From b0606c7cdfd07afd00f76e34463d8b0d60029466 Mon Sep 17 00:00:00 2001 From: dylanholmes <4370153+dylanholmes@users.noreply.github.com> Date: Wed, 22 May 2024 11:02:50 -0700 Subject: [PATCH] Fix hugging face prompt pipeline driver + docs (#796) --- .../drivers/prompt-drivers.md | 20 +- .../huggingface_pipeline_prompt_driver.py | 1 + poetry.lock | 321 +++++++++++++++++- pyproject.toml | 3 + 4 files changed, 336 insertions(+), 9 deletions(-) diff --git a/docs/griptape-framework/drivers/prompt-drivers.md b/docs/griptape-framework/drivers/prompt-drivers.md index ae798b22e..e2b324ee1 100644 --- a/docs/griptape-framework/drivers/prompt-drivers.md +++ b/docs/griptape-framework/drivers/prompt-drivers.md @@ -242,6 +242,15 @@ The [HuggingFaceHubPromptDriver](../../reference/griptape/drivers/prompt/hugging - text2text-generation - text-generation +!!! warning + Not all models featured on the Hugging Face Hub are supported by this driver. Models that are not supported by + [Hugging Face serverless inference](https://huggingface.co/docs/api-inference/en/index) will not work with this driver. + Due to the limitations of Hugging Face serverless inference, only models that are than 10GB are supported. + +!!! info + The `prompt_stack_to_string_converter` function is intended to convert a `PromptStack` to model specific input. You + should consult the model's documentation to determine the correct format. + Let's recreate the [Falcon-7B-Instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) example using Griptape: ```python @@ -319,9 +328,9 @@ agent.run("Write the code for a snake game.") ### Hugging Face Pipeline !!! info - This driver requires the `drivers-prompt-huggingface` [extra](../index.md#extras). + This driver requires the `drivers-prompt-huggingface-pipeline` [extra](../index.md#extras). -The [HuggingFaceHubPromptDriver](../../reference/griptape/drivers/prompt/huggingface_pipeline_prompt_driver.md) uses [Hugging Face Pipelines](https://huggingface.co/docs/transformers/main_classes/pipelines) for inference locally. It supports models with the following tasks: +The [HuggingFacePipelinePromptDriver](../../reference/griptape/drivers/prompt/huggingface_pipeline_prompt_driver.md) uses [Hugging Face Pipelines](https://huggingface.co/docs/transformers/main_classes/pipelines) for inference locally. It supports models with the following tasks: - text2text-generation - text-generation @@ -332,7 +341,7 @@ The [HuggingFaceHubPromptDriver](../../reference/griptape/drivers/prompt/hugging ```python import os from griptape.structures import Agent -from griptape.drivers import HuggingFaceHubPromptDriver +from griptape.drivers import HuggingFacePipelinePromptDriver from griptape.rules import Rule, Ruleset from griptape.utils import PromptStack from griptape.config import StructureConfig @@ -357,9 +366,8 @@ def prompt_stack_to_string_converter(prompt_stack: PromptStack) -> str: agent = Agent( config=StructureConfig( - prompt_driver=HuggingFaceHubPromptDriver( - model="tiiuae/falcon-7b-instruct", - api_token=os.environ["HUGGINGFACE_HUB_ACCESS_TOKEN"], + prompt_driver=HuggingFacePipelinePromptDriver( + model="TinyLlama/TinyLlama-1.1B-Chat-v0.6", prompt_stack_to_string=prompt_stack_to_string_converter, ) ), diff --git a/griptape/drivers/prompt/huggingface_pipeline_prompt_driver.py b/griptape/drivers/prompt/huggingface_pipeline_prompt_driver.py index d93a3a10c..9fb8b9ece 100644 --- a/griptape/drivers/prompt/huggingface_pipeline_prompt_driver.py +++ b/griptape/drivers/prompt/huggingface_pipeline_prompt_driver.py @@ -21,6 +21,7 @@ class HuggingFacePipelinePromptDriver(BasePromptDriver): SUPPORTED_TASKS = ["text2text-generation", "text-generation"] DEFAULT_PARAMS = {"return_full_text": False, "num_return_sequences": 1} + max_tokens: int = field(default=250, kw_only=True, metadata={"serializable": True}) model: str = field(kw_only=True, metadata={"serializable": True}) params: