Start adding embeddings computation

pdm.lock

@@ -5,7 +5,7 @@
 groups = ["default"]
 strategy = ["cross_platform", "inherit_metadata"]
 lock_version = "4.4.1"
-content_hash = "sha256:4c270a78a0a28a5426bc46b9fe833d8ebd04d1352497613cc5837cc9e71bd4b8"
+content_hash = "sha256:94cab6806602f6354eb0bb6e0daab4fd448f73b02773036e6375b9a134b458af"
 
 [[package]]
 name = "aioboto3"
@@ -311,7 +311,7 @@ version = "0.4.6"
 requires_python = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
 summary = "Cross-platform colored terminal text."
 groups = ["default"]
-marker = "sys_platform == \"win32\""
+marker = "sys_platform == \"win32\" or platform_system == \"Windows\""
 files = [
     {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
     {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
@@ -328,6 +328,17 @@ files = [
     {file = "dnspython-2.6.1.tar.gz", hash = "sha256:e8f0f9c23a7b7cb99ded64e6c3a6f3e701d78f50c55e002b839dea7225cff7cc"},
 ]
 
+[[package]]
+name = "filelock"
+version = "3.13.4"
+requires_python = ">=3.8"
+summary = "A platform independent file lock."
+groups = ["default"]
+files = [
+    {file = "filelock-3.13.4-py3-none-any.whl", hash = "sha256:404e5e9253aa60ad457cae1be07c0f0ca90a63931200a47d9b6a6af84fd7b45f"},
+    {file = "filelock-3.13.4.tar.gz", hash = "sha256:d13f466618bfde72bd2c18255e269f72542c6e70e7bac83a0232d6b1cc5c8cf4"},
+]
+
 [[package]]
 name = "frozenlist"
 version = "1.4.1"
@@ -354,6 +365,37 @@ files = [
     {file = "frozenlist-1.4.1.tar.gz", hash = "sha256:c037a86e8513059a2613aaba4d817bb90b9d9b6b69aace3ce9c877e8c8ed402b"},
 ]
 
+[[package]]
+name = "fsspec"
+version = "2024.3.1"
+requires_python = ">=3.8"
+summary = "File-system specification"
+groups = ["default"]
+files = [
+    {file = "fsspec-2024.3.1-py3-none-any.whl", hash = "sha256:918d18d41bf73f0e2b261824baeb1b124bcf771767e3a26425cd7dec3332f512"},
+    {file = "fsspec-2024.3.1.tar.gz", hash = "sha256:f39780e282d7d117ffb42bb96992f8a90795e4d0fb0f661a70ca39fe9c43ded9"},
+]
+
+[[package]]
+name = "huggingface-hub"
+version = "0.22.2"
+requires_python = ">=3.8.0"
+summary = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
+groups = ["default"]
+dependencies = [
+    "filelock",
+    "fsspec>=2023.5.0",
+    "packaging>=20.9",
+    "pyyaml>=5.1",
+    "requests",
+    "tqdm>=4.42.1",
+    "typing-extensions>=3.7.4.3",
+]
+files = [
+    {file = "huggingface_hub-0.22.2-py3-none-any.whl", hash = "sha256:3429e25f38ccb834d310804a3b711e7e4953db5a9e420cc147a5e194ca90fd17"},
+    {file = "huggingface_hub-0.22.2.tar.gz", hash = "sha256:32e9a9a6843c92f253ff9ca16b9985def4d80a93fb357af5353f770ef74a81be"},
+]
+
 [[package]]
 name = "idna"
 version = "3.6"
@@ -376,6 +418,20 @@ files = [
     {file = "itsdangerous-2.1.2.tar.gz", hash = "sha256:5dbbc68b317e5e42f327f9021763545dc3fc3bfe22e6deb96aaf1fc38874156a"},
 ]
 
+[[package]]
+name = "jinja2"
+version = "3.1.3"
+requires_python = ">=3.7"
+summary = "A very fast and expressive template engine."
