From 0386eb909a7c249ce57bd08f02c42a83e9371cde Mon Sep 17 00:00:00 2001 From: David Chiu Date: Fri, 28 Jun 2024 01:24:25 +0800 Subject: [PATCH] fix: huggingface embedding version --- poetry.lock | 135 ++++++++++++++++++++++++++++++++++++++++++++++--- pyproject.toml | 2 +- 2 files changed, 129 insertions(+), 8 deletions(-) diff --git a/poetry.lock b/poetry.lock index c4ba0cb..e5b5be2 100644 --- a/poetry.lock +++ b/poetry.lock @@ -1376,20 +1376,19 @@ wrapt = "*" [[package]] name = "llama-index-embeddings-huggingface" -version = "0.1.5" +version = "0.2.2" description = "llama-index embeddings huggingface integration" optional = false python-versions = "<4.0,>=3.8.1" files = [ - {file = "llama_index_embeddings_huggingface-0.1.5-py3-none-any.whl", hash = "sha256:3cfe007ad1b730c5a42f1b3a9234afb711a01ddba237ec93626283299bd5f0d2"}, - {file = "llama_index_embeddings_huggingface-0.1.5.tar.gz", hash = "sha256:ba86c39d2aab09990d9d5f7d2c859e4238f299d1e2d5053f129cb4607c74bb50"}, + {file = "llama_index_embeddings_huggingface-0.2.2-py3-none-any.whl", hash = "sha256:3445b1c7823cdb45622f90e79f2540db870ea55b226ec7538be963d340f43240"}, + {file = "llama_index_embeddings_huggingface-0.2.2.tar.gz", hash = "sha256:43b2978740d29291ae4c7566922d2b1c7543dc979e268794b578e1a2adfb4319"}, ] [package.dependencies] huggingface-hub = {version = ">=0.19.0", extras = ["inference"]} llama-index-core = ">=0.10.1,<0.11.0" -torch = ">=2.1.2,<3.0.0" -transformers = ">=4.37.0,<5.0.0" +sentence-transformers = ">=2.6.1" [[package]] name = "llama-index-embeddings-openai" @@ -2263,7 +2262,6 @@ description = "Nvidia JIT LTO Library" optional = false python-versions = ">=3" files = [ - {file = "nvidia_nvjitlink_cu12-12.5.40-py3-none-manylinux2014_aarch64.whl", hash = "sha256:004186d5ea6a57758fd6d57052a123c73a4815adf365eb8dd6a85c9eaa7535ff"}, {file = "nvidia_nvjitlink_cu12-12.5.40-py3-none-manylinux2014_x86_64.whl", hash = "sha256:d9714f27c1d0f0895cd8915c07a87a1d0029a0aa36acaf9156952ec2a8a12189"}, {file = "nvidia_nvjitlink_cu12-12.5.40-py3-none-win_amd64.whl", hash = "sha256:c3401dc8543b52d3a8158007a0c1ab4e9c768fcbd24153a48c86972102197ddd"}, ] @@ -3546,6 +3544,118 @@ tensorflow = ["safetensors[numpy]", "tensorflow (>=2.11.0)"] testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "hypothesis (>=6.70.2)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "safetensors[numpy]", "setuptools-rust (>=1.5.2)"] torch = ["safetensors[numpy]", "torch (>=1.10)"] +[[package]] +name = "scikit-learn" +version = "1.5.0" +description = "A set of python modules for machine learning and data mining" +optional = false +python-versions = ">=3.9" +files = [ + {file = "scikit_learn-1.5.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:12e40ac48555e6b551f0a0a5743cc94cc5a765c9513fe708e01f0aa001da2801"}, + {file = "scikit_learn-1.5.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:f405c4dae288f5f6553b10c4ac9ea7754d5180ec11e296464adb5d6ac68b6ef5"}, + {file = "scikit_learn-1.5.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:df8ccabbf583315f13160a4bb06037bde99ea7d8211a69787a6b7c5d4ebb6fc3"}, + {file = "scikit_learn-1.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c75ea812cd83b1385bbfa94ae971f0d80adb338a9523f6bbcb5e0b0381151d4"}, + {file = "scikit_learn-1.5.0-cp310-cp310-win_amd64.whl", hash = "sha256:a90c5da84829a0b9b4bf00daf62754b2be741e66b5946911f5bdfaa869fcedd6"}, + {file = "scikit_learn-1.5.