dict = field(factory=dict, kw_only=True, metadata={"serializable": True}) tokenizer: HuggingFaceTokenizer = field( diff --git a/poetry.lock b/poetry.lock index 02da58de3..c4e2e1024 100644 --- a/poetry.lock +++ b/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand. +# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand. [[package]] name = "aiohttp" @@ -1954,6 +1954,20 @@ files = [ {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"}, ] +[[package]] +name = "intel-openmp" +version = "2021.4.0" +description = "Intel OpenMP* Runtime Library" +optional = true +python-versions = "*" +files = [ + {file = "intel_openmp-2021.4.0-py2.py3-none-macosx_10_15_x86_64.macosx_11_0_x86_64.whl", hash = "sha256:41c01e266a7fdb631a7609191709322da2bbf24b252ba763f125dd651bcc7675"}, + {file = "intel_openmp-2021.4.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:3b921236a38384e2016f0f3d65af6732cf2c12918087128a9163225451e776f2"}, + {file = "intel_openmp-2021.4.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:e2240ab8d01472fed04f3544a878cda5da16c26232b7ea1b59132dbfb48b186e"}, + {file = "intel_openmp-2021.4.0-py2.py3-none-win32.whl", hash = "sha256:6e863d8fd3d7e8ef389d52cf97a50fe2afe1a19247e8c0d168ce021546f96fc9"}, + {file = "intel_openmp-2021.4.0-py2.py3-none-win_amd64.whl", hash = "sha256:eef4c8bcc8acefd7f5cd3b9384dbf73d59e2c99fc56545712ded913f43c4a94f"}, +] + [[package]] name = "ipython" version = "8.18.1" @@ -2672,6 +2686,24 @@ files = [ griffe = ">=0.37" mkdocstrings = ">=0.20" +[[package]] +name = "mkl" +version = "2021.4.0" +description = "Intel® oneAPI Math Kernel Library" +optional = true +python-versions = "*" +files = [ + {file = "mkl-2021.4.0-py2.py3-none-macosx_10_15_x86_64.macosx_11_0_x86_64.whl", hash = "sha256:67460f5cd7e30e405b54d70d1ed3ca78118370b65f7327d495e9c8847705e2fb"}, + {file = "mkl-2021.4.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:636d07d90e68ccc9630c654d47ce9fdeb036bb46e2b193b3a9ac8cfea683cce5"}, + {file = "mkl-2021.4.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:398dbf2b0d12acaf54117a5210e8f191827f373d362d796091d161f610c1ebfb"}, + {file = "mkl-2021.4.0-py2.py3-none-win32.whl", hash = "sha256:439c640b269a5668134e3dcbcea4350459c4a8bc46469669b2d67e07e3d330e8"}, + {file = "mkl-2021.4.0-py2.py3-none-win_amd64.whl", hash = "sha256:ceef3cafce4c009dd25f65d7ad0d833a0fbadc3d8903991ec92351fe5de1e718"}, +] + +[package.dependencies] +intel-openmp = "==2021.*" +tbb = "==2021.*" + [[package]] name = "mongomock" version = "4.1.2" @@ -2745,6 +2777,23 @@ server = ["PyYAML (>=5.1)", "aws-xray-sdk (>=0.93,!=0.96)", "cfn-lint (>=0.40.0) ssm = ["PyYAML (>=5.1)"] xray = ["aws-xray-sdk (>=0.93,!=0.96)", "setuptools"] +[[package]] +name = "mpmath" +version = "1.3.0" +description = "Python library for arbitrary-precision floating-point arithmetic" +optional = true +python-versions = "*" +files = [ + {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"}, + {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"}, +] + +[package.extras] +develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"] +docs = ["sphinx"] +gmpy = ["gmpy2 (>=2.1.0a4)"] +tests = ["pytest (>=4.6)"] + [[package]] name = "multidict" version = "6.0.5" @@ -2914,6 +2963,24 @@ files = [ [package.dependencies] typing-extensions = {version = ">=4.1.0", markers = "python_version < \"3.12\""} +[[package]] +name = "networkx" +version = "3.2.1" +description = "Python package for creating and manipulating graphs and networks" +optional = true +python-versions = ">=3.9" +files = [ + {file = "networkx-3.2.1-py3-none-any.whl", hash = "sha256:f18c69adc97877c42332c170849c96cefa91881c99a7cb3e95b7c659ebdc1ec2"}, + {file = "networkx-3.2.1.tar.gz", hash = "sha256:9f1bb5cf3409bf324e0a722c20bdb4c20ee39bf1c30ce8ae499c8502b0b5e0c6"}, +] + +[package.extras] +default = ["matplotlib (>=3.5)", "numpy (>=1.22)", "pandas (>=1.4)", "scipy (>=1.9,!