From 6e9e194f338330747079e2a9db9574ffd51cb63f Mon Sep 17 00:00:00 2001 From: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com> Date: Tue, 7 Mar 2023 17:55:23 +0100 Subject: [PATCH] final --- clients/python/Makefile | 6 + clients/python/README.md | 53 +- clients/python/poetry.lock | 462 +++++++++++++++++- clients/python/pyproject.toml | 15 +- clients/python/tests/conftest.py | 46 ++ clients/python/tests/test_api_inference.py | 34 ++ clients/python/tests/test_client.py | 127 +++++ clients/python/tests/test_errors.py | 64 +++ clients/python/tests/test_types.py | 39 ++ clients/python/text_generation/__init__.py | 18 +- .../python/text_generation/api_inference.py | 124 ++++- clients/python/text_generation/client.py | 243 ++++++++- clients/python/text_generation/errors.py | 17 +- clients/python/text_generation/types.py | 10 +- 14 files changed, 1207 insertions(+), 51 deletions(-) create mode 100644 clients/python/Makefile create mode 100644 clients/python/tests/conftest.py create mode 100644 clients/python/tests/test_api_inference.py create mode 100644 clients/python/tests/test_client.py create mode 100644 clients/python/tests/test_errors.py create mode 100644 clients/python/tests/test_types.py diff --git a/clients/python/Makefile b/clients/python/Makefile new file mode 100644 index 00000000..8b4334bd --- /dev/null +++ b/clients/python/Makefile @@ -0,0 +1,6 @@ +unit-tests: + python -m pytest --cov=text_generation tests + +install: + pip install pip --upgrade + pip install -e . \ No newline at end of file diff --git a/clients/python/README.md b/clients/python/README.md index 1ae11928..414360bf 100644 --- a/clients/python/README.md +++ b/clients/python/README.md @@ -1 +1,52 @@ -# Text Generation \ No newline at end of file +# Text Generation + +The Hugging Face Text Generation Python library provides a convenient way of interfacing with a +`text-generation-inference` instance running on your own infrastructure or on the Hugging Face Hub. + +## Get Started + +### Install + +```shell +pip install text-generation +``` + +### Usage + +```python +from text_generation import InferenceAPIClient + +client = InferenceAPIClient("bigscience/bloomz") +text = client.generate("Why is the sky blue?").generated_text +print(text) +# ' Rayleigh scattering' + +# Token Streaming +text = "" +for response in client.generate_stream("Why is the sky blue?"): + if not response.token.special: + text += response.token.text + +print(text) +# ' Rayleigh scattering' +``` + +or with the asynchronous client: + +```python +from text_generation import InferenceAPIAsyncClient + +client = InferenceAPIAsyncClient("bigscience/bloomz") +response = await client.generate("Why is the sky blue?") +print(response.generated_text) +# ' Rayleigh scattering' + +# Token Streaming +text = "" +async for response in client.generate_stream("Why is the sky blue?"): + if not response.token.special: + text += response.token.text + +print(text) +# ' Rayleigh scattering' +``` diff --git a/clients/python/poetry.lock b/clients/python/poetry.lock index bd2acf68..fe1f34cb 100644 --- a/clients/python/poetry.lock +++ b/clients/python/poetry.lock @@ -9,10 +9,12 @@ python-versions = ">=3.6" [package.dependencies] aiosignal = ">=1.1.2" async-timeout = ">=4.0.0a3,<5.0" +asynctest = {version = "0.13.0", markers = "python_version < \"3.8\""} attrs = ">=17.3.0" charset-normalizer = ">=2.0,<4.0" frozenlist = ">=1.1.1" multidict = ">=4.5,<7.0" +typing-extensions = {version = ">=3.7.4", markers = "python_version < \"3.8\""} yarl = ">=1.0,<2.0" [package.extras] @@ -37,6 +39,25 @@ category = "main" optional = false python-versions = ">=3.6" +[package.dependencies] +typing-extensions = {version = ">=3.6.5", markers = "python_version < \"3.8\""} + +[[package]] +name = "asynctest" +version = "0.13.0" +description = "Enhance the standard unittest package with features for testing asyncio libraries" +category = "main" +optional = false +python-versions = ">=3.5" + +[[package]] +name = "atomicwrites" +version = "1.4.1" +description = "Atomic file writes." +category = "dev" +optional = false +python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*" + [[package]] name = "attrs" version = "22.2.0" @@ -53,6 +74,14 @@ tests = ["attrs[tests-no-zope]", "zope.interface"] tests-no-zope = ["cloudpickle", "hypothesis", "mypy (>=0.971,<0.990)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"] tests_no_zope = ["cloudpickle", "hypothesis", "mypy (>=0.971,<0.990)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"] +[[package]] +name = "certifi" +version = "2022.12.7" +description = "Python package for providing Mozilla's CA Bundle." +category = "main" +optional = false +python-versions = ">=3.6" + [[package]] name = "charset-normalizer" version = "3.1.0" @@ -61,6 +90,40 @@ category = "main" optional = false python-versions = ">=3.7.0" +[[package]] +name = "colorama" +version = "0.4.6" +description = "Cross-platform colored terminal text." +category = "main" +optional = false +python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7" + +[[package]] +name = "coverage" +version = "7.2.1" +description = "Code coverage measurement for Python" +category = "dev" +optional = false +python-versions = ">=3.7" + +[package.dependencies] +tomli = {version = "*", optional = true, markers = "python_full_version <= \"3.11.0a6\" and extra == \"toml\""} + +[package.extras] +toml = ["tomli"] + +[[package]] +name = "filelock" +version = "3.9.0" +description = "A platform independent file lock." +category = "main" +optional = false +python-versions = ">=3.7" + +[package.extras] +docs = ["furo (>=2022.12.7)", "sphinx (>=5.3)", "sphinx-autodoc-typehints (>=1.19.5)"] +testing = ["covdefaults (>=2.2.2)", "coverage (>=7.0.1)", "pytest (>=7.2)", "pytest-cov (>=4)", "pytest-timeout (>=2.1)"] + [[package]] name = "frozenlist" version = "1.3.3" @@ -69,6 +132,34 @@ category = "main" optional = false python-versions = ">=3.7" +[[package]] +name = "huggingface-hub" +version = "0.12.1" +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" + +[package.dependencies] +filelock = "*" +importlib-metadata = {version = "*", markers = "python_version < \"3.8\""} +packaging = ">=20.9" +pyyaml = ">=5.1" +requests = "*" +tqdm = ">=4.42.1" +typing-extensions = ">=3.7.4.3" + +[package.extras] +all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "black (==22.3)", "flake8 (>=3.8.3)", "flake8-bugbear", "isort (>=5.5.4)", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"] +cli = ["InquirerPy (==0.3.4)"] +dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "black (==22.3)", "flake8 (>=3.8.3)", "flake8-bugbear", "isort (>=5.5.4)", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "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", "Pillow", "isort (>=5.5.4)", "jedi", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "soundfile"] +torch = ["torch"] +typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"] + [[package]] name = "idna" version = "3.4" @@ -77,6 +168,31 @@ category = "main" optional = false python-versions = ">=3.5" +[[package]] +name = "importlib-metadata" +version = "6.0.0" +description = "Read metadata from Python packages" +category = "main" +optional = false +python-versions = ">=3.7" + +[package.dependencies] +typing-extensions = {version = ">=3.6.4", markers = "python_version < \"3.8\""} +zipp = ">=0.5" + +[package.extras] +docs = ["furo", "jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"] +perf = ["ipython"] +testing = ["flake8 (<5)", "flufl.flake8", "importlib-resources (>=1.3)", "packaging", "pyfakefs", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)", "pytest-perf (>=0.9.2)"] + +[[package]] +name = "iniconfig" +version = "2.0.0" +description = "brain-dead simple config-ini parsing" +category = "dev" +optional = false +python-versions = ">=3.7" + [[package]] name = "multidict" version = "6.0.4" @@ -85,6 +201,37 @@ category = "main" optional = false python-versions = ">=3.7" +[[package]] +name = "packaging" +version = "23.0" +description = "Core utilities for Python packages" +category = "main" +optional = false +python-versions = ">=3.7" + +[[package]] +name = "pluggy" +version = "1.0.0" +description = "plugin and hook calling mechanisms for python" +category = "dev" +optional = false +python-versions = ">=3.6" + +[package.dependencies] +importlib-metadata = {version = ">=0.12", markers = "python_version < \"3.8\""} + +[package.extras] +dev = ["pre-commit", "tox"] +testing = ["pytest", "pytest-benchmark"] + +[[package]] +name = "py" +version = "1.11.0" +description = "library with cross-python path, ini-parsing, io, code, log facilities" +category = "dev" +optional = false +python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*" + [[package]] name = "pydantic" version = "1.10.5" @@ -100,6 +247,117 @@ typing-extensions = ">=4.2.0" dotenv = ["python-dotenv (>=0.10.4)"] email = ["email-validator (>=1.0.3)"] +[[package]] +name = "pytest" +version = "6.2.5" +description = "pytest: simple powerful testing with Python" +category = "dev" +optional = false +python-versions = ">=3.6" + +[package.dependencies] +atomicwrites = {version = ">=1.0", markers = "sys_platform == \"win32\""} +attrs = ">=19.2.0" +colorama = {version = "*", markers = "sys_platform == \"win32\""} +importlib-metadata = {version = ">=0.12", markers = "python_version < \"3.8\""} +iniconfig = "*" +packaging = "*" +pluggy = ">=0.12,<2.0" +py = ">=1.8.2" +toml = "*" + +[package.extras] +testing = ["argcomplete", "hypothesis (>=3.56)", "mock", "nose", "requests", "xmlschema"] + +[[package]] +name = "pytest-asyncio" +version = "0.17.2" +description = "Pytest support for asyncio" +category = "dev" +optional = false +python-versions = ">=3.7" + +[package.dependencies] +pytest = ">=6.1.0" +typing-extensions = {version = ">=4.0", markers = "python_version < \"3.8\""} + +[package.extras] +testing = ["coverage (==6.2)", "flaky (>=3.5.0)", "hypothesis (>=5.7.1)", "mypy (==0.931)"] + +[[package]] +name = "pytest-cov" +version = "3.0.0" +description = "Pytest plugin for measuring coverage." +category = "dev" +optional = false +python-versions = ">=3.6" + +[package.dependencies] +coverage = {version = ">=5.2.1", extras = ["toml"]} +pytest = ">=4.6" + +[package.extras] +testing = ["fields", "hunter", "process-tests", "pytest-xdist", "six", "virtualenv"] + +[[package]] +name = "PyYAML" +version = "6.0" +description = "YAML parser and emitter for Python" +category = "main" +optional = false +python-versions = ">=3.6" + +[[package]] +name = "requests" +version = "2.28.2" +description = "Python HTTP for Humans." +category = "main" +optional = false +python-versions = ">=3.7, <4" + +[package.dependencies] +certifi = ">=2017.4.17" +charset-normalizer = ">=2,<4" +idna = ">=2.5,<4" +urllib3 = ">=1.21.1,<1.27" + +[package.extras] +socks = ["PySocks (>=1.5.6,!=1.5.7)"] +use_chardet_on_py3 = ["chardet (>=3.0.2,<6)"] + +[[package]] +name = "toml" +version = "0.10.2" +description = "Python Library for Tom's Obvious, Minimal Language" +category = "dev" +optional = false +python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*" + +[[package]] +name = "tomli" +version = "2.0.1" +description = "A lil' TOML parser" +category = "dev" +optional = false +python-versions = ">=3.7" + +[[package]] +name = "tqdm" +version = "4.65.0" +description = "Fast, Extensible Progress Meter" +category = "main" +optional = false +python-versions = ">=3.7" + +[package.dependencies] +colorama = {version = "*", markers = "platform_system == \"Windows\""} + +[package.extras] +dev = ["py-make (>=0.1.0)", "twine", "wheel"] +notebook = ["ipywidgets (>=6)"] +slack = ["slack-sdk"] +telegram = ["requests"] + [[package]] name = "typing-extensions" version = "4.5.0" @@ -108,6 +366,19 @@ category = "main" optional = false python-versions = ">=3.7" +[[package]] +name = "urllib3" +version = "1.26.14" +description = "HTTP library with thread-safe connection pooling, file post, and more." +category = "main" +optional = false +python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*" + +[package.extras] +brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"] +secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"] +socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"] + [[package]] name = "yarl" version = "1.8.2" @@ -119,11 +390,24 @@ python-versions = ">=3.7" [package.dependencies] idna = ">=2.0" multidict = ">=4.0" +typing-extensions = {version = ">=3.7.4", markers = "python_version < \"3.8\""} + +[[package]] +name = "zipp" +version = "3.15.0" +description = "Backport of pathlib-compatible object wrapper for zip files" +category = "main" +optional = false +python-versions = ">=3.7" + +[package.extras] +docs = ["furo", "jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"] +testing = ["big-O", "flake8 (<5)", "jaraco.functools", "jaraco.itertools", "more-itertools", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)"] [metadata] lock-version = "1.1" -python-versions = "^3.9" -content-hash = "b1b9949a4e7006b90d2bf0189f00b0ac4ad70e3056ac98a4cc4e3949ad16f084" +python-versions = "^3.7" +content-hash = "12eb0ce46193750e35aec1f1fb32a0ce094aebd1db30682d06424ee6ccd23536" [metadata.files] aiohttp = [ @@ -223,10 +507,21 @@ async-timeout = [ {file = "async-timeout-4.0.2.tar.gz", hash = "sha256:2163e1640ddb52b7a8c80d0a67a08587e5d245cc9c553a74a847056bc2976b15"}, {file = "async_timeout-4.0.2-py3-none-any.whl", hash = "sha256:8ca1e4fcf50d07413d66d1a5e416e42cfdf5851c981d679a09851a6853383b3c"}, ] +asynctest = [ + {file = "asynctest-0.13.0-py3-none-any.whl", hash = "sha256:5da6118a7e6d6b54d83a8f7197769d046922a44d2a99c21382f0a6e4fadae676"}, + {file = "asynctest-0.13.0.tar.gz", hash = "sha256:c27862842d15d83e6a34eb0b2866c323880eb3a75e4485b079ea11748fd77fac"}, +] +atomicwrites = [ + {file = "atomicwrites-1.4.1.tar.gz", hash = "sha256:81b2c9071a49367a7f770170e5eec8cb66567cfbbc8c73d20ce5ca4a8d71cf11"}, +] attrs = [ {file = "attrs-22.2.0-py3-none-any.whl", hash = "sha256:29e95c7f6778868dbd49170f98f8818f78f3dc5e0e37c0b1f474e3561b240836"}, {file = "attrs-22.2.0.tar.gz", hash = "sha256:c9227bfc2f01993c03f68db37d1d15c9690188323c067c641f1a35ca58185f99"}, ] +certifi = [ + {file = "certifi-2022.12.7-py3-none-any.whl", hash = "sha256:4ad3232f5e926d6718ec31cfc1fcadfde020920e278684144551c91769c7bc18"}, + {file = "certifi-2022.12.7.tar.gz", hash = "sha256:35824b4c3a97115964b408844d64aa14db1cc518f6562e8d7261699d1350a9e3"}, +] charset-normalizer = [ {file = "charset-normalizer-3.1.0.tar.gz", hash = "sha256:34e0a2f9c370eb95597aae63bf85eb5e96826d81e3dcf88b8886012906f509b5"}, {file = "charset_normalizer-3.1.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:e0ac8959c929593fee38da1c2b64ee9778733cdf03c482c9ff1d508b6b593b2b"}, @@ -304,6 +599,67 @@ charset-normalizer = [ {file = "charset_normalizer-3.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:830d2948a5ec37c386d3170c483063798d7879037492540f10a475e3fd6f244b"}, {file = "charset_normalizer-3.1.0-py3-none-any.whl", hash = "sha256:3d9098b479e78c85080c98e1e35ff40b4a31d8953102bb0fd7d1b6f8a2111a3d"}, ] +colorama = [ + {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"}, + {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"}, +] +coverage = [ + {file = "coverage-7.2.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:49567ec91fc5e0b15356da07a2feabb421d62f52a9fff4b1ec40e9e19772f5f8"}, + {file = "coverage-7.2.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d2ef6cae70168815ed91388948b5f4fcc69681480a0061114db737f957719f03"}, + {file = "coverage-7.2.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3004765bca3acd9e015794e5c2f0c9a05587f5e698127ff95e9cfba0d3f29339"}, + {file = "coverage-7.2.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cca7c0b7f5881dfe0291ef09ba7bb1582cb92ab0aeffd8afb00c700bf692415a"}, + {file = "coverage-7.2.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b2167d116309f564af56f9aa5e75ef710ef871c5f9b313a83050035097b56820"}, + {file = "coverage-7.2.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:cb5f152fb14857cbe7f3e8c9a5d98979c4c66319a33cad6e617f0067c9accdc4"}, + {file = "coverage-7.2.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:87dc37f16fb5e3a28429e094145bf7c1753e32bb50f662722e378c5851f7fdc6"}, + {file = "coverage-7.2.