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:2a65af2d8a6cce4e163a7951a4cfbfa7fceb2d5c013a4b593686c7f16445cf9d"}, + {file = "scikit_learn-1.5.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:4c0c56c3005f2ec1db3787aeaabefa96256580678cec783986836fc64f8ff622"}, + {file = "scikit_learn-1.5.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f77547165c00625551e5c250cefa3f03f2fc92c5e18668abd90bfc4be2e0bff"}, + {file = "scikit_learn-1.5.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:118a8d229a41158c9f90093e46b3737120a165181a1b58c03461447aa4657415"}, + {file = "scikit_learn-1.5.0-cp311-cp311-win_amd64.whl", hash = "sha256:a03b09f9f7f09ffe8c5efffe2e9de1196c696d811be6798ad5eddf323c6f4d40"}, + {file = "scikit_learn-1.5.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:460806030c666addee1f074788b3978329a5bfdc9b7d63e7aad3f6d45c67a210"}, + {file = "scikit_learn-1.5.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:1b94d6440603752b27842eda97f6395f570941857456c606eb1d638efdb38184"}, + {file = "scikit_learn-1.5.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d82c2e573f0f2f2f0be897e7a31fcf4e73869247738ab8c3ce7245549af58ab8"}, + {file = "scikit_learn-1.5.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a3a10e1d9e834e84d05e468ec501a356226338778769317ee0b84043c0d8fb06"}, + {file = "scikit_learn-1.5.0-cp312-cp312-win_amd64.whl", hash = "sha256:855fc5fa8ed9e4f08291203af3d3e5fbdc4737bd617a371559aaa2088166046e"}, + {file = "scikit_learn-1.5.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:40fb7d4a9a2db07e6e0cae4dc7bdbb8fada17043bac24104d8165e10e4cff1a2"}, + {file = "scikit_learn-1.5.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:47132440050b1c5beb95f8ba0b2402bbd9057ce96ec0ba86f2f445dd4f34df67"}, + {file = "scikit_learn-1.5.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:174beb56e3e881c90424e21f576fa69c4ffcf5174632a79ab4461c4c960315ac"}, + {file = "scikit_learn-1.5.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:261fe334ca48f09ed64b8fae13f9b46cc43ac5f580c4a605cbb0a517456c8f71"}, + {file = "scikit_learn-1.5.0-cp39-cp39-win_amd64.whl", hash = "sha256:057b991ac64b3e75c9c04b5f9395eaf19a6179244c089afdebaad98264bff37c"}, + {file = "scikit_learn-1.5.0.tar.gz", hash = "sha256:789e3db01c750ed6d496fa2db7d50637857b451e57bcae863bff707c1247bef7"}, +] + +[package.dependencies] +joblib = ">=1.2.0" +numpy = ">=1.19.5" +scipy = ">=1.6.0" +threadpoolctl = ">=3.1.0" + +[package.extras] +benchmark = ["matplotlib (>=3.3.4)", "memory_profiler (>=0.57.0)", "pandas (>=1.1.5)"] +build = ["cython (>=3.0.10)", "meson-python (>=0.15.0)", "numpy (>=1.19.5)", "scipy (>=1.6.0)"] +docs = ["Pillow (>=7.1.2)", "matplotlib (>=3.3.4)", "memory_profiler (>=0.57.0)", "numpydoc (>=1.2.0)", "pandas (>=1.1.5)", "plotly (>=5.14.0)", "polars (>=0.20.23)", "pooch (>=1.6.0)", "scikit-image (>=0.17.2)", "seaborn (>=0.9.0)", "sphinx (>=6.0.0)", "sphinx-copybutton (>=0.5.2)", "sphinx-gallery (>=0.15.0)", "sphinx-prompt (>=1.3.0)", "sphinxext-opengraph (>=0.4.2)"] +examples = ["matplotlib (>=3.3.4)", "pandas (>=1.1.5)", "plotly (>=5.14.0)", "pooch (>=1.6.0)", "scikit-image (>=0.17.2)", "seaborn (>=0.9.0)"] +install = ["joblib (>=1.2.0)", "numpy (>=1.19.5)", "scipy (>=1.6.0)", "threadpoolctl (>=3.1.0)"] +maintenance = ["conda-lock (==2.5.6)"] +tests = ["black (>=24.3.0)", "matplotlib (>=3.3.4)", "mypy (>=1.9)", "numpydoc (>=1.2.0)", "pandas (>=1.1.5)", "polars (>=0.20.23)", "pooch (>=1.6.0)", "pyamg (>=4.0.0)", "pyarrow (>=12.0.0)", "pytest (>=7.1.2)", "pytest-cov (>=2.9.0)", "ruff (>=0.2.1)", "scikit-image (>=0.17.2)"] + +[[package]] +name = "scipy" +version = "1.14.0" +description = "Fundamental algorithms for scientific computing in Python" +optional = false +python-versions = ">=3.10" +files = [ + {file = "scipy-1.14.