+groups = ["default"]
+dependencies = [
+    "MarkupSafe>=2.0",
+]
+files = [
+    {file = "Jinja2-3.1.3-py3-none-any.whl", hash = "sha256:7d6d50dd97d52cbc355597bd845fabfbac3f551e1f99619e39a35ce8c370b5fa"},
+    {file = "Jinja2-3.1.3.tar.gz", hash = "sha256:ac8bd6544d4bb2c9792bf3a159e80bba8fda7f07e81bc3aed565432d5925ba90"},
+]
+
 [[package]]
 name = "jmespath"
 version = "1.0.1"
@@ -387,6 +443,17 @@ files = [
     {file = "jmespath-1.0.1.tar.gz", hash = "sha256:90261b206d6defd58fdd5e85f478bf633a2901798906be2ad389150c5c60edbe"},
 ]
 
+[[package]]
+name = "joblib"
+version = "1.4.0"
+requires_python = ">=3.8"
+summary = "Lightweight pipelining with Python functions"
+groups = ["default"]
+files = [
+    {file = "joblib-1.4.0-py3-none-any.whl", hash = "sha256:42942470d4062537be4d54c83511186da1fc14ba354961a2114da91efa9a4ed7"},
+    {file = "joblib-1.4.0.tar.gz", hash = "sha256:1eb0dc091919cd384490de890cb5dfd538410a6d4b3b54eef09fb8c50b409b1c"},
+]
+
 [[package]]
 name = "loguru"
 version = "0.7.2"
@@ -434,6 +501,26 @@ files = [
     {file = "lxml-5.1.0.tar.gz", hash = "sha256:3eea6ed6e6c918e468e693c41ef07f3c3acc310b70ddd9cc72d9ef84bc9564ca"},
 ]
 
+[[package]]
+name = "markupsafe"
+version = "2.1.5"
+requires_python = ">=3.7"
+summary = "Safely add untrusted strings to HTML/XML markup."
+groups = ["default"]
+files = [
+    {file = "MarkupSafe-2.1.5-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:629ddd2ca402ae6dbedfceeba9c46d5f7b2a61d9749597d4307f943ef198fc1f"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5b7b716f97b52c5a14bffdf688f971b2d5ef4029127f1ad7a513973cfd818df2"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ec585f69cec0aa07d945b20805be741395e28ac1627333b1c5b0105962ffced"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b91c037585eba9095565a3556f611e3cbfaa42ca1e865f7b8015fe5c7336d5a5"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7502934a33b54030eaf1194c21c692a534196063db72176b0c4028e140f8f32c"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0e397ac966fdf721b2c528cf028494e86172b4feba51d65f81ffd65c63798f3f"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:c061bb86a71b42465156a3ee7bd58c8c2ceacdbeb95d05a99893e08b8467359a"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:3a57fdd7ce31c7ff06cdfbf31dafa96cc533c21e443d57f5b1ecc6cdc668ec7f"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-win32.whl", hash = "sha256:397081c1a0bfb5124355710fe79478cdbeb39626492b15d399526ae53422b906"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-win_amd64.whl", hash = "sha256:2b7c57a4dfc4f16f7142221afe5ba4e093e09e728ca65c51f5620c9aaeb9a617"},
+    {file = "MarkupSafe-2.1.5.tar.gz", hash = "sha256:d283d37a890ba4c1ae73ffadf8046435c76e7bc2247bbb63c00bd1a709c6544b"},
+]
+
 [[package]]
 name = "motor"
 version = "3.3.2"
@@ -448,6 +535,16 @@ files = [
     {file = "motor-3.3.2.tar.gz", hash = "sha256:d2fc38de15f1c8058f389c1a44a4d4105c0405c48c061cd492a654496f7bc26a"},