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:e191a63a05851f8bce77bc875e75457f9b01d42843f8bd7feed2fc26bbe60833"}, + {file = "coverage-7.2.1-cp310-cp310-win32.whl", hash = "sha256:e3ea04b23b114572b98a88c85379e9e9ae031272ba1fb9b532aa934c621626d4"}, + {file = "coverage-7.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:0cf557827be7eca1c38a2480484d706693e7bb1929e129785fe59ec155a59de6"}, + {file = "coverage-7.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:570c21a29493b350f591a4b04c158ce1601e8d18bdcd21db136fbb135d75efa6"}, + {file = "coverage-7.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9e872b082b32065ac2834149dc0adc2a2e6d8203080501e1e3c3c77851b466f9"}, + {file = "coverage-7.2.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fac6343bae03b176e9b58104a9810df3cdccd5cfed19f99adfa807ffbf43cf9b"}, + {file = "coverage-7.2.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:abacd0a738e71b20e224861bc87e819ef46fedba2fb01bc1af83dfd122e9c319"}, + {file = "coverage-7.2.1-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d9256d4c60c4bbfec92721b51579c50f9e5062c21c12bec56b55292464873508"}, + {file = "coverage-7.2.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:80559eaf6c15ce3da10edb7977a1548b393db36cbc6cf417633eca05d84dd1ed"}, + {file = "coverage-7.2.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:0bd7e628f6c3ec4e7d2d24ec0e50aae4e5ae95ea644e849d92ae4805650b4c4e"}, + {file = "coverage-7.2.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:09643fb0df8e29f7417adc3f40aaf379d071ee8f0350ab290517c7004f05360b"}, + {file = "coverage-7.2.1-cp311-cp311-win32.whl", hash = "sha256:1b7fb13850ecb29b62a447ac3516c777b0e7a09ecb0f4bb6718a8654c87dfc80"}, + {file = "coverage-7.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:617a94ada56bbfe547aa8d1b1a2b8299e2ec1ba14aac1d4b26a9f7d6158e1273"}, + {file = "coverage-7.2.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8649371570551d2fd7dee22cfbf0b61f1747cdfb2b7587bb551e4beaaa44cb97"}, + {file = "coverage-7.2.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5d2b9b5e70a21474c105a133ba227c61bc95f2ac3b66861143ce39a5ea4b3f84"}, + {file = "coverage-7.2.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ae82c988954722fa07ec5045c57b6d55bc1a0890defb57cf4a712ced65b26ddd"}, + {file = "coverage-7.2.1-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:861cc85dfbf55a7a768443d90a07e0ac5207704a9f97a8eb753292a7fcbdfcfc"}, + {file = "coverage-7.2.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:0339dc3237c0d31c3b574f19c57985fcbe494280153bbcad33f2cdf469f4ac3e"}, + {file = "coverage-7.2.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:5928b85416a388dd557ddc006425b0c37e8468bd1c3dc118c1a3de42f59e2a54"}, + {file = "coverage-7.2.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:8d3843ca645f62c426c3d272902b9de90558e9886f15ddf5efe757b12dd376f5"}, + {file = "coverage-7.2.1-cp37-cp37m-win32.whl", hash = "sha256:6a034480e9ebd4e83d1aa0453fd78986414b5d237aea89a8fdc35d330aa13bae"}, + {file = "coverage-7.2.1-cp37-cp37m-win_amd64.whl", hash = "sha256:6fce673f79a0e017a4dc35e18dc7bb90bf6d307c67a11ad5e61ca8d42b87cbff"}, + {file = "coverage-7.2.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7f099da6958ddfa2ed84bddea7515cb248583292e16bb9231d151cd528eab657"}, + {file = "coverage-7.2.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:97a3189e019d27e914ecf5c5247ea9f13261d22c3bb0cfcfd2a9b179bb36f8b1"}, + {file = "coverage-7.2.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a81dbcf6c6c877986083d00b834ac1e84b375220207a059ad45d12f6e518a4e3"}, + {file = "coverage-7.2.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:78d2c3dde4c0b9be4b02067185136b7ee4681978228ad5ec1278fa74f5ca3e99"}, + {file = "coverage-7.2.1-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3a209d512d157379cc9ab697cbdbb4cfd18daa3e7eebaa84c3d20b6af0037384"}, + {file = "coverage-7.2.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:f3d07edb912a978915576a776756069dede66d012baa503022d3a0adba1b6afa"}, + {file = "coverage-7.2.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:8dca3c1706670297851bca1acff9618455122246bdae623be31eca744ade05ec"}, + {file = "coverage-7.2.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:b1991a6d64231a3e5bbe3099fb0dd7c9aeaa4275ad0e0aeff4cb9ef885c62ba2"}, + {file = "coverage-7.2.1-cp38-cp38-win32.whl", hash = "sha256:22c308bc508372576ffa3d2dbc4824bb70d28eeb4fcd79d4d1aed663a06630d0"}, + {file = "coverage-7.2.1-cp38-cp38-win_amd64.whl", hash = "sha256:b0c0d46de5dd97f6c2d1b560bf0fcf0215658097b604f1840365296302a9d1fb"}, + {file = "coverage-7.2.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4dd34a935de268a133e4741827ae951283a28c0125ddcdbcbba41c4b98f2dfef"}, + {file = "coverage-7.2.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:0f8318ed0f3c376cfad8d3520f496946977abde080439d6689d7799791457454"}, + {file = "coverage-7.2.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:834c2172edff5a08d78e2f53cf5e7164aacabeb66b369f76e7bb367ca4e2d993"}, + {file = "coverage-7.2.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e4d70c853f0546855f027890b77854508bdb4d6a81242a9d804482e667fff6e6"}, + {file = "coverage-7.2.1-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8a6450da4c7afc4534305b2b7d8650131e130610cea448ff240b6ab73d7eab63"}, + {file = "coverage-7.2.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:99f4dd81b2bb8fc67c3da68b1f5ee1650aca06faa585cbc6818dbf67893c6d58"}, + {file = "coverage-7.2.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:bdd3f2f285ddcf2e75174248b2406189261a79e7fedee2ceeadc76219b6faa0e"}, + {file = "coverage-7.2.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:f29351393eb05e6326f044a7b45ed8e38cb4dcc38570d12791f271399dc41431"}, + {file = "coverage-7.2.1-cp39-cp39-win32.whl", hash = "sha256:e2b50ebc2b6121edf352336d503357321b9d8738bb7a72d06fc56153fd3f4cd8"}, + {file = "coverage-7.2.1-cp39-cp39-win_amd64.whl", hash = "sha256:bd5a12239c0006252244f94863f1c518ac256160cd316ea5c47fb1a11b25889a"}, + {file = "coverage-7.2.1-pp37.pp38.pp39-none-any.whl", hash = "sha256:436313d129db7cf5b4ac355dd2bd3f7c7e5294af077b090b85de75f8458b8616"}, + {file = "coverage-7.2.1.tar.gz", hash = "sha256:c77f2a9093ccf329dd523a9b2b3c854c20d2a3d968b6def3b820272ca6732242"}, +] +filelock = [ + {file = "filelock-3.9.0-py3-none-any.whl", hash = "sha256:f58d535af89bb9ad5cd4df046f741f8553a418c01a7856bf0d173bbc9f6bd16d"}, + {file = "filelock-3.9.0.tar.gz", hash = "sha256:7b319f24340b51f55a2bf7a12ac0755a9b03e718311dac567a0f4f7fabd2f5de"}, +] frozenlist = [ {file = "frozenlist-1.3.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:ff8bf625fe85e119553b5383ba0fb6aa3d0ec2ae980295aaefa552374926b3f4"}, {file = "frozenlist-1.3.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:dfbac4c2dfcc082fcf8d942d1e49b6aa0766c19d3358bd86e2000bf0fa4a9cf0"}, @@ -380,10 +736,22 @@ frozenlist = [ {file = "frozenlist-1.3.3-cp39-cp39-win_amd64.whl", hash = "sha256:cfe33efc9cb900a4c46f91a5ceba26d6df370ffddd9ca386eb1d4f0ad97b9ea9"}, {file = "frozenlist-1.3.3.tar.gz", hash = "sha256:58bcc55721e8a90b88332d6cd441261ebb22342e238296bb330968952fbb3a6a"}, ] +huggingface-hub = [ + {file = "huggingface_hub-0.12.1-py3-none-any.whl", hash = "sha256:867586cc8543fe1bd43a219fedbea7d71690021ad80f0c46f35c4751069278d7"}, + {file = "huggingface_hub-0.12.1.tar.gz", hash = "sha256:6f960f6246ef9c3446d0d6275e853485515682c350917fdaf2a59705f8b9ebb3"}, +] idna = [ {file = "idna-3.4-py3-none-any.whl", hash = "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"}, {file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"}, ] +importlib-metadata = [ + {file = "importlib_metadata-6.0.0-py3-none-any.whl", hash = "sha256:7efb448ec9a5e313a57655d35aa54cd3e01b7e1fbcf72dce1bf06119420f5bad"}, + {file = "importlib_metadata-6.0.0.tar.gz", hash = "sha256:e354bedeb60efa6affdcc8ae121b73544a7aa74156d047311948f6d711cd378d"}, +] +iniconfig = [ + {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"}, + {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"}, +] multidict = [ {file = "multidict-6.0.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0b1a97283e0c85772d613878028fec909f003993e1007eafa715b24b377cb9b8"}, {file = "multidict-6.0.