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:7e911933d54ead4d557c02402710c2396529540b81dd554fc1ba270eb7308484"}, + {file = "scipy-1.14.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:687af0a35462402dd851726295c1a5ae5f987bd6e9026f52e9505994e2f84ef6"}, + {file = "scipy-1.14.0-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:07e179dc0205a50721022344fb85074f772eadbda1e1b3eecdc483f8033709b7"}, + {file = "scipy-1.14.0-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:6a9c9a9b226d9a21e0a208bdb024c3982932e43811b62d202aaf1bb59af264b1"}, + {file = "scipy-1.14.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:076c27284c768b84a45dcf2e914d4000aac537da74236a0d45d82c6fa4b7b3c0"}, + {file = "scipy-1.14.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42470ea0195336df319741e230626b6225a740fd9dce9642ca13e98f667047c0"}, + {file = "scipy-1.14.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:176c6f0d0470a32f1b2efaf40c3d37a24876cebf447498a4cefb947a79c21e9d"}, + {file = "scipy-1.14.0-cp310-cp310-win_amd64.whl", hash = "sha256:ad36af9626d27a4326c8e884917b7ec321d8a1841cd6dacc67d2a9e90c2f0359"}, + {file = "scipy-1.14.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6d056a8709ccda6cf36cdd2eac597d13bc03dba38360f418560a93050c76a16e"}, + {file = "scipy-1.14.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:f0a50da861a7ec4573b7c716b2ebdcdf142b66b756a0d392c236ae568b3a93fb"}, + {file = "scipy-1.14.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:94c164a9e2498e68308e6e148646e486d979f7fcdb8b4cf34b5441894bdb9caf"}, + {file = "scipy-1.14.0-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:a7d46c3e0aea5c064e734c3eac5cf9eb1f8c4ceee756262f2c7327c4c2691c86"}, + {file = "scipy-1.14.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9eee2989868e274aae26125345584254d97c56194c072ed96cb433f32f692ed8"}, + {file = "scipy-1.14.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e3154691b9f7ed73778d746da2df67a19d046a6c8087c8b385bc4cdb2cfca74"}, + {file = "scipy-1.14.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:c40003d880f39c11c1edbae8144e3813904b10514cd3d3d00c277ae996488cdb"}, + {file = "scipy-1.14.0-cp311-cp311-win_amd64.whl", hash = "sha256:5b083c8940028bb7e0b4172acafda6df762da1927b9091f9611b0bcd8676f2bc"}, + {file = "scipy-1.14.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:bff2438ea1330e06e53c424893ec0072640dac00f29c6a43a575cbae4c99b2b9"}, + {file = "scipy-1.14.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:bbc0471b5f22c11c389075d091d3885693fd3f5e9a54ce051b46308bc787e5d4"}, + {file = "scipy-1.14.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:64b2ff514a98cf2bb734a9f90d32dc89dc6ad4a4a36a312cd0d6327170339eb0"}, + {file = "scipy-1.14.0-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:7d3da42fbbbb860211a811782504f38ae7aaec9de8764a9bef6b262de7a2b50f"}, + {file = "scipy-1.14.