 ]
 
+[[package]]
+name = "mpmath"
+version = "1.3.0"
+summary = "Python library for arbitrary-precision floating-point arithmetic"
+groups = ["default"]
+files = [
+    {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
+    {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"},
+]
+
 [[package]]
 name = "multidict"
 version = "6.0.5"
@@ -474,6 +571,237 @@ files = [
     {file = "multidict-6.0.5.tar.gz", hash = "sha256:f7e301075edaf50500f0b341543c41194d8df3ae5caf4702f2095f3ca73dd8da"},
 ]
 
+[[package]]
+name = "networkx"
+version = "3.3"
+requires_python = ">=3.10"
+summary = "Python package for creating and manipulating graphs and networks"
+groups = ["default"]
+files = [
+    {file = "networkx-3.3-py3-none-any.whl", hash = "sha256:28575580c6ebdaf4505b22c6256a2b9de86b316dc63ba9e93abde3d78dfdbcf2"},
+    {file = "networkx-3.3.tar.gz", hash = "sha256:0c127d8b2f4865f59ae9cb8aafcd60b5c70f3241ebd66f7defad7c4ab90126c9"},
+]
+
+[[package]]
+name = "numpy"
+version = "1.26.4"
+requires_python = ">=3.9"
+summary = "Fundamental package for array computing in Python"
+groups = ["default"]
+files = [
+    {file = "numpy-1.26.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4c66707fabe114439db9068ee468c26bbdf909cac0fb58686a42a24de1760c71"},
+    {file = "numpy-1.26.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:edd8b5fe47dab091176d21bb6de568acdd906d1887a4584a15a9a96a1dca06ef"},
+    {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7ab55401287bfec946ced39700c053796e7cc0e3acbef09993a9ad2adba6ca6e"},
+    {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:666dbfb6ec68962c033a450943ded891bed2d54e6755e35e5835d63f4f6931d5"},
+    {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:96ff0b2ad353d8f990b63294c8986f1ec3cb19d749234014f4e7eb0112ceba5a"},
+    {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:60dedbb91afcbfdc9bc0b1f3f402804070deed7392c23eb7a7f07fa857868e8a"},
+    {file = "numpy-1.26.4-cp311-cp311-win32.whl", hash = "sha256:1af303d6b2210eb850fcf03064d364652b7120803a0b872f5211f5234b399f20"},
+    {file = "numpy-1.26.4-cp311-cp311-win_amd64.whl", hash = "sha256:cd25bcecc4974d09257ffcd1f098ee778f7834c3ad767fe5db785be9a4aa9cb2"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:afedb719a9dcfc7eaf2287b839d8198e06dcd4cb5d276a3df279231138e83d30"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95a7476c59002f2f6c590b9b7b998306fba6a5aa646b1e22ddfeaf8f78c3a29c"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7e50d0a0cc3189f9cb0aeb3a6a6af18c16f59f004b866cd2be1c14b36134a4a0"},
+    {file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"},
+]
+
+[[package]]
+name = "nvidia-cublas-cu12"
+version = "12.1.3.1"
+requires_python = ">=3"
+summary = "CUBLAS native runtime libraries"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+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"
+requires_python = ">=3"
+summary = "CUDA profiling tools runtime libs."