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:eeb6dcc05e911516ae3d1f207d4b0520d07f54484c49dfc294d6e7d63b734171"}, @@ -460,6 +828,18 @@ multidict = [ {file = "multidict-6.0.4-cp39-cp39-win_amd64.whl", hash = "sha256:33029f5734336aa0d4c0384525da0387ef89148dc7191aae00ca5fb23d7aafc2"}, {file = "multidict-6.0.4.tar.gz", hash = "sha256:3666906492efb76453c0e7b97f2cf459b0682e7402c0489a95484965dbc1da49"}, ] +packaging = [ + {file = "packaging-23.0-py3-none-any.whl", hash = "sha256:714ac14496c3e68c99c29b00845f7a2b85f3bb6f1078fd9f72fd20f0570002b2"}, + {file = "packaging-23.0.tar.gz", hash = "sha256:b6ad297f8907de0fa2fe1ccbd26fdaf387f5f47c7275fedf8cce89f99446cf97"}, +] +pluggy = [ + {file = "pluggy-1.0.0-py2.py3-none-any.whl", hash = "sha256:74134bbf457f031a36d68416e1509f34bd5ccc019f0bcc952c7b909d06b37bd3"}, + {file = "pluggy-1.0.0.tar.gz", hash = "sha256:4224373bacce55f955a878bf9cfa763c1e360858e330072059e10bad68531159"}, +] +py = [ + {file = "py-1.11.0-py2.py3-none-any.whl", hash = "sha256:607c53218732647dff4acdfcd50cb62615cedf612e72d1724fb1a0cc6405b378"}, + {file = "py-1.11.0.tar.gz", hash = "sha256:51c75c4126074b472f746a24399ad32f6053d1b34b68d2fa41e558e6f4a98719"}, +] pydantic = [ {file = "pydantic-1.10.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:5920824fe1e21cbb3e38cf0f3dd24857c8959801d1031ce1fac1d50857a03bfb"}, {file = "pydantic-1.10.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:3bb99cf9655b377db1a9e47fa4479e3330ea96f4123c6c8200e482704bf1eda2"}, @@ -498,10 +878,84 @@ pydantic = [ {file = "pydantic-1.10.5-py3-none-any.whl", hash = "sha256:7c5b94d598c90f2f46b3a983ffb46ab806a67099d118ae0da7ef21a2a4033b28"}, {file = "pydantic-1.10.5.tar.gz", hash = "sha256:9e337ac83686645a46db0e825acceea8e02fca4062483f40e9ae178e8bd1103a"}, ] +pytest = [ + {file = "pytest-6.2.5-py3-none-any.whl", hash = "sha256:7310f8d27bc79ced999e760ca304d69f6ba6c6649c0b60fb0e04a4a77cacc134"}, + {file = "pytest-6.2.5.tar.gz", hash = "sha256:131b36680866a76e6781d13f101efb86cf674ebb9762eb70d3082b6f29889e89"}, +] +pytest-asyncio = [ + {file = "pytest-asyncio-0.17.2.tar.gz", hash = "sha256:6d895b02432c028e6957d25fc936494e78c6305736e785d9fee408b1efbc7ff4"}, + {file = "pytest_asyncio-0.17.2-py3-none-any.whl", hash = "sha256:e0fe5dbea40516b661ef1bcfe0bd9461c2847c4ef4bb40012324f2454fb7d56d"}, +] +pytest-cov = [ + {file = "pytest-cov-3.0.0.tar.gz", hash = "sha256:e7f0f5b1617d2210a2cabc266dfe2f4c75a8d32fb89eafb7ad9d06f6d076d470"}, + {file = "pytest_cov-3.0.0-py3-none-any.whl", hash = "sha256:578d5d15ac4a25e5f961c938b85a05b09fdaae9deef3bb6de9a6e766622ca7a6"}, +] +PyYAML = [ + {file = "PyYAML-6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d4db7c7aef085872ef65a8fd7d6d09a14ae91f691dec3e87ee5ee0539d516f53"}, + {file = "PyYAML-6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9df7ed3b3d2e0ecfe09e14741b857df43adb5a3ddadc919a2d94fbdf78fea53c"}, + {file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77f396e6ef4c73fdc33a9157446466f1cff553d979bd00ecb64385760c6babdc"}, + {file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a80a78046a72361de73f8f395f1f1e49f956c6be882eed58505a15f3e430962b"}, + {file = "PyYAML-6.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f84fbc98b019fef2ee9a1cb3ce93e3187a6df0b2538a651bfb890254ba9f90b5"}, + {file = "PyYAML-6.0-cp310-cp310-win32.whl", hash = "sha256:2cd5df3de48857ed0544b34e2d40e9fac445930039f3cfe4bcc592a1f836d513"}, + {file = "PyYAML-6.0-cp310-cp310-win_amd64.whl", hash = "sha256:daf496c58a8c52083df09b80c860005194014c3698698d1a57cbcfa182142a3a"}, + {file = "PyYAML-6.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d4b0ba9512519522b118090257be113b9468d804b19d63c71dbcf4a48fa32358"}, + {file = "PyYAML-6.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:81957921f441d50af23654aa6c5e5eaf9b06aba7f0a19c18a538dc7ef291c5a1"}, + {file = "PyYAML-6.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:afa17f5bc4d1b10afd4466fd3a44dc0e245382deca5b3c353d8b757f9e3ecb8d"}, + {file = "PyYAML-6.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dbad0e9d368bb989f4515da330b88a057617d16b6a8245084f1b05400f24609f"}, + {file = "PyYAML-6.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:432557aa2c09802be39460360ddffd48156e30721f5e8d917f01d31694216782"}, + {file = "PyYAML-6.0-cp311-cp311-win32.whl", hash = "sha256:bfaef573a63ba8923503d27530362590ff4f576c626d86a9fed95822a8255fd7"}, + {file = "PyYAML-6.0-cp311-cp311-win_amd64.whl", hash = "sha256:01b45c0191e6d66c470b6cf1b9531a771a83c1c4208272ead47a3ae4f2f603bf"}, + {file = "PyYAML-6.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:897b80890765f037df3403d22bab41627ca8811ae55e9a722fd0392850ec4d86"}, + {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:50602afada6d6cbfad699b0c7bb50d5ccffa7e46a3d738092afddc1f9758427f"}, + {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:48c346915c114f5fdb3ead70312bd042a953a8ce5c7106d5bfb1a5254e47da92"}, + {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:98c4d36e99714e55cfbaaee6dd5badbc9a1ec339ebfc3b1f52e293aee6bb71a4"}, + {file = "PyYAML-6.0-cp36-cp36m-win32.whl", hash = "sha256:0283c35a6a9fbf047493e3a0ce8d79ef5030852c51e9d911a27badfde0605293"}, + {file = "PyYAML-6.0-cp36-cp36m-win_amd64.whl", hash = "sha256:07751360502caac1c067a8132d150cf3d61339af5691fe9e87803040dbc5db57"}, + {file = "PyYAML-6.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:819b3830a1543db06c4d4b865e70ded25be52a2e0631ccd2f6a47a2822f2fd7c"}, + {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:473f9edb243cb1935ab5a084eb238d842fb8f404ed2193a915d1784b5a6b5fc0"}, + {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0ce82d761c532fe4ec3f87fc45688bdd3a4c1dc5e0b4a19814b9009a29baefd4"}, + {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:231710d57adfd809ef5d34183b8ed1eeae3f76459c18fb4a0b373ad56bedcdd9"}, + {file = "PyYAML-6.0-cp37-cp37m-win32.whl", hash = "sha256:c5687b8d43cf58545ade1fe3e055f70eac7a5a1a0bf42824308d868289a95737"}, + {file = "PyYAML-6.0-cp37-cp37m-win_amd64.whl", hash = "sha256:d15a181d1ecd0d4270dc32edb46f7cb7733c7c508857278d3d378d14d606db2d"}, + {file = "PyYAML-6.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:0b4624f379dab24d3725ffde76559cff63d9ec94e1736b556dacdfebe5ab6d4b"}, + {file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:213c60cd50106436cc818accf5baa1aba61c0189ff610f64f4a3e8c6726218ba"}, + {file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9fa600030013c4de8165339db93d182b9431076eb98eb40ee068700c9c813e34"}, + {file = "PyYAML-6.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:277a0ef2981ca40581a47093e9e2d13b3f1fbbeffae064c1d21bfceba2030287"}, + {file = "PyYAML-6.0-cp38-cp38-win32.whl", hash = "sha256:d4eccecf9adf6fbcc6861a38015c2a64f38b9d94838ac1810a9023a0609e1b78"}, + {file = "PyYAML-6.0-cp38-cp38-win_amd64.whl", hash = "sha256:1e4747bc279b4f613a09eb64bba2ba602d8a6664c6ce6396a4d0cd413a50ce07"}, + {file = "PyYAML-6.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:055d937d65826939cb044fc8c9b08889e8c743fdc6a32b33e2390f66013e449b"}, + {file = "PyYAML-6.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e61ceaab6f49fb8bdfaa0f92c4b57bcfbea54c09277b1b4f7ac376bfb7a7c174"}, + {file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d67d839ede4ed1b28a4e8909735fc992a923cdb84e618544973d7dfc71540803"}, + {file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cba8c411ef271aa037d7357a2bc8f9ee8b58b9965831d9e51baf703280dc73d3"}, + {file = "PyYAML-6.