizers-0.13.2-cp39-cp39-win_amd64.whl", hash = "sha256:486d637b413fddada845a10a45c74825d73d3725da42ccd8796ccd7a1c07a024"},
{file = "tokenizers-0.13.2.tar.gz", hash = "sha256:f9525375582fd1912ac3caa2f727d36c86ff8c0c6de45ae1aaff90f87f33b907"},
]
[package.extras]
dev = ["black (==22.3)", "datasets", "numpy", "pytest", "requests"]
docs = ["setuptools-rust", "sphinx", "sphinx-rtd-theme"]
testing = ["black (==22.3)", "datasets", "numpy", "pytest", "requests"]
[[package]]
name = "toml"
version = "0.10.2"
@ -2204,6 +2553,86 @@ files = [
{file = "tomlkit-0.11.6.tar.gz", hash = "sha256:71b952e5721688937fb02cf9d354dbcf0785066149d2855e44531ebdd2b65d73"},
]
[[package]]
name = "torch"
version = "1.13.1"
description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
category = "main"
optional = false
python-versions = ">=3.7.0"
files = [
{file = "torch-1.13.1-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:fd12043868a34a8da7d490bf6db66991108b00ffbeecb034228bfcbbd4197143"},
{file = "torch-1.13.1-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:d9fe785d375f2e26a5d5eba5de91f89e6a3be5d11efb497e76705fdf93fa3c2e"},
{file = "torch-1.13.1-cp310-cp310-win_amd64.whl", hash = "sha256:98124598cdff4c287dbf50f53fb455f0c1e3a88022b39648102957f3445e9b76"},
{file = "torch-1.13.1-cp310-none-macosx_10_9_x86_64.whl", hash = "sha256:393a6273c832e047581063fb74335ff50b4c566217019cc6ace318cd79eb0566"},
{file = "torch-1.13.1-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:0122806b111b949d21fa1a5f9764d1fd2fcc4a47cb7f8ff914204fd4fc752ed5"},
{file = "torch-1.13.1-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:22128502fd8f5b25ac1cd849ecb64a418382ae81dd4ce2b5cebaa09ab15b0d9b"},
{file = "torch-1.13.1-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:76024be052b659ac1304ab8475ab03ea0a12124c3e7626282c9c86798ac7bc11"},
{file = "torch-1.13.1-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:ea8dda84d796094eb8709df0fcd6b56dc20b58fdd6bc4e8d7109930dafc8e419"},
{file = "torch-1.13.1-cp37-cp37m-win_amd64.whl", hash = "sha256:2ee7b81e9c457252bddd7d3da66fb1f619a5d12c24d7074de91c4ddafb832c93"},
{file = "torch-1.13.1-cp37-none-macosx_10_9_x86_64.whl", hash = "sha256:0d9b8061048cfb78e675b9d2ea8503bfe30db43d583599ae8626b1263a0c1380"},
{file = "torch-1.13.1-cp37-none-macosx_11_0_arm64.whl", hash = "sha256:f402ca80b66e9fbd661ed4287d7553f7f3899d9ab54bf5c67faada1555abde28"},
{file = "torch-1.13.1-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:727dbf00e2cf858052364c0e2a496684b9cb5aa01dc8a8bc8bbb7c54502bdcdd"},
{file = "torch-1.13.1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:df8434b0695e9ceb8cc70650afc1310d8ba949e6db2a0525ddd9c3b2b181e5fe"},
{file = "torch-1.13.1-cp38-cp38-win_amd64.whl", hash = "sha256:5e1e722a41f52a3f26f0c4fcec227e02c6c42f7c094f32e49d4beef7d1e213ea"},
{file = "torch-1.13.1-cp38-none-macosx_10_9_x86_64.whl", hash = "sha256:33e67eea526e0bbb9151263e65417a9ef2d8fa53cbe628e87310060c9dcfa312"},
{file = "torch-1.13.1-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:eeeb204d30fd40af6a2d80879b46a7efbe3cf43cdbeb8838dd4f3d126cc90b2b"},
{file = "torch-1.13.1-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:50ff5e76d70074f6653d191fe4f6a42fdbe0cf942fbe2a3af0b75eaa414ac038"},
{file = "torch-1.13.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:2c3581a3fd81eb1f0f22997cddffea569fea53bafa372b2c0471db373b26aafc"},
{file = "torch-1.13.1-cp39-cp39-win_amd64.whl", hash = "sha256:0aa46f0ac95050c604bcf9ef71da9f1172e5037fdf2ebe051962d47b123848e7"},
{file = "torch-1.13.1-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:6930791efa8757cb6974af73d4996b6b50c592882a324b8fb0589c6a9ba2ddaf"},
{file = "torch-1.13.1-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:e0df902a7c7dd6c795698532ee5970ce898672625635d885eade9976e5a04949"},
]
[package.dependencies]
nvidia-cublas-cu11 = {version = "11.10.3.66", markers = "platform_system == \"Linux\""}
nvidia-cuda-nvrtc-cu11 = {version = "11.7.99", markers = "platform_system == \"Linux\""}
nvidia-cuda-runtime-cu11 = {version = "11.7.99", markers = "platform_system == \"Linux\""}
nvidia-cudnn-cu11 = {version = "8.5.0.96", markers = "platform_system == \"Linux\""}
typing-extensions = "*"
[package.extras]
opt-einsum = ["opt-einsum (>=3.3)"]
[[package]]
name = "torchvision"
version = "0.14.1"
description = "image and video datasets and models for torch deep learning"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
{file = "torchvision-0.14.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:eeb05dd9dd3af5428fee525400759daf8da8e4caec45ddd6908cfb36571f6433"},
{file = "torchvision-0.14.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8d0766ea92affa7af248e327dd85f7c9cfdf51a57530b43212d4e1858548e9d7"},