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d91db2c41dd6c20646af280355d41dfa1ec7eead235642178bd57635a3f82209"}, + {file = "scipy-1.14.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a01cc03bcdc777c9da3cfdcc74b5a75caffb48a6c39c8450a9a05f82c4250a14"}, + {file = "scipy-1.14.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:65df4da3c12a2bb9ad52b86b4dcf46813e869afb006e58be0f516bc370165159"}, + {file = "scipy-1.14.0-cp312-cp312-win_amd64.whl", hash = "sha256:4c4161597c75043f7154238ef419c29a64ac4a7c889d588ea77690ac4d0d9b20"}, + {file = "scipy-1.14.0.tar.gz", hash = "sha256:b5923f48cb840380f9854339176ef21763118a7300a88203ccd0bdd26e58527b"}, +] + +[package.dependencies] +numpy = ">=1.23.5,<2.3" + +[package.extras] +dev = ["cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy (==1.10.0)", "pycodestyle", "pydevtool", "rich-click", "ruff (>=0.0.292)", "types-psutil", "typing_extensions"] +doc = ["jupyterlite-pyodide-kernel", "jupyterlite-sphinx (>=0.13.1)", "jupytext", "matplotlib (>=3.5)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (>=0.15.2)", "sphinx (>=5.0.0)", "sphinx-design (>=0.4.0)"] +test = ["Cython", "array-api-strict", "asv", "gmpy2", "hypothesis (>=6.30)", "meson", "mpmath", "ninja", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"] + +[[package]] +name = "sentence-transformers" +version = "3.0.1" +description = "Multilingual text embeddings" +optional = false +python-versions = ">=3.8.0" +files = [ + {file = "sentence_transformers-3.0.1-py3-none-any.whl", hash = "sha256:01050cc4053c49b9f5b78f6980b5a72db3fd3a0abb9169b1792ac83875505ee6"}, + {file = "sentence_transformers-3.0.1.tar.gz", hash = "sha256:8a3d2c537cc4d1014ccc20ac92be3d6135420a3bc60ae29a3a8a9b4bb35fbff6"}, +] + +[package.dependencies] +huggingface-hub = ">=0.15.1" +numpy = "*" +Pillow = "*" +scikit-learn = "*" +scipy = "*" +torch = ">=1.11.0" +tqdm = "*" +transformers = ">=4.34.0,<5.0.0" + +[package.extras] +dev = ["accelerate (>=0.20.3)", "datasets", "pre-commit", "pytest", "ruff (>=0.3.0)"] +train = ["accelerate (>=0.20.3)", "datasets"] + [[package]] name = "setuptools" version = "70.1.1" @@ -3762,6 +3872,17 @@ files = [ doc = ["reno", "sphinx"] test = ["pytest", "tornado (>=4.5)", "typeguard"] +[[package]] +name = "threadpoolctl" +version = "3.5.0" +description = "threadpoolctl" +optional = false +python-versions = ">=3.8" +files = [ + {file = "threadpoolctl-3.5.0-py3-none-any.whl", hash = "sha256:56c1e26c150397e58c4926da8eeee87533b1e32bef131bd4bf6a2f45f3185467"}, + {file = "threadpoolctl-3.5.0.tar.gz", hash = "sha256:082433502dd922bf738de0d8bcc4fdcbf0979ff44c42bd40f5af8a282f6fa107"}, +] + [[package]] name = "tiktoken" version = "0.7.0" @@ -4701,4 +4822,4 @@ test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools", [metadata] lock-version = "2.0" python-versions = "^3.12" -content-hash = "9ae647d0bfcc3f333be5713f30c27d72f8c1140c53e57d48b259671c02454af5" +content-hash = "4bfea5209b176c7604b417b56dfacd21aec903f12ad8a8ee1f9a91733df6b0a9" diff --git a/pyproject.toml b/pyproject.toml index 3b0219a..84787a8 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -17,7 +17,7 @@ chromadb = "^0.5.3" llama-index = "^0.10.11" transformers = "^4.35.2" llama-index-vector-stores-chroma = "^0.1.3" -llama-index-embeddings-huggingface = "^0.1.3" +llama-index-embeddings-huggingface = "^0.2.2" llama-index-readers-mongodb = "^0.1.5" pydantic = "^2.7.3"