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+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"
+requires_python = ">=3"
+summary = "NVRTC native runtime libraries"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+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"
+requires_python = ">=3"
+summary = "CUDA Runtime native Libraries"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+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"
+requires_python = ">=3"
+summary = "cuDNN runtime libraries"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+dependencies = [
+    "nvidia-cublas-cu12",
+]
+files = [
+    {file = "nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl", hash = "sha256:5ccb288774fdfb07a7e7025ffec286971c06d8d7b4fb162525334616d7629ff9"},
+]
+
+[[package]]
+name = "nvidia-cufft-cu12"
+version = "11.0.2.54"
+requires_python = ">=3"
+summary = "CUFFT native runtime libraries"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+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"
+requires_python = ">=3"
+summary = "CURAND native runtime libraries"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+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"
+requires_python = ">=3"
+summary = "CUDA solver native runtime libraries"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+dependencies = [
+    "nvidia-cublas-cu12",
+    "nvidia-cusparse-cu12",
+    "nvidia-nvjitlink-cu12",
+]
+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]]
+name = "nvidia-cusparse-cu12"
+version = "12.1.0.106"
+requires_python = ">=3"
+summary = "CUSPARSE native runtime libraries"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+dependencies = [
+    "nvidia-nvjitlink-cu12",
+]
+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]]
+name = "nvidia-nccl-cu12"
+version = "2.19.3"
+requires_python = ">=3"
+summary = "NVIDIA Collective Communication Library (NCCL) Runtime"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+files = [
+    {file = "nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl", hash = "sha256:a9734707a2c96443331c1e48c717024aa6678a0e2a4cb66b2c364d18cee6b48d"},
+]
+
+[[package]]
+name = "nvidia-nvjitlink-cu12"
+version = "12.4.127"
+requires_python = ">=3"
+summary = "Nvidia JIT LTO Library"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+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"
+requires_python = ">=3"
+summary = "NVIDIA Tools Extension"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+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 = "packaging"
+version = "24.0"
+requires_python = ">=3.7"
+summary = "Core utilities for Python packages"
+groups = ["default"]
+files = [
+    {file = "packaging-24.0-py3-none-any.whl", hash = "sha256:2ddfb553fdf02fb784c234c7ba6ccc288296ceabec964ad2eae3777778130bc5"},
+    {file = "packaging-24.0.tar.gz", hash = "sha256:eb82c5e3e56209074766e6885bb04b8c38a0c015d0a30036ebe7ece34c9989e9"},
+]
+
+[[package]]
+name = "pillow"
+version = "10.3.0"
+requires_python = ">=3.8"
+summary = "Python Imaging Library (Fork)"
+groups = ["default"]
+files = [
+    {file = "pillow-10.3.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:5f77cf66e96ae734717d341c145c5949c63180842a545c47a0ce7ae52ca83795"},
+    {file = "pillow-10.3.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e4b878386c4bf293578b48fc570b84ecfe477d3b77ba39a6e87150af77f40c57"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fdcbb4068117dfd9ce0138d068ac512843c52295ed996ae6dd1faf537b6dbc27"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9797a6c8fe16f25749b371c02e2ade0efb51155e767a971c61734b1bf6293994"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:9e91179a242bbc99be65e139e30690e081fe6cb91a8e77faf4c409653de39451"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:1b87bd9d81d179bd8ab871603bd80d8645729939f90b71e62914e816a76fc6bd"},
+    {file = "pillow-10.3.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:81d09caa7b27ef4e61cb7d8fbf1714f5aec1c6b6c5270ee53504981e6e9121ad"},