=1.11.0,!=1.11.1)"] +developer = ["changelist (==0.4)", "mypy (>=1.1)", "pre-commit (>=3.2)", "rtoml"] +doc = ["nb2plots (>=0.7)", "nbconvert (<7.9)", "numpydoc (>=1.6)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.14)", "sphinx (>=7)", "sphinx-gallery (>=0.14)", "texext (>=0.6.7)"] +extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.11)", "sympy (>=1.10)"] +test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"] + [[package]] name = "nh3" version = "0.2.17" @@ -2998,6 +3065,148 @@ files = [ {file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"}, ] +[[package]] +name = "nvidia-cublas-cu12" +version = "12.1.3.1" +description = "CUBLAS native runtime libraries" +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:ee53ccca76a6fc08fb9701aa95b6ceb242cdaab118c3bb152af4e579af792728"}, + {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-win_amd64.whl", hash = "sha256:2b964d60e8cf11b5e1073d179d85fa340c120e99b3067558f3cf98dd69d02906"}, +] + +[[package]] +name = "nvidia-cuda-cupti-cu12" +version = "12.1.105" +description = "CUDA profiling tools runtime libs." +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:e54fde3983165c624cb79254ae9818a456eb6e87a7fd4d56a2352c24ee542d7e"}, + {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:bea8236d13a0ac7190bd2919c3e8e6ce1e402104276e6f9694479e48bb0eb2a4"}, +] + +[[package]] +name = "nvidia-cuda-nvrtc-cu12" +version = "12.1.105" +description = "NVRTC native runtime libraries" +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:339b385f50c309763ca65456ec75e17bbefcbbf2893f462cb8b90584cd27a1c2"}, + {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:0a98a522d9ff138b96c010a65e145dc1b4850e9ecb75a0172371793752fd46ed"}, +] + +[[package]] +name = "nvidia-cuda-runtime-cu12" +version = "12.1.105" +description = "CUDA Runtime native Libraries" +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:6e258468ddf5796e25f1dc591a31029fa317d97a0a94ed93468fc86301d61e40"}, + {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:dfb46ef84d73fababab44cf03e3b83f80700d27ca300e537f85f636fac474344"}, +] + +[[package]] +name = "nvidia-cudnn-cu12" +version = "8.9.2.26" +description = "cuDNN runtime libraries" +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl", hash = "sha256:5ccb288774fdfb07a7e7025ffec286971c06d8d7b4fb162525334616d7629ff9"}, +] + +[package.dependencies] +nvidia-cublas-cu12 = "*" + +[[package]] +name = "nvidia-cufft-cu12" +version = "11.0.2.54" +description = "CUFFT native runtime libraries" +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl", hash = "sha256:794e3948a1aa71fd817c3775866943936774d1c14e7628c74f6f7417224cdf56"}, + {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-win_amd64.whl", hash = "sha256:d9ac353f78ff89951da4af698f80870b1534ed69993f10a4cf1d96f21357e253"}, +] + +[[package]] +name = "nvidia-curand-cu12" +version = "10.3.2.106" +description = "CURAND native runtime libraries" +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:9d264c5036dde4e64f1de8c50ae753237c12e0b1348738169cd0f8a536c0e1e0"}, + {file = "nvidia_curand_cu12-10.3.2.106-py3-none-win_amd64.whl", hash = "sha256:75b6b0c574c0037839121317e17fd01f8a69fd2ef8e25853d826fec30bdba74a"}, +] + +[[package]] +name = "nvidia-cusolver-cu12" +version = "11.4.5.107" +description = "CUDA solver native runtime libraries" +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd"}, + {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-win_amd64.whl", hash = "sha256:74e0c3a24c78612192a74fcd90dd117f1cf21dea4822e66d89e8ea80e3cd2da5"}, +] + +[package.dependencies] +nvidia-cublas-cu12 = "*" +nvidia-cusparse-cu12 = "*" +nvidia-nvjitlink-cu12 = "*" + +[[package]] +name = "nvidia-cusparse-cu12" +version = "12.1.0.106" +description = "CUSPARSE native runtime libraries" +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c"}, + {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-win_amd64.whl", hash = "sha256:b798237e81b9719373e8fae8d4f091b70a0cf09d9d85c95a557e11df2d8e9a5a"}, +] + +[package.dependencies] +nvidia-nvjitlink-cu12 = "*" + +[[package]] +name = "nvidia-nccl-cu12" +version = "2.20.5" +description = "NVIDIA Collective Communication Library (NCCL) Runtime" +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1fc150d5c3250b170b29410ba682384b14581db722b2531b0d8d33c595f33d01"}, + {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:057f6bf9685f75215d0c53bf3ac4a10b3e6578351de307abad9e18a99182af56"}, +] + +[[package]] +name = "nvidia-nvjitlink-cu12" +version = "12.4.127" +description = "Nvidia JIT LTO Library" +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:06b3b9b25bf3f8af351d664978ca26a16d2c5127dbd53c0497e28d1fb9611d57"}, + {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:fd9020c501d27d135f983c6d3e244b197a7ccad769e34df53a42e276b0e25fa1"}, +] + +[[package]] +name = "nvidia-nvtx-cu12" +version = "12.1.105" +description = "NVIDIA Tools Extension" +optional = true +python-versions = ">=3" +files = [ + {file = "nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:dc21cf308ca5691e7c04d962e213f8a4aa9bbfa23d95412f452254c2caeb09e5"}, + {file = "nvidia_nvtx_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:65f4d98982b31b60026e0e6de73fbdfc09d08a96f4656dd3665ca616a11e1e82"}, +] + [[package]] name = "openai" version = "1.30.1" @@ -4027,6 +4236,7 @@ files = [ {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"}, {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"}, {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"}, + {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"}, {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"}, {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"}, {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"}, @@ -4869,6 +5079,33 @@ files = [ {file = "stringcase-1.2.0.tar.gz", hash = "sha256:48a06980661908efe8d9d34eab2b6c13aefa2163b3ced26972902e3bdfd87008"}, ] +[[package]] +name = "sympy" +version = "1.12" +description = "Computer algebra system (CAS) in Python" +optional = true +python-versions = ">=3.8" +files = [ + {file = "sympy-1.12-py3-none-any.whl", hash = "sha256:c3588cd4295d0c0f603d0f2ae780587e64e2efeedb3521e46b9bb1d08d184fa5"}, + {file = "sympy-1.12.tar.gz", hash = "sha256:ebf595c8dac3e0fdc4152c51878b498396ec7f30e7a914d6071e674d49420fb8"}, +] + +[package.dependencies] +mpmath = ">=0.19" + +[[package]] +name = "tbb" +version = "2021.12.0" +description = "Intel® oneAPI Threading Building Blocks (oneTBB)" +optional = true +python-versions = "*" +files = [ + {file = "tbb-2021.12.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:f2cc9a7f8ababaa506cbff796ce97c3bf91062ba521e15054394f773375d81d8"}, + {file = "tbb-2021.12.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:a925e9a7c77d3a46ae31c34b0bb7f801c4118e857d137b68f68a8e458fcf2bd7"}, + {file = "tbb-2021.12.0-py3-none-win32.whl", hash = "sha256:b1725b30c174048edc8be70bd43bb95473f396ce895d91151a474d0fa9f450a8"}, + {file = "tbb-2021.12.0-py3-none-win_amd64.whl", hash = "sha256:fc2772d850229f2f3df85f1109c4844c495a2db7433d38200959ee9265b34789"}, +] + [[package]] name = "tenacity" version = "8.3.0" @@ -5086,6 +5323,60 @@ files = [ {file = "tomlkit-0.12.5.tar.gz", hash = "sha256:eef34fba39834d4d6b73c9ba7f3e4d1c417a4e56f89a7e96e090dd0d24b8fb3c"}, ] +[[package]] +name = "torch" +version = "2.3.0" +description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration" +optional = true +python-versions = ">=3.8.0" +files = [ + {file = "torch-2.3.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:d8ea5a465dbfd8501f33c937d1f693176c9aef9d1c1b0ca1d44ed7b0a18c52ac"}, + {file = "torch-2.3.0-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:09c81c5859a5b819956c6925a405ef1cdda393c9d8a01ce3851453f699d3358c"}, + {file = "torch-2.