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:40527857252b61eacd1d9af500c3337ba8deb8fc298940291486c465c8b46ec0"}, + {file = "PyYAML-6.0-cp39-cp39-win32.whl", hash = "sha256:b5b9eccad747aabaaffbc6064800670f0c297e52c12754eb1d976c57e4f74dcb"}, + {file = "PyYAML-6.0-cp39-cp39-win_amd64.whl", hash = "sha256:b3d267842bf12586ba6c734f89d1f5b871df0273157918b0ccefa29deb05c21c"}, + {file = "PyYAML-6.0.tar.gz", hash = "sha256:68fb519c14306fec9720a2a5b45bc9f0c8d1b9c72adf45c37baedfcd949c35a2"}, +] +requests = [ + {file = "requests-2.28.2-py3-none-any.whl", hash = "sha256:64299f4909223da747622c030b781c0d7811e359c37124b4bd368fb8c6518baa"}, + {file = "requests-2.28.2.tar.gz", hash = "sha256:98b1b2782e3c6c4904938b84c0eb932721069dfdb9134313beff7c83c2df24bf"}, +] +toml = [ + {file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"}, + {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"}, +] +tomli = [ + {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"}, + {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"}, +] +tqdm = [ + {file = "tqdm-4.65.0-py3-none-any.whl", hash = "sha256:c4f53a17fe37e132815abceec022631be8ffe1b9381c2e6e30aa70edc99e9671"}, + {file = "tqdm-4.65.0.tar.gz", hash = "sha256:1871fb68a86b8fb3b59ca4cdd3dcccbc7e6d613eeed31f4c332531977b89beb5"}, +] typing-extensions = [ {file = "typing_extensions-4.5.0-py3-none-any.whl", hash = "sha256:fb33085c39dd998ac16d1431ebc293a8b3eedd00fd4a32de0ff79002c19511b4"}, {file = "typing_extensions-4.5.0.tar.gz", hash = "sha256:5cb5f4a79139d699607b3ef622a1dedafa84e115ab0024e0d9c044a9479ca7cb"}, ] +urllib3 = [ + {file = "urllib3-1.26.14-py2.py3-none-any.whl", hash = "sha256:75edcdc2f7d85b137124a6c3c9fc3933cdeaa12ecb9a6a959f22797a0feca7e1"}, + {file = "urllib3-1.26.14.tar.gz", hash = "sha256:076907bf8fd355cde77728471316625a4d2f7e713c125f51953bb5b3eecf4f72"}, +] yarl = [ {file = "yarl-1.8.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:bb81f753c815f6b8e2ddd2eef3c855cf7da193b82396ac013c661aaa6cc6b0a5"}, {file = "yarl-1.8.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:47d49ac96156f0928f002e2424299b2c91d9db73e08c4cd6742923a086f1c863"}, @@ -578,3 +1032,7 @@ yarl = [ {file = "yarl-1.8.2-cp39-cp39-win_amd64.whl", hash = "sha256:6604711362f2dbf7160df21c416f81fac0de6dbcf0b5445a2ef25478ecc4c778"}, {file = "yarl-1.8.2.tar.gz", hash = "sha256:49d43402c6e3013ad0978602bf6bf5328535c48d192304b91b97a3c6790b1562"}, ] +zipp = [ + {file = "zipp-3.15.0-py3-none-any.whl", hash = "sha256:48904fc76a60e542af151aded95726c1a5c34ed43ab4134b597665c86d7ad556"}, + {file = "zipp-3.15.0.tar.gz", hash = "sha256:112929ad649da941c23de50f356a2b5570c954b65150642bccdd66bf194d224b"}, +] diff --git a/clients/python/pyproject.toml b/clients/python/pyproject.toml index 226ab0b7..895a351b 100644 --- a/clients/python/pyproject.toml +++ b/clients/python/pyproject.toml @@ -1,14 +1,25 @@ [tool.poetry] name = "text-generation" version = "0.3.2" -description = "Text Generation Inference Python Client" +description = "Hugging Face Text Generation Python Client" +license = "Apache-2.0" authors = ["Olivier Dehaene "] +maintainers = ["Olivier Dehaene "] +readme = "README.md" +homepage = "https://github.com/huggingface/text-generation-inference" +repository = "https://github.com/huggingface/text-generation-inference" + [tool.poetry.dependencies] -python = "^3.9" +python = "^3.7" pydantic = "^1.10.5" aiohttp = "^3.8.4" +huggingface-hub = "^0.12.1" +[tool.poetry.dev-dependencies] +pytest = "^6.2.5" +pytest-asyncio = "^0.17.2" +pytest-cov = "^3.0.0" [build-system] requires = ["poetry-core"] diff --git a/clients/python/tests/conftest.py b/clients/python/tests/conftest.py new file mode 100644 index 00000000..7aa296cf --- /dev/null +++ b/clients/python/tests/conftest.py @@ -0,0 +1,46 @@ +import pytest + +from text_generation import __version__ +from huggingface_hub.utils import build_hf_headers + + +@pytest.fixture +def bloom_model(): + return "bigscience/bloom" + + +@pytest.fixture +def fake_model(): + return "fake/model" + + +@pytest.fixture +def unsupported_model(): + return "gpt2" + + +@pytest.fixture +def base_url(): + return "https://api-inference.huggingface.co/models" + + +@pytest.fixture +def bloom_url(base_url, bloom_model): + return f"{base_url}/{bloom_model}" + + +@pytest.fixture +def fake_url(base_url, fake_model): + return f"{base_url}/{fake_model}" + + +@pytest.fixture +def unsupported_url(base_url, unsupported_model): + return f"{base_url}/{unsupported_model}" + + +@pytest.fixture(scope="session") +def hf_headers(): + return build_hf_headers( + library_name="text-generation-tests", library_version=__version__ + ) diff --git a/clients/python/tests/test_api_inference.py b/clients/python/tests/test_api_inference.py new file mode 100644 index 00000000..67a5dbea --- /dev/null +++ b/clients/python/tests/test_api_inference.py @@ -0,0 +1,34 @@ +import pytest + +from text_generation import ( + InferenceAPIClient, + InferenceAPIAsyncClient, + Client, + AsyncClient, +) +from text_generation.errors import NotSupportedError +from text_generation.api_inference import get_supported_models + + +def test_get_supported_models(): + assert isinstance(get_supported_models(), list) + + +def test_client(bloom_model): + client = InferenceAPIClient(bloom_model) + assert isinstance(client, Client) + + +def test_client_unsupported_model(unsupported_model): + with pytest.raises(NotSupportedError): + InferenceAPIClient(unsupported_model) + + +def test_async_client(bloom_model): + client = InferenceAPIAsyncClient(bloom_model) + assert isinstance(client, AsyncClient) + + +def test_async_client_unsupported_model(unsupported_model): + with pytest.raises(NotSupportedError): + InferenceAPIAsyncClient(unsupported_model) diff --git a/clients/python/tests/test_client.py b/clients/python/tests/test_client.py new file mode 100644 index 00000000..e9a6684d --- /dev/null +++ b/clients/python/tests/test_client.py @@ -0,0 +1,127 @@ +import pytest + +from text_generation import Client, AsyncClient +from text_generation.errors import NotFoundError, ValidationError +from text_generation.types import FinishReason, PrefillToken, Token + + +def test_generate(bloom_url, hf_headers): + client = Client(bloom_url, hf_headers) + response = client.generate("test", max_new_tokens=1) + + assert response.generated_text == "." + assert response.details.finish_reason == FinishReason.Length + assert response.details.generated_tokens == 1 + assert response.details.seed is None + assert len(response.details.prefill) == 1 + assert response.details.prefill[0] == PrefillToken( + id=9234, text="test", logprob=None + ) + assert len(response.details.tokens) == 1 + assert response.details.tokens[0] == Token( + id=17, text=".", logprob=-1.75, special=False + ) + + +def test_generate_not_found(fake_url, hf_headers): + client = Client(fake_url, hf_headers) + with pytest.raises(NotFoundError): + client.generate("test") + + +def test_generate_validation_error(bloom_url, hf_headers): + client = Client(bloom_url, hf_headers) + with pytest.raises(ValidationError): + client.generate("test", max_new_tokens=10_000) + + +def test_generate_stream(bloom_url, hf_headers): + client = Client(bloom_url, hf_headers) + responses = [ + response for response in client.generate_stream("test", max_new_tokens=1) + ] + + assert len(responses) == 1 + response = responses[0] + + assert response.generated_text == "." + assert response.details.finish_reason == FinishReason.Length + assert response.details.generated_tokens == 1 + assert response.details.seed is None + + +def test_generate_stream_not_found(fake_url, hf_headers): + client = Client(fake_url, hf_headers) + with pytest.raises(NotFoundError): + list(client.generate_stream("test")) + + +def test_generate_stream_validation_error(bloom_url, hf_headers): + client = Client(bloom_url, hf_headers) + with pytest.raises(ValidationError): + list(client.generate_stream("test", max_new_tokens=10_000)) + + +@pytest.mark.asyncio +async def test_generate_async(bloom_url, hf_headers): + client = AsyncClient(bloom_url, hf_headers) + response = await client.generate("test", max_new_tokens=1) + + assert response.generated_text == "." + assert response.details.finish_reason == FinishReason.Length + assert response.details.generated_tokens == 1 + assert response.details.seed is None + assert len(response.details.prefill) == 1 + assert response.details.prefill[0] == PrefillToken( + id=9234, text="test", logprob=None + ) + assert len(response.details.tokens) == 1 + assert response.details.tokens[0] == Token( + id=17, text=".", logprob=-1.75, special=False + ) + + +@pytest.mark.asyncio +async def test_generate_async_not_found(fake_url, hf_headers): + client = AsyncClient(fake_url, hf_headers) + with pytest.raises(NotFoundError): + await client.generate("test") + + +@pytest.mark.asyncio +async def test_generate_async_validation_error(bloom_url, hf_headers): + client = AsyncClient(bloom_url, hf_headers) + with pytest.raises(ValidationError): + await client.generate("test", max_new_tokens=10_000) + + +@pytest.mark.asyncio +async def