+    {file = "pillow-10.3.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:048ad577748b9fa4a99a0548c64f2cb8d672d5bf2e643a739ac8faff1164238c"},
+    {file = "pillow-10.3.0-cp311-cp311-win32.whl", hash = "sha256:7161ec49ef0800947dc5570f86568a7bb36fa97dd09e9827dc02b718c5643f09"},
+    {file = "pillow-10.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:8eb0908e954d093b02a543dc963984d6e99ad2b5e36503d8a0aaf040505f747d"},
+    {file = "pillow-10.3.0-cp311-cp311-win_arm64.whl", hash = "sha256:4e6f7d1c414191c1199f8996d3f2282b9ebea0945693fb67392c75a3a320941f"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-macosx_10_10_x86_64.whl", hash = "sha256:6b02471b72526ab8a18c39cb7967b72d194ec53c1fd0a70b050565a0f366d355"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:8ab74c06ffdab957d7670c2a5a6e1a70181cd10b727cd788c4dd9005b6a8acd9"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:048eeade4c33fdf7e08da40ef402e748df113fd0b4584e32c4af74fe78baaeb2"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e2ec1e921fd07c7cda7962bad283acc2f2a9ccc1b971ee4b216b75fad6f0463"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:4c8e73e99da7db1b4cad7f8d682cf6abad7844da39834c288fbfa394a47bbced"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:16563993329b79513f59142a6b02055e10514c1a8e86dca8b48a893e33cf91e3"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:dd78700f5788ae180b5ee8902c6aea5a5726bac7c364b202b4b3e3ba2d293170"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-macosx_10_10_x86_64.whl", hash = "sha256:aff76a55a8aa8364d25400a210a65ff59d0168e0b4285ba6bf2bd83cf675ba32"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:b7bc2176354defba3edc2b9a777744462da2f8e921fbaf61e52acb95bafa9828"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:793b4e24db2e8742ca6423d3fde8396db336698c55cd34b660663ee9e45ed37f"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d93480005693d247f8346bc8ee28c72a2191bdf1f6b5db469c096c0c867ac015"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c83341b89884e2b2e55886e8fbbf37c3fa5efd6c8907124aeb72f285ae5696e5"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:1a1d1915db1a4fdb2754b9de292642a39a7fb28f1736699527bb649484fb966a"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:a0eaa93d054751ee9964afa21c06247779b90440ca41d184aeb5d410f20ff591"},
+    {file = "pillow-10.3.0.tar.gz", hash = "sha256:9d2455fbf44c914840c793e89aa82d0e1763a14253a000743719ae5946814b2d"},
+]
+
 [[package]]
 name = "platformdirs"
 version = "4.2.0"
@@ -520,6 +848,24 @@ files = [
     {file = "python_dateutil-2.8.2-py2.py3-none-any.whl", hash = "sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9"},
 ]
 
+[[package]]
+name = "pyyaml"
+version = "6.0.1"
+requires_python = ">=3.6"
+summary = "YAML parser and emitter for Python"
+groups = ["default"]
+files = [
+    {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
+    {file = "PyYAML-6.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f003ed9ad21d6a4713f0a9b5a7a0a79e08dd0f221aff4525a2be4c346ee60aab"},
+    {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
+    {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
+    {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
+    {file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
+    {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
+    {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
+    {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
+]
+
 [[package]]
 name = "redis"
 version = "5.0.1"
@@ -534,6 +880,31 @@ files = [
     {file = "redis-5.0.1.tar.gz", hash = "sha256:0dab495cd5753069d3bc650a0dde8a8f9edde16fc5691b689a566eda58100d0f"},
 ]
 
+[[package]]
+name = "regex"
+version = "2023.12.25"
+requires_python = ">=3.7"
+summary = "Alternative regular expression module, to replace re."
+groups = ["default"]
+files = [
+    {file = "regex-2023.12.25-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:1b9d811f72210fa9306aeb88385b8f8bcef0dfbf3873410413c00aa94c56c2b6"},