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:1bf023aa20902586f614f7682fedfa463e773e26c58820b74158a72470259459"}, + {file = "torch-2.3.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:758ef938de87a2653bba74b91f703458c15569f1562bf4b6c63c62d9c5a0c1f5"}, + {file = "torch-2.3.0-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:493d54ee2f9df100b5ce1d18c96dbb8d14908721f76351e908c9d2622773a788"}, + {file = "torch-2.3.0-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:bce43af735c3da16cc14c7de2be7ad038e2fbf75654c2e274e575c6c05772ace"}, + {file = "torch-2.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:729804e97b7cf19ae9ab4181f91f5e612af07956f35c8b2c8e9d9f3596a8e877"}, + {file = "torch-2.3.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:d24e328226d8e2af7cf80fcb1d2f1d108e0de32777fab4aaa2b37b9765d8be73"}, + {file = "torch-2.3.0-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:b0de2bdc0486ea7b14fc47ff805172df44e421a7318b7c4d92ef589a75d27410"}, + {file = "torch-2.3.0-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:a306c87a3eead1ed47457822c01dfbd459fe2920f2d38cbdf90de18f23f72542"}, + {file = "torch-2.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:f9b98bf1a3c8af2d4c41f0bf1433920900896c446d1ddc128290ff146d1eb4bd"}, + {file = "torch-2.3.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:dca986214267b34065a79000cee54232e62b41dff1ec2cab9abc3fc8b3dee0ad"}, + {file = "torch-2.3.0-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:20572f426965dd8a04e92a473d7e445fa579e09943cc0354f3e6fef6130ce061"}, + {file = "torch-2.3.0-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:e65ba85ae292909cde0dde6369826d51165a3fc8823dc1854cd9432d7f79b932"}, + {file = "torch-2.3.0-cp38-cp38-win_amd64.whl", hash = "sha256:5515503a193781fd1b3f5c474e89c9dfa2faaa782b2795cc4a7ab7e67de923f6"}, + {file = "torch-2.3.0-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:6ae9f64b09516baa4ef890af0672dc981c20b1f0d829ce115d4420a247e88fba"}, + {file = "torch-2.3.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:cd0dc498b961ab19cb3f8dbf0c6c50e244f2f37dbfa05754ab44ea057c944ef9"}, + {file = "torch-2.3.0-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:e05f836559251e4096f3786ee99f4a8cbe67bc7fbedba8ad5e799681e47c5e80"}, + {file = "torch-2.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:4fb27b35dbb32303c2927da86e27b54a92209ddfb7234afb1949ea2b3effffea"}, + {file = "torch-2.3.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:760f8bedff506ce9e6e103498f9b1e9e15809e008368594c3a66bf74a8a51380"}, +] + +[package.dependencies] +filelock = "*" +fsspec = "*" +jinja2 = "*" +mkl = {version = ">=2021.1.1,<=2021.4.0", markers = "platform_system == \"Windows\""} +networkx = "*" +nvidia-cublas-cu12 = {version = "12.1.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cuda-cupti-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cuda-nvrtc-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cuda-runtime-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cudnn-cu12 = {version = "8.9.2.26", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cufft-cu12 = {version = "11.0.2.54", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-nccl-cu12 = {version = "2.20.5", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +sympy = "*" +triton = {version = "2.3.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.12\""} +typing-extensions = ">=4.8.0" + +[package.extras] +opt-einsum = ["opt-einsum (>=3.3)"] +optree = ["optree (>=0.9.1)"] + [[package]] name = "tqdm" version = "4.66.4" @@ -5213,6 +5504,29 @@ torchhub = ["filelock", "huggingface-hub (>=0.19.3,<1.0)", "importlib-metadata", video = ["av (==9.2.0)", "decord (==0.6.0)"] vision = ["Pillow (>=10.0.1,<=15.0)"] +[[package]] +name = "triton" +version = "2.3.0" +description = "A language and compiler for custom Deep Learning operations" +optional = true +python-versions = "*" +files = [ + {file = "triton-2.