{file = "torchvision-0.14.1-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:6d7b35653113664ea3fdcb71f515cfbf29d2fe393000fd8aaff27a1284de6908"},
{file = "torchvision-0.14.1-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:8a9eb773a2fa8f516e404ac09c059fb14e6882c48fdbb9c946327d2ce5dba6cd"},
{file = "torchvision-0.14.1-cp310-cp310-win_amd64.whl", hash = "sha256:13986f0c15377ff23039e1401012ccb6ecf71024ce53def27139e4eac5a57592"},
{file = "torchvision-0.14.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:fb7a793fd33ce1abec24b42778419a3fb1e3159d7dfcb274a3ca8fb8cbc408dc"},
{file = "torchvision-0.14.1-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:89fb0419780ec9a9eb9f7856a0149f6ac9f956b28f44b0c0080c6b5b48044db7"},
{file = "torchvision-0.14.1-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:a2d4237d3c9705d7729eb4534e4eb06f1d6be7ff1df391204dfb51586d9b0ecb"},
{file = "torchvision-0.14.1-cp37-cp37m-win_amd64.whl", hash = "sha256:92a324712a87957443cc34223274298ae9496853f115c252f8fc02b931f2340e"},
{file = "torchvision-0.14.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:68ed03359dcd3da9cd21b8ab94da21158df8a6a0c5bad0bf4a42f0e448d28cb3"},
{file = "torchvision-0.14.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:30fcf0e9fe57d4ac4ce6426659a57dce199637ccb6c70be1128670f177692624"},
{file = "torchvision-0.14.1-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:0ed02aefd09bf1114d35f1aa7dce55aa61c2c7e57f9aa02dce362860be654e85"},
{file = "torchvision-0.14.1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:a541e49fc3c4e90e49e6988428ab047415ed52ea97d0c0bfd147d8bacb8f4df8"},
{file = "torchvision-0.14.1-cp38-cp38-win_amd64.whl", hash = "sha256:6099b3191dc2516099a32ae38a5fb349b42e863872a13545ab1a524b6567be60"},
{file = "torchvision-0.14.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c5e744f56e5f5b452deb5fc0f3f2ba4d2f00612d14d8da0dbefea8f09ac7690b"},
{file = "torchvision-0.14.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:758b20d079e810b4740bd60d1eb16e49da830e3360f9be379eb177ee221fa5d4"},
{file = "torchvision-0.14.1-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:83045507ef8d3c015d4df6be79491375b2f901352cfca6e72b4723e9c4f9a55d"},
{file = "torchvision-0.14.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:eaed58cf454323ed9222d4e0dd5fb897064f454b400696e03a5200e65d3a1e76"},
{file = "torchvision-0.14.1-cp39-cp39-win_amd64.whl", hash = "sha256:b337e1245ca4353623dd563c03cd8f020c2496a7c5d12bba4d2e381999c766e0"},
]
[package.dependencies]
numpy = "*"
pillow = ">=5.3.0,<8.3.0 || >=8.4.0"
requests = "*"
torch = "1.13.1"
typing-extensions = "*"
[package.extras]
scipy = ["scipy"]
[[package]]
name = "tornado"
version = "6.2"
@ -2246,6 +2675,72 @@ notebook = ["ipywidgets (>=6)"]
slack = ["slack-sdk"]
telegram = ["requests"]
[[package]]
name = "transformers"
version = "4.25.1"
description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
category = "main"
optional = false
python-versions = ">=3.7.0"
files = [
{file = "transformers-4.25.1-py3-none-any.whl", hash = "sha256:60f1be15e17e4a54373c787c713ec149dabcc63464131ac45611618fe7c2016e"},
{file = "transformers-4.25.1.tar.gz", hash = "sha256:6dad398b792d45dc04e9ee7e9e06bf758ab19dca2efc119065e661bb0f8f843b"},
]
[package.dependencies]
filelock = "*"
huggingface-hub = ">=0.10.0,<1.0"
numpy = ">=1.17"
packaging = ">=20.0"
pyyaml = ">=5.1"
regex = "!=2019.12.17"
requests = "*"
tokenizers = ">=0.11.1,<0.11.3 || >0.11.3,<0.14"
tqdm = ">=4.27"
[package.extras]
accelerate = ["accelerate (>=0.10.0)"]
all = ["Pillow", "accelerate (>=0.10.0)", "codecarbon (==1.2.0)", "flax (>=0.4.1)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8)", "optuna", "phonemizer", "protobuf (<=3.20.2)", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.4,<2.11)", "tensorflow-text", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.7,!=1.12.0)", "torchaudio"]
audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
codecarbon = ["codecarbon (==1.2.0)"]
deepspeed = ["accelerate (>=0.10.0)", "deepspeed (>=0.6.5)"]
deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.10.0)", "beautifulsoup4", "black (==22.3)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.6.5)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "optuna", "parameterized", "protobuf (<=3.20.2)", "psutil", "pytest", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "safetensors (>=0.2.1)", "timeout-decorator"]
dev = ["GitPython (<3.1.19)", "Pillow", "accelerate (>=0.10.0)", "beautifulsoup4", "black (==22.3)", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flake8 (>=3.8.3)", "flax (>=0.4.1)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8)", "optuna", "parameterized", "phonemizer", "protobuf (<=3.20.2)", "psutil", "pyctcdecode (>=0.4.0)", "pyknp (>=0.6.1)", "pytest", "pytest-timeout", "pytest-xdist", "ray[tune]", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "safetensors (>=0.2.1)", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorflow (>=2.4,<2.11)", "tensorflow-text", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.7,!=1.12.0)", "torchaudio", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)"]