test_generate_stream_async(bloom_url, hf_headers): + client = AsyncClient(bloom_url, hf_headers) + responses = [ + response async for response in client.generate_stream("test", max_new_tokens=1) + ] + + assert len(responses) == 1 + response = responses[0] + + assert response.generated_text == "." + assert response.details.finish_reason == FinishReason.Length + assert response.details.generated_tokens == 1 + assert response.details.seed is None + + +@pytest.mark.asyncio +async def test_generate_stream_async_not_found(fake_url, hf_headers): + client = AsyncClient(fake_url, hf_headers) + with pytest.raises(NotFoundError): + async for _ in client.generate_stream("test"): + pass + + +@pytest.mark.asyncio +async def test_generate_stream_async_validation_error(bloom_url, hf_headers): + client = AsyncClient(bloom_url, hf_headers) + with pytest.raises(ValidationError): + async for _ in client.generate_stream("test", max_new_tokens=10_000): + pass diff --git a/clients/python/tests/test_errors.py b/clients/python/tests/test_errors.py new file mode 100644 index 00000000..8389ed31 --- /dev/null +++ b/clients/python/tests/test_errors.py @@ -0,0 +1,64 @@ +from text_generation.errors import ( + parse_error, + GenerationError, + IncompleteGenerationError, + OverloadedError, + ValidationError, + BadRequestError, + ShardNotReadyError, + ShardTimeoutError, + NotFoundError, + RateLimitExceededError, + UnknownError, +) + + +def test_generation_error(): + payload = {"error_type": "generation", "error": "test"} + assert isinstance(parse_error(400, payload), GenerationError) + + +def test_incomplete_generation_error(): + payload = {"error_type": "incomplete_generation", "error": "test"} + assert isinstance(parse_error(400, payload), IncompleteGenerationError) + + +def test_overloaded_error(): + payload = {"error_type": "overloaded", "error": "test"} + assert isinstance(parse_error(400, payload), OverloadedError) + + +def test_validation_error(): + payload = {"error_type": "validation", "error": "test"} + assert isinstance(parse_error(400, payload), ValidationError) + + +def test_bad_request_error(): + payload = {"error": "test"} + assert isinstance(parse_error(400, payload), BadRequestError) + + +def test_shard_not_ready_error(): + payload = {"error": "test"} + assert isinstance(parse_error(403, payload), ShardNotReadyError) + assert isinstance(parse_error(424, payload), ShardNotReadyError) + + +def test_shard_timeout_error(): + payload = {"error": "test"} + assert isinstance(parse_error(504, payload), ShardTimeoutError) + + +def test_not_found_error(): + payload = {"error": "test"} + assert isinstance(parse_error(404, payload), NotFoundError) + + +def test_rate_limit_exceeded_error(): + payload = {"error": "test"} + assert isinstance(parse_error(429, payload), RateLimitExceededError) + + +def test_unknown_error(): + payload = {"error": "test"} + assert isinstance(parse_error(500, payload), UnknownError) diff --git a/clients/python/tests/test_types.py b/clients/python/tests/test_types.py new file mode 100644 index 00000000..d319b570 --- /dev/null +++ b/clients/python/tests/test_types.py @@ -0,0 +1,39 @@ +import pytest + +from text_generation.types import Parameters +from text_generation.errors import ValidationError + + +def test_parameters_validation(): + # Test repetition_penalty + Parameters(repetition_penalty=1) + with pytest.raises(ValidationError): + Parameters(repetition_penalty=0) + with pytest.raises(ValidationError): + Parameters(repetition_penalty=-1) + + # Test seed + Parameters(seed=1) + with pytest.raises(ValidationError): + Parameters(seed=-1) + + # Test temperature + Parameters(temperature=1) + with pytest.raises(ValidationError): + Parameters(temperature=0) + with pytest.raises(ValidationError): + Parameters(temperature=-1) + + # Test top_k + Parameters(top_k=1) + with pytest.raises(ValidationError): + Parameters(top_k=0) + with pytest.raises(ValidationError): + Parameters(top_k=-1) + + # Test top_p + Parameters(top_p=1) + with pytest.raises(ValidationError): + Parameters(top_p=0) + with pytest.raises(ValidationError): + Parameters(top_p=-1) diff --git a/clients/python/text_generation/__init__.py b/clients/python/text_generation/__init__.py index 493547a2..0ef7d9fc 100644 --- a/clients/python/text_generation/__init__.py +++ b/clients/python/text_generation/__init__.py @@ -1,2 +1,18 @@ +# Copyright 2023 The HuggingFace Team. All rights reserved. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +__version__ = "0.3.2" + from text_generation.client import Client, AsyncClient -from text_generation.api_inference import APIInferenceAsyncClient +from text_generation.api_inference import InferenceAPIClient, InferenceAPIAsyncClient diff --git a/clients/python/text_generation/api_inference.py b/clients/python/text_generation/api_inference.py index ce7937d5..bc6022b3 100644 --- a/clients/python/text_generation/api_inference.py +++ b/clients/python/text_generation/api_inference.py @@ -5,8 +5,9 @@ import json import warnings from typing import List, Optional +from huggingface_hub.utils import build_hf_headers -from text_generation import Client, AsyncClient +from text_generation import Client, AsyncClient, __version__ from text_generation.errors import NotSupportedError INFERENCE_ENDPOINT = os.environ.get( @@ -17,6 +18,12 @@ SUPPORTED_MODELS = None def get_supported_models() -> Optional[List[str]]: + """ + Get the list of supported text-generation models from GitHub + + Returns: + Optional[List[str]]: supported models list or None if unable to get the list from GitHub + """ global SUPPORTED_MODELS if SUPPORTED_MODELS is not None: return SUPPORTED_MODELS @@ -34,31 +41,110 @@ def get_supported_models() -> Optional[List[str]]: return None -class APIInferenceClient(Client): - def __init__(self, model_id: str, token: Optional[str] = None, timeout: int = 10): +class InferenceAPIClient(Client): + """Client to make calls to the HuggingFace Inference API. + + Only supports a subset of the available text-generation or text2text-generation models that are served using + text-generation-inference + + Example: + + ```python + >>> from text_generation import InferenceAPIClient + + >>> client = InferenceAPIClient("bigscience/bloomz") + >>> client.generate("Why is the sky blue?").generated_text + ' Rayleigh scattering' + + >>> result = "" + >>> for response in client.generate_stream("Why is the sky blue?"): + >>> if not response.token.special: + >>> result += response.token.text + >>> result + ' Rayleigh scattering' + ``` + """ + + def __init__(self, repo_id: str, token: Optional[str] = None, timeout: int = 10): + """ + Init headers and API information + + Args: + repo_id (`str`): + Id of repository (e.g. `bigscience/bloom`). + token (`str`, `optional`): + The API token to use as HTTP bearer authorization. This is not + the authentication token. You can find the token in + https://huggingface.co/settings/token. Alternatively, you can + find both your organizations and personal API tokens using + `HfApi().whoami(token)`. + timeout (`int`): + Timeout in seconds + """ + # Text Generation Inference client only supports a subset of the available hub models supported_models = get_supported_models() - if supported_models is not None and model_id not in supported_models: - raise NotSupportedError(model_id) + if supported_models is not None and repo_id not in supported_models: + raise NotSupportedError(repo_id) - headers = {} - if token is not None: - headers = {"Authorization": f"Bearer {token}"} - base_url = f"{INFERENCE_ENDPOINT}/models/{model_id}" + headers = build_hf_headers( + token=token, library_name="text-generation", library_version=__version__ + ) + base_url = f"{INFERENCE_ENDPOINT}/models/{repo_id}" - super(APIInferenceClient, self).__init__(base_url, headers, timeout) + super(InferenceAPIClient, self).