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5ce4b8ff70c48e47274c66f269cce8861cf1dc347ceeb7a67414ca151b1822d8"}, + {file = "triton-2.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3c3d9607f85103afdb279938fc1dd2a66e4f5999a58eb48a346bd42738f986dd"}, + {file = "triton-2.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:218d742e67480d9581bafb73ed598416cc8a56f6316152e5562ee65e33de01c0"}, + {file = "triton-2.3.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:381ec6b3dac06922d3e4099cfc943ef032893b25415de295e82b1a82b0359d2c"}, + {file = "triton-2.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:038e06a09c06a164fef9c48de3af1e13a63dc1ba3c792871e61a8e79720ea440"}, + {file = "triton-2.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d8f636e0341ac348899a47a057c3daea99ea7db31528a225a3ba4ded28ccc65"}, +] + +[package.dependencies] +filelock = "*" + +[package.extras] +build = ["cmake (>=3.20)", "lit"] +tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)", "torch"] +tutorials = ["matplotlib", "pandas", "tabulate", "torch"] + [[package]] name = "twine" version = "5.0.0" @@ -5671,7 +5985,7 @@ docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.link testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-ignore-flaky", "pytest-mypy", "pytest-ruff (>=0.2.1)"] [extras] -all = ["anthropic", "beautifulsoup4", "boto3", "cohere", "elevenlabs", "google-generativeai", "mail-parser", "markdownify", "marqo", "opensearch-py", "pandas", "pgvector", "pillow", "pinecone-client", "playwright", "psycopg2-binary", "pymongo", "pypdf", "redis", "snowflake-sqlalchemy", "sqlalchemy-redshift", "trafilatura", "transformers", "voyageai"] +all = ["anthropic", "beautifulsoup4", "boto3", "cohere", "elevenlabs", "google-generativeai", "mail-parser", "markdownify", "marqo", "opensearch-py", "pandas", "pgvector", "pillow", "pinecone-client", "playwright", "psycopg2-binary", "pymongo", "pypdf", "redis", "snowflake-sqlalchemy", "sqlalchemy-redshift", "torch", "trafilatura", "transformers", "voyageai"] drivers-embedding-amazon-bedrock = ["boto3"] drivers-embedding-amazon-sagemaker = ["boto3"] drivers-embedding-google = ["google-generativeai"] @@ -5687,6 +6001,7 @@ drivers-prompt-anthropic = ["anthropic"] drivers-prompt-cohere = ["cohere"] drivers-prompt-google = ["google-generativeai"] drivers-prompt-huggingface = ["huggingface-hub", "transformers"] +drivers-prompt-huggingface-pipeline = ["huggingface-hub", "torch", "transformers"] drivers-sql-postgres = ["pgvector", "psycopg2-binary"] drivers-sql-redshift = ["boto3", "sqlalchemy-redshift"] drivers-sql-snowflake = ["snowflake-sqlalchemy"] @@ -5707,4 +6022,4 @@ loaders-pdf = ["pypdf"] [metadata] lock-version = "2.0" python-versions = "^3.9" -content-hash = "7e866d7a5968b9e5a5c166be3cf667488d00d03d412deabe29090a9f6d1ab83d" +content-hash = "2590fc0528b584775d753939abbde032c34055a92db2538385002b9808d1fa31" diff --git a/pyproject.toml b/pyproject.toml index 9206f23c9..5ca064399 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -52,6 +52,7 @@ beautifulsoup4 = {version = "^4.12.3", optional = true} markdownify = {version = "^0.11.6", optional = true} voyageai = {version = "^0.2.1", optional = true} elevenlabs = {version = "^1.1.2", optional = true} +torch = {version = "^2.3.0", optional = true} # loaders pandas = {version = "^1.3", optional = true} @@ -63,6 +64,7 @@ mail-parser = {version = "^3.15.0", optional = true} drivers-prompt-cohere = ["cohere"] drivers-prompt-anthropic = ["anthropic"] drivers-prompt-huggingface = ["huggingface-hub", "transformers"] +drivers-prompt-huggingface-pipeline = ["huggingface-hub", "transformers", "torch"] drivers-prompt-amazon-bedrock = ["boto3", "anthropic"] drivers-prompt-amazon-sagemaker = ["boto3", "transformers"] drivers-prompt-google = ["google-generativeai"] @@ -123,6 +125,7 @@ all = [ "markdownify", "voyageai", "elevenlabs", + "torch", # loaders "pandas",