+    {file = "regex-2023.12.25-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d902a43085a308cef32c0d3aea962524b725403fd9373dea18110904003bac97"},
+    {file = "regex-2023.12.25-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d166eafc19f4718df38887b2bbe1467a4f74a9830e8605089ea7a30dd4da8887"},
+    {file = "regex-2023.12.25-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c7ad32824b7f02bb3c9f80306d405a1d9b7bb89362d68b3c5a9be53836caebdb"},
+    {file = "regex-2023.12.25-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:636ba0a77de609d6510235b7f0e77ec494d2657108f777e8765efc060094c98c"},
+    {file = "regex-2023.12.25-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0fda75704357805eb953a3ee15a2b240694a9a514548cd49b3c5124b4e2ad01b"},
+    {file = "regex-2023.12.25-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f72cbae7f6b01591f90814250e636065850c5926751af02bb48da94dfced7baa"},
+    {file = "regex-2023.12.25-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:db2a0b1857f18b11e3b0e54ddfefc96af46b0896fb678c85f63fb8c37518b3e7"},
+    {file = "regex-2023.12.25-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:7502534e55c7c36c0978c91ba6f61703faf7ce733715ca48f499d3dbbd7657e0"},
+    {file = "regex-2023.12.25-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:e8c7e08bb566de4faaf11984af13f6bcf6a08f327b13631d41d62592681d24fe"},
+    {file = "regex-2023.12.25-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:283fc8eed679758de38fe493b7d7d84a198b558942b03f017b1f94dda8efae80"},
+    {file = "regex-2023.12.25-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:f44dd4d68697559d007462b0a3a1d9acd61d97072b71f6d1968daef26bc744bd"},
+    {file = "regex-2023.12.25-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:67d3ccfc590e5e7197750fcb3a2915b416a53e2de847a728cfa60141054123d4"},
+    {file = "regex-2023.12.25-cp311-cp311-win32.whl", hash = "sha256:68191f80a9bad283432385961d9efe09d783bcd36ed35a60fb1ff3f1ec2efe87"},
+    {file = "regex-2023.12.25-cp311-cp311-win_amd64.whl", hash = "sha256:7d2af3f6b8419661a0c421584cfe8aaec1c0e435ce7e47ee2a97e344b98f794f"},
+    {file = "regex-2023.12.25.tar.gz", hash = "sha256:29171aa128da69afdf4bde412d5bedc335f2ca8fcfe4489038577d05f16181e5"},
+]
+
 [[package]]
 name = "requests"
 version = "2.31.0"
@@ -610,6 +981,116 @@ files = [
     {file = "s3transfer-0.10.0.tar.gz", hash = "sha256:d0c8bbf672d5eebbe4e57945e23b972d963f07d82f661cabf678a5c88831595b"},
 ]
 
+[[package]]
+name = "safetensors"
+version = "0.4.2"
+requires_python = ">=3.7"
+summary = ""
+groups = ["default"]
+files = [
+    {file = "safetensors-0.4.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:c5dd2ed788730ed56b415d1a11c62026b8cc8c573f55a2092afb3ab383e94fff"},
+    {file = "safetensors-0.4.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:cc41791b33efb9c83a59b731619f3d15f543dfe71f3a793cb8fbf9bd5d0d5d71"},
+    {file = "safetensors-0.4.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4c888bf71d5ca12a720f1ed87d407c4918afa022fb247a6546d8fac15b1f112b"},
+    {file = "safetensors-0.4.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e6b2feb4b47226a16a792e6fac3f49442714884a3d4c1008569d5068a3941be9"},
+    {file = "safetensors-0.4.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f41cc0ee4b838ae8f4d8364a1b162067693d11a3893f0863be8c228d40e4d0ee"},
+    {file = "safetensors-0.4.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:51b7228e46c0a483c40ba4b9470dea00fb1ff8685026bb4766799000f6328ac2"},
+    {file = "safetensors-0.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:02697f8f2be8ca3c37a4958702dbdb1864447ef765e18b5328a1617022dcf164"},
+    {file = "safetensors-0.4.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:27fd8f65cf7c80e4280cae1ee6bcd85c483882f6580821abe71ee1a0d3dcfca7"},
+    {file = "safetensors-0.4.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c487b5f113b0924c9534a07dc034830fb4ef05ce9bb6d78cfe016a7dedfe281f"},