dev-tensorflow = ["GitPython (<3.1.19)", "Pillow", "beautifulsoup4", "black (==22.3)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flake8 (>=3.8.3)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf (<=3.20.2)", "psutil", "pyctcdecode (>=0.4.0)", "pytest", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "safetensors (>=0.2.1)", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorflow (>=2.4,<2.11)", "tensorflow-text", "tf2onnx", "timeout-decorator", "tokenizers (>=0.11.1,!=0.11.3,<0.14)"]
dev-torch = ["GitPython (<3.1.19)", "Pillow", "beautifulsoup4", "black (==22.3)", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flake8 (>=3.8.3)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf (<=3.20.2)", "psutil", "pyctcdecode (>=0.4.0)", "pyknp (>=0.6.1)", "pytest", "pytest-timeout", "pytest-xdist", "ray[tune]", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "safetensors (>=0.2.1)", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.7,!=1.12.0)", "torchaudio", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)"]
docs = ["Pillow", "accelerate (>=0.10.0)", "codecarbon (==1.2.0)", "flax (>=0.4.1)", "hf-doc-builder", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8)", "optuna", "phonemizer", "protobuf (<=3.20.2)", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.4,<2.11)", "tensorflow-text", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.7,!=1.12.0)", "torchaudio"]
docs-specific = ["hf-doc-builder"]
fairscale = ["fairscale (>0.3)"]
flax = ["flax (>=0.4.1)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "optax (>=0.0.8)"]
flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
ftfy = ["ftfy"]
integrations = ["optuna", "ray[tune]", "sigopt"]
ja = ["fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "pyknp (>=0.6.1)", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)"]
modelcreation = ["cookiecutter (==1.7.3)"]
natten = ["natten (>=0.14.4)"]
onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"]
onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
optuna = ["optuna"]
quality = ["GitPython (<3.1.19)", "black (==22.3)", "datasets (!=2.5.0)", "flake8 (>=3.8.3)", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)"]
ray = ["ray[tune]"]
retrieval = ["datasets (!=2.5.0)", "faiss-cpu"]
sagemaker = ["sagemaker (>=2.31.0)"]
sentencepiece = ["protobuf (<=3.20.2)", "sentencepiece (>=0.1.91,!=0.1.92)"]
serving = ["fastapi", "pydantic", "starlette", "uvicorn"]
sigopt = ["sigopt"]
sklearn = ["scikit-learn"]
speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
testing = ["GitPython (<3.1.19)", "beautifulsoup4", "black (==22.3)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "parameterized", "protobuf (<=3.20.2)", "psutil", "pytest", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "safetensors (>=0.2.1)", "timeout-decorator"]
tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>=2.4,<2.11)", "tensorflow-text", "tf2onnx"]
tf-cpu = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>=2.4,<2.11)", "tensorflow-text", "tf2onnx"]
tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
timm = ["timm"]
tokenizers = ["tokenizers (>=0.11.1,!=0.11.3,<0.14)"]
torch = ["torch (>=1.7,!=1.12.0)"]
torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
torchhub = ["filelock", "huggingface-hub (>=0.10.0,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf (<=3.20.2)", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.7,!=1.12.0)", "tqdm (>=4.27)"]
vision = ["Pillow"]
[[package]]
name = "tryceratops"
version = "1.1.0"
@ -2378,6 +2873,21 @@ files = [
{file = "webencodings-0.5.1.tar.gz", hash = "sha256:b36a1c245f2d304965eb4e0a82848379241dc04b865afcc4aab16748587e1923"},
]
[[package]]
name = "wheel"
version = "0.38.4"
description = "A built-package format for Python"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
{file = "wheel-0.38.4-py3-none-any.whl", hash = "sha256:b60533f3f5d530e971d6737ca6d58681ee434818fab630c83a734bb10c083ce8"},
{file = "wheel-0.38.4.tar.gz", hash = "sha256:965f5259b566725405b05e7cf774052044b1ed30119b5d586b2703aafe8719ac"},
]
[package.extras]
test = ["pytest (>=3.0.0)"]
[[package]]
name = "zipp"
version = "3.11.0"
@ -2397,4 +2907,4 @@ testing = ["flake8 (<5)", "func-timeout", "jaraco.functools", "jaraco.itertools"
[metadata]
lock-version = "2.0"
python-versions = ">=3.9.0, <4.0"
content-hash = "98276af914546a90b1ddf76a62d2bb170c9d31135b9d9ef6f855e7029bae1fd7"
content-hash = "34a3fad8c1a4f517b1a0b69126ef05892054d27a1ee8600d0c57da19f61130fa"