__init__(base_url, headers, timeout) -class APIInferenceAsyncClient(AsyncClient): - def __init__(self, model_id: str, token: Optional[str] = None, timeout: int = 10): +class InferenceAPIAsyncClient(AsyncClient): + """Aynschronous Client to make calls to the HuggingFace Inference API. + + Only supports a subset of the available text-generation or text2text-generation models that are served using + text-generation-inference + + Example: + + ```python + >>> from text_generation import InferenceAPIAsyncClient + + >>> client = InferenceAPIAsyncClient("bigscience/bloomz") + >>> response = await client.generate("Why is the sky blue?") + >>> response.generated_text + ' Rayleigh scattering' + + >>> result = "" + >>> async for response in client.generate_stream("Why is the sky blue?"): + >>> if not response.token.special: + >>> result += response.token.text + >>> result + ' Rayleigh scattering' + ``` + """ + + def __init__(self, repo_id: str, token: Optional[str] = None, timeout: int = 10): + """ + Init headers and API information + + Args: + repo_id (`str`): + Id of repository (e.g. `bigscience/bloom`). + token (`str`, `optional`): + The API token to use as HTTP bearer authorization. This is not + the authentication token. You can find the token in + https://huggingface.co/settings/token. Alternatively, you can + find both your organizations and personal API tokens using + `HfApi().whoami(token)`. + timeout (`int`): + Timeout in seconds + """ + # Text Generation Inference client only supports a subset of the available hub models supported_models = get_supported_models() - if supported_models is not None and model_id not in supported_models: - raise NotSupportedError(model_id) + if supported_models is not None and repo_id not in supported_models: + raise NotSupportedError(repo_id) - headers = {} - if token is not None: - headers = {"Authorization": f"Bearer {token}"} - base_url = f"{INFERENCE_ENDPOINT}/models/{model_id}" + headers = build_hf_headers( + token=token, library_name="text-generation", library_version=__version__ + ) + base_url = f"{INFERENCE_ENDPOINT}/models/{repo_id}" - super(APIInferenceAsyncClient, self).__init__(base_url, headers, timeout) + super(InferenceAPIAsyncClient, self).__init__(base_url, headers, timeout) diff --git a/clients/python/text_generation/client.py b/clients/python/text_generation/client.py index dbfd5dce..d0a67915 100644 --- a/clients/python/text_generation/client.py +++ b/clients/python/text_generation/client.py @@ -15,9 +15,38 @@ from text_generation.errors import parse_error class Client: + """Client to make calls to a text-generation-inference instance + + Example: + + ```python + >>> from text_generation import Client + + >>> client = Client("https://api-inference.huggingface.co/models/bigscience/bloomz") + >>> client.generate("Why is the sky blue?").generated_text + ' Rayleigh scattering' + + >>> result = "" + >>> for response in client.generate_stream("Why is the sky blue?"): + >>> if not response.token.special: + >>> result += response.token.text + >>> result + ' Rayleigh scattering' + ``` + """ + def __init__( - self, base_url: str, headers: Dict[str, str] = None, timeout: int = 10 + self, base_url: str, headers: Optional[Dict[str, str]] = None, timeout: int = 10 ): + """ + Args: + base_url (`str`): + text-generation-inference instance base url + headers (`Optional[Dict[str, str]]`): + Additional headers + timeout (`int`): + Timeout in seconds + """ self.base_url = base_url self.headers = headers self.timeout = timeout @@ -30,12 +59,45 @@ class Client: repetition_penalty: Optional[float] = None, return_full_text: bool = False, seed: Optional[int] = None, - stop: Optional[List[str]] = None, + stop_sequences: Optional[List[str]] = None, temperature: Optional[float] = None, top_k: Optional[int] = None, top_p: Optional[float] = None, - watermark: bool = False, + watermarking: bool = False, ) -> Response: + """ + Given a prompt, generate the following text + + Args: + prompt (`str`): + Input text + do_sample (`bool`): + Activate logits sampling + max_new_tokens (`int`): + Maximum number of generated tokens + repetition_penalty (`float`): + The parameter for repetition penalty. 1.0 means no penalty. See [this + paper](https://arxiv.org/pdf/1909.05858.pdf) for more details. + return_full_text (`bool`): + Whether to prepend the prompt to the generated text + seed (`int`): + Random sampling seed + stop_sequences (`List[str]`): + Stop generating tokens if a member of `stop_sequences` is generated + temperature (`float`): + The value used to module the logits distribution. + top_k (`int`): + The number of highest probability vocabulary tokens to keep for top-k-filtering. + top_p (`float`): + If set to < 1, only the smallest set of most probable tokens with probabilities that add up to `top_p` or + higher are kept for generation. + watermarking (`bool`): + Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226) + + Returns: + Response: generated response + """ + # Validate parameters parameters = Parameters( details=True, do_sample=do_sample, @@ -43,11 +105,11 @@ class Client: repetition_penalty=repetition_penalty, return_full_text=return_full_text, seed=seed, - stop=stop if stop is not None else [], + stop=stop_sequences if stop_sequences is not None else [], temperature=temperature, top_k=top_k, top_p=top_p, - watermark=watermark, + watermark=watermarking, ) request = Request(inputs=prompt, stream=False, parameters=parameters) @@ -70,12 +132,45 @@ class Client: repetition_penalty: Optional[float] = None, return_full_text: bool = False, seed: Optional[int] = None, - stop: Optional[List[str]] = None, + stop_sequences: Optional[List[str]] = None, temperature: Optional[float] = None, top_k: Optional[int] = None, top_p: Optional[float] = None, - watermark: bool = False, + watermarking: bool = False, ) -> Iterator[StreamResponse]: + """ + Given a prompt, generate the following stream of tokens + + Args: + prompt (`str`): + Input text + do_sample (`bool`): + Activate logits sampling + max_new_tokens (`int`): + Maximum number of generated tokens + repetition_penalty (`float`): + The parameter for repetition penalty. 1.0 means no penalty. See [this + paper](https://arxiv.org/pdf/1909.05858.pdf) for more details. + return_full_text (`bool`): + Whether to prepend the prompt to the generated text + seed (`int`): + Random sampling seed + stop_sequences (`List[str]`): + Stop generating tokens if a member of `stop_sequences` is generated + temperature (`float`): + The value used to module the logits distribution. + top_k (`int`): + The number of highest probability vocabulary tokens to keep for top-k-filtering. + top_p (`float`): + If set to < 1, only the smallest set of most probable tokens with probabilities that add up to `top_p` or + higher are kept for generation. + watermarking (`bool`): + Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226) + + Returns: + Iterator[StreamResponse]: stream of generated tokens + """ + # Validate parameters parameters = Parameters( details=True, do_sample=do_sample, @@ -83,11 +178,11 @@ class Client: repetition_penalty=repetition_penalty, return_full_text=return_full_text, seed=seed, - stop=stop if stop is not None else [], + stop=stop_sequences if stop_sequences is not None else [], temperature=temperature, top_k=top_k, top_p=top_p, - watermark=watermark, + watermark=watermarking, ) request = Request(inputs=prompt, stream=True, parameters=parameters) @@ -96,31 +191,67 @@ class Client: json=request.dict(), headers=self.headers, timeout=self.timeout, - stream=True, + stream=False, ) if resp.status_code != 200: raise parse_error(resp.status_code, resp.json()) + # Parse ServerSentEvents for byte_payload in resp.iter_lines(): + # Skip line if byte_payload == b"\n": continue payload = byte_payload.decode("utf-8") + # Event data if payload.startswith("data:"): + # Decode payload json_payload = json.loads(payload.lstrip("data:").rstrip("/n")) + # Parse payload try: response = StreamResponse(**json_payload) except ValidationError: + # If we failed to parse the payload, then it is an error payload raise parse_error(resp.status_code, json_payload) yield response class AsyncClient: + """Asynchronous Client to make calls to a text-generation-inference instance + + Example: + + ```python + >>> from text_generation import AsyncClient + + >>> client = AsyncClient("https://api-inference.huggingface.co/models/bigscience/bloomz") + >>> response = await client.generate("Why is the sky blue?") + >>> response.generated_text + ' Rayleigh