+    {file = "safetensors-0.4.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:da7f6483f3fe67ff39b3a55552552c67930ea10a36e9f2539d36fc205273d767"},
+    {file = "safetensors-0.4.2-cp311-none-win32.whl", hash = "sha256:52a7012f6cb9cb4a132760b6308daede18a9f5f8952ce08adc7c67a7d865c2d8"},
+    {file = "safetensors-0.4.2-cp311-none-win_amd64.whl", hash = "sha256:4d1361a097ac430b310ce9eed8ed4746edee33ddafdfbb965debc8966fc34dc2"},
+    {file = "safetensors-0.4.2-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:4e70d442ad17e8b153ef9095bf48ea64f15a66bf26dc2b6ca94660c154edbc24"},
+    {file = "safetensors-0.4.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:b90f1d9809caf4ff395951b4703295a68d12907f6945bbc3129e934ff8ae46f6"},
+    {file = "safetensors-0.4.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c7ac9ad3728838006598e296b3ae9f27d80b489effd4685b92d97b3fc4c98f6"},
+    {file = "safetensors-0.4.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:de5730d77e6ff7f4c7039e20913661ad0ea2f86c09e71c039e73dfdd1f394f08"},
+    {file = "safetensors-0.4.2-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:44feb8cb156d6803dcd19fc6b81b27235f29b877660605a6ac35e1da7d64f0e4"},
+    {file = "safetensors-0.4.2-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:523a241c33e7c827ab9a3a23760d75c7d062f43dfe55b6b019409f89b0fb52d1"},
+    {file = "safetensors-0.4.2-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:fb18300e8eb74291225214f26c9a8ae2110fd61a6c9b5a2ff4c4e0eb1bb9a998"},
+    {file = "safetensors-0.4.2-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:fe5437ff9fb116e44f2ab558981249ae63f978392b4576e62fcfe167d353edbc"},
+    {file = "safetensors-0.4.2-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d9304a0934ced5a5d272f39de36291dc141dfc152d277f03fb4d65f2fb2ffa7c"},
+    {file = "safetensors-0.4.2-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:160ba1b1e11cf874602c233ab80a14f588571d09556cbc3586900121d622b5ed"},
+    {file = "safetensors-0.4.2-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:04fcd6fcf7d9c13c7e5dc7e08de5e492ee4daa8f4ad74b4d8299d3eb0224292f"},
+    {file = "safetensors-0.4.2-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:906d14c4a677d35834fb0f3a5455ef8305e1bba10a5e0f2e0f357b3d1ad989f2"},
+    {file = "safetensors-0.4.2-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:df3fcdec0cd543084610d1f09c65cdb10fb3079f79bceddc092b0d187c6a265b"},
+    {file = "safetensors-0.4.2-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:5ca76f13fb1cef242ea3ad2cb37388e7d005994f42af8b44bee56ba48b2d45ce"},
+    {file = "safetensors-0.4.2-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:278a1a3414c020785decdcd741c578725721274d2f9f787fcc930882e83b89cc"},
+    {file = "safetensors-0.4.2-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:05b5a461cc68ecd42d9d546e5e1268a39d8ede7934a68d1ce17c3c659cb829d6"},
+    {file = "safetensors-0.4.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c2341411412a41671d25e26bed59ec121e46bf4fadb8132895e610411c4b9681"},
+    {file = "safetensors-0.4.2-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:3497ac3895acf17c5f98197f1fa4769f09c5e7ede07fcb102f1c201e663e052c"},
+    {file = "safetensors-0.4.2-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:01b5e71d3754d2201294f1eb7a6d59cce3a5702ff96d83d226571b2ca2183837"},
+    {file = "safetensors-0.4.2-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:3627dbd1ea488dd8046a0491de5087f3c0d641e7acc80c0189a33c69398f1cd1"},
+    {file = "safetensors-0.4.2-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:9d56f0ef53afad26ec54ceede78a43e9a23a076dadbbda7b44d304c591abf4c1"},
+    {file = "safetensors-0.4.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:b259ca73d42daf658a1bda463f1f83885ae4d93a60869be80d7f7dfcc9d8bbb5"},
+    {file = "safetensors-0.4.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1ebc3cd401e4eb54e7c0a70346be565e81942d9a41fafd5f4bf7ab3a55d10378"},