1
pyproject.toml
Unescape Escape View File

@ -41,6 +41,7 @@ faiss-cpu = "^1.7.3"
python-dotenv = "^0.21.0"
panel = "^0.14.2"
slug = "^2.0"
sentence-transformers = "^2.2.2"
[tool.poetry.group.dev.dependencies]
autoflake = "*"

7
src/doc_search/app.py
Unescape Escape View File

@ -32,6 +32,13 @@ def parse_args() -> Namespace:
parser.add_argument("-t", "--train", action="store_true", help="Train and index the PDF file")
parser.add_argument("-a", "--web-app", action="store_true", help="Start WebApp")
parser.add_argument("-p", "--pre-process", action="store_true", help="Extract text from PDF file")
parser.add_argument(
"-b",
"--embedding",
choices=["openai", "huggingface", "huggingface-hub", "cohere"],
default="openai",
help="Embedding to use",
)
parser.add_argument(
"-v",

18
src/doc_search/workflow/__init__.py
Unescape Escape View File

@ -7,6 +7,9 @@ from typing import Any
import faiss # type: ignore
import openai
from langchain import OpenAI, VectorDBQA
from langchain.embeddings import HuggingFaceEmbeddings, HuggingFaceHubEmbeddings
from langchain.embeddings.base import Embeddings
from langchain.embeddings.cohere import CohereEmbeddings
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.prompts import PromptTemplate
from langchain.text_splitter import CharacterTextSplitter
@ -158,11 +161,22 @@ class CreateIndex(WorkflowBase):
app_dir: Path
overwrite_index: bool
chunked_text_list: list[str]
embedding: str
@retry(exceptions=openai.error.RateLimitError, tries=2, delay=60, back_off=2)
def append_to_index(self, docsearch: FAISS, text: str, embeddings: OpenAIEmbeddings) -> None:
def append_to_index(self, docsearch: FAISS, text: str, embeddings: Embeddings) -> None:
docsearch.from_texts([text], embeddings)
def embedding_from_selection(self) -> Embeddings:
if self.embedding == "huggingface":
return HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
elif self.embedding == "huggingface-hub":
return HuggingFaceHubEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
elif self.embedding == "cohere":
return CohereEmbeddings()
else:
return OpenAIEmbeddings()
def execute(self) -> dict:
faiss_db = pdf_to_faiss_db_path(self.app_dir, self.input_pdf_path)
index_path = pdf_to_index_path(self.app_dir, self.input_pdf_path)
@ -178,7 +192,7 @@ class CreateIndex(WorkflowBase):
faiss_db.exists(),
)
embeddings = OpenAIEmbeddings()
embeddings = self.embedding_from_selection()
docsearch: FAISS = FAISS.from_texts(self.chunked_text_list[:2], embeddings)
for text in self.chunked_text_list[2:]:
self.append_to_index(docsearch, text, embeddings)

Write Preview
Loading…
Cancel
Save