scattering' + + >>> result = "" + >>> async for response in client.generate_stream("Why is the sky blue?"): + >>> if not response.token.special: + >>> result += response.token.text + >>> result + ' Rayleigh scattering' + ``` + """ + def __init__( - self, base_url: str, headers: Dict[str, str] = None, timeout: int = 10 + self, base_url: str, headers: Optional[Dict[str, str]] = None, timeout: int = 10 ): + """ + Args: + base_url (`str`): + text-generation-inference instance base url + headers (`Optional[Dict[str, str]]`): + Additional headers + timeout (`int`): + Timeout in seconds + """ self.base_url = base_url self.headers = headers self.timeout = ClientTimeout(timeout * 60) @@ -133,12 +264,45 @@ class AsyncClient: repetition_penalty: Optional[float] = None, return_full_text: bool = False, seed: Optional[int] = None, - stop: Optional[List[str]] = None, + stop_sequences: Optional[List[str]] = None, temperature: Optional[float] = None, top_k: Optional[int] = None, top_p: Optional[float] = None, - watermark: bool = False, + watermarking: bool = False, ) -> Response: + """ + Given a prompt, generate the following text asynchronously + + Args: + prompt (`str`): + Input text + do_sample (`bool`): + Activate logits sampling + max_new_tokens (`int`): + Maximum number of generated tokens + repetition_penalty (`float`): + The parameter for repetition penalty. 1.0 means no penalty. See [this + paper](https://arxiv.org/pdf/1909.05858.pdf) for more details. + return_full_text (`bool`): + Whether to prepend the prompt to the generated text + seed (`int`): + Random sampling seed + stop_sequences (`List[str]`): + Stop generating tokens if a member of `stop_sequences` is generated + temperature (`float`): + The value used to module the logits distribution. + top_k (`int`): + The number of highest probability vocabulary tokens to keep for top-k-filtering. + top_p (`float`): + If set to < 1, only the smallest set of most probable tokens with probabilities that add up to `top_p` or + higher are kept for generation. + watermarking (`bool`): + Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226) + + Returns: + Response: generated response + """ + # Validate parameters parameters = Parameters( details=True, do_sample=do_sample, @@ -146,17 +310,18 @@ class AsyncClient: repetition_penalty=repetition_penalty, return_full_text=return_full_text, seed=seed, - stop=stop if stop is not None else [], + stop=stop_sequences if stop_sequences is not None else [], temperature=temperature, top_k=top_k, top_p=top_p, - watermark=watermark, + watermark=watermarking, ) request = Request(inputs=prompt, stream=False, parameters=parameters) async with ClientSession(headers=self.headers, timeout=self.timeout) as session: async with session.post(self.base_url, json=request.dict()) as resp: payload = await resp.json() + if resp.status != 200: raise parse_error(resp.status, payload) return Response(**payload[0]) @@ -169,12 +334,45 @@ class AsyncClient: repetition_penalty: Optional[float] = None, return_full_text: bool = False, seed: Optional[int] = None, - stop: Optional[List[str]] = None, + stop_sequences: Optional[List[str]] = None, temperature: Optional[float] = None, top_k: Optional[int] = None, top_p: Optional[float] = None, - watermark: bool = False, + watermarking: bool = False, ) -> AsyncIterator[StreamResponse]: + """ + Given a prompt, generate the following stream of tokens asynchronously + + Args: + prompt (`str`): + Input text + do_sample (`bool`): + Activate logits sampling + max_new_tokens (`int`): + Maximum number of generated tokens + repetition_penalty (`float`): + The parameter for repetition penalty. 1.0 means no penalty. See [this + paper](https://arxiv.org/pdf/1909.05858.pdf) for more details. + return_full_text (`bool`): + Whether to prepend the prompt to the generated text + seed (`int`): + Random sampling seed + stop_sequences (`List[str]`): + Stop generating tokens if a member of `stop_sequences` is generated + temperature (`float`): + The value used to module the logits distribution. + top_k (`int`): + The number of highest probability vocabulary tokens to keep for top-k-filtering. + top_p (`float`): + If set to < 1, only the smallest set of most probable tokens with probabilities that add up to `top_p` or + higher are kept for generation. + watermarking (`bool`): + Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226) + + Returns: + AsyncIterator[StreamResponse]: stream of generated tokens + """ + # Validate parameters parameters = Parameters( details=True, do_sample=do_sample, @@ -182,29 +380,36 @@ class AsyncClient: repetition_penalty=repetition_penalty, return_full_text=return_full_text, seed=seed, - stop=stop if stop is not None else [], + stop=stop_sequences if stop_sequences is not None else [], temperature=temperature, top_k=top_k, top_p=top_p, - watermark=watermark, + watermark=watermarking, ) request = Request(inputs=prompt, stream=True, parameters=parameters) async with ClientSession(headers=self.headers, timeout=self.timeout) as session: async with session.post(self.base_url, json=request.dict()) as resp: + if resp.status != 200: raise parse_error(resp.status, await resp.json()) + # Parse ServerSentEvents async for byte_payload in resp.content: + # Skip line if byte_payload == b"\n": continue payload = byte_payload.decode("utf-8") + # Event data if payload.startswith("data:"): + # Decode payload json_payload = json.loads(payload.lstrip("data:").rstrip("/n")) + # Parse payload try: response = StreamResponse(**json_payload) except ValidationError: + # If we failed to parse the payload, then it is an error payload raise parse_error(resp.status, json_payload) yield response diff --git a/clients/python/text_generation/errors.py b/clients/python/text_generation/errors.py index c4289ce6..dbf0b761 100644 --- a/clients/python/text_generation/errors.py +++ b/clients/python/text_generation/errors.py @@ -33,7 +33,7 @@ class ShardNotReadyError(Exception): super().__init__(message) -class TimeoutError(Exception): +class ShardTimeoutError(Exception): def __init__(self, message: str): super().__init__(message) @@ -64,6 +64,19 @@ class UnknownError(Exception): def parse_error(status_code: int, payload: Dict[str, str]) -> Exception: + """ + Parse error given an HTTP status code and a json payload + + Args: + status_code (`int`): + HTTP status code + payload (`Dict[str, str]`): + Json payload + + Returns: + Exception: parsed exception + + """ # Try to parse a Text Generation Inference error message = payload["error"] if "error_type" in payload: @@ -83,7 +96,7 @@ def parse_error(status_code: int, payload: Dict[str, str]) -> Exception: if status_code == 403 or status_code == 424: return ShardNotReadyError(message) if status_code == 504: - return TimeoutError(message) + return ShardTimeoutError(message) if status_code == 404: return NotFoundError(message) if status_code == 429: diff --git a/clients/python/text_generation/types.py b/clients/python/text_generation/types.py index 86d0962e..d276b60e 100644 --- a/clients/python/text_generation/types.py +++ b/clients/python/text_generation/types.py @@ -10,7 +10,7 @@ class Parameters(BaseModel): max_new_tokens: int = 20 repetition_penalty: Optional[float] = None return_full_text: bool = False - stop: List[str] + stop: List[str] = [] seed: Optional[int] temperature: Optional[float] top_k: Optional[int] @@ -20,25 +20,25 @@ class Parameters(BaseModel): @validator("repetition_penalty") def valid_repetition_penalty(cls, v): - if v is not None and v is v < 0: + if v is not None and v is v <= 0: raise ValidationError("`repetition_penalty` must be strictly positive") return v @validator("seed") def valid_seed(cls, v): if v is not None and v is v < 0: - raise ValidationError("`seed` must be strictly positive") + raise ValidationError("`seed` must be positive") return v @validator("temperature") def valid_temp(cls, v): - if v is not None and v < 0: + if v is not None and v <= 0: raise ValidationError("`temperature` must be strictly positive") return v @validator("top_k") def valid_top_k(cls, v): - if v is not None and v < 0: + if v is not None and v <= 0: raise ValidationError("`top_k` must be strictly positive") return v