+    {file = "safetensors-0.4.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5bc384a0309b706aa0425c93abb0390508a61bf029ce99c7d9df4220f25871a5"},
+    {file = "safetensors-0.4.2-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:af2d8f7235d8a08fbccfb8394387890e7fa38942b349a94e6eff13c52ac98087"},
+    {file = "safetensors-0.4.2-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:0911315bbcc5289087d063c2c2c7ccd711ea97a7e557a7bce005ac2cf80146aa"},
+    {file = "safetensors-0.4.2-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:1efe31673be91832d73439a2af426743e1395fc9ef7b081914e9e1d567bd7b5f"},
+    {file = "safetensors-0.4.2.tar.gz", hash = "sha256:acc85dcb09ec5e8aa787f588d7ad4d55c103f31e4ff060e17d92cc0e8b8cac73"},
+]
+
+[[package]]
+name = "scikit-learn"
+version = "1.4.2"
+requires_python = ">=3.9"
+summary = "A set of python modules for machine learning and data mining"
+groups = ["default"]
+dependencies = [
+    "joblib>=1.2.0",
+    "numpy>=1.19.5",
+    "scipy>=1.6.0",
+    "threadpoolctl>=2.0.0",
+]
+files = [
+    {file = "scikit-learn-1.4.2.tar.gz", hash = "sha256:daa1c471d95bad080c6e44b4946c9390a4842adc3082572c20e4f8884e39e959"},
+    {file = "scikit_learn-1.4.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:45dee87ac5309bb82e3ea633955030df9bbcb8d2cdb30383c6cd483691c546cc"},
+    {file = "scikit_learn-1.4.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:1d0b25d9c651fd050555aadd57431b53d4cf664e749069da77f3d52c5ad14b3b"},
+    {file = "scikit_learn-1.4.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b0203c368058ab92efc6168a1507d388d41469c873e96ec220ca8e74079bf62e"},
+    {file = "scikit_learn-1.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:44c62f2b124848a28fd695db5bc4da019287abf390bfce602ddc8aa1ec186aae"},
+    {file = "scikit_learn-1.4.2-cp311-cp311-win_amd64.whl", hash = "sha256:5cd7b524115499b18b63f0c96f4224eb885564937a0b3477531b2b63ce331904"},
+]
+
+[[package]]
+name = "scipy"
+version = "1.13.0"
+requires_python = ">=3.9"
+summary = "Fundamental algorithms for scientific computing in Python"
+groups = ["default"]
+dependencies = [
+    "numpy<2.3,>=1.22.4",
+]
+files = [
+    {file = "scipy-1.13.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0fbcf8abaf5aa2dc8d6400566c1a727aed338b5fe880cde64907596a89d576fa"},
+    {file = "scipy-1.13.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:5e4a756355522eb60fcd61f8372ac2549073c8788f6114449b37e9e8104f15a5"},
+    {file = "scipy-1.13.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b5acd8e1dbd8dbe38d0004b1497019b2dbbc3d70691e65d69615f8a7292865d7"},
+    {file = "scipy-1.13.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9ff7dad5d24a8045d836671e082a490848e8639cabb3dbdacb29f943a678683d"},
+    {file = "scipy-1.13.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:4dca18c3ffee287ddd3bc8f1dabaf45f5305c5afc9f8ab9cbfab855e70b2df5c"},
+    {file = "scipy-1.13.0-cp311-cp311-win_amd64.whl", hash = "sha256:a2f471de4d01200718b2b8927f7d76b5d9bde18047ea0fa8bd15c5ba3f26a1d6"},
+    {file = "scipy-1.13.0.tar.gz", hash = "sha256:58569af537ea29d3f78e5abd18398459f195546bb3be23d16677fb26616cc11e"},
+]
+
+[[package]]
+name = "sentence-transformers"
+version = "2.6.1"
+requires_python = ">=3.8.0"
+summary = "Multilingual text embeddings"
+groups = ["default"]
+dependencies = [
+    "Pillow",
+    "huggingface-hub>=0.15.1",
+    "numpy",
+    "scikit-learn",
+    "scipy",
+    "torch>=1.11.0",
+    "tqdm",
+    "transformers<5.0.0,>=4.32.0",
+]
+files = [
+    {file = "sentence-transformers-2.6.1.tar.gz", hash = "sha256:633ad6b70e390ea335de8689652a5d6c21a323b79ed19519c2f392451088487f"},
+    {file = "sentence_transformers-2.6.1-py3-none-any.whl", hash = "sha256:a887e17696b513f99a709ce1f37fd547f53857aebe863785ede546c303b09ea0"},
+]
+
 [[package]]
 name = "six"
 version = "1.16.0"
@@ -632,6 +1113,167 @@ files = [
     {file = "soupsieve-2.5.tar.gz", hash = "sha256:5663d5a7b3bfaeee0bc4372e7fc48f9cff4940b3eec54a6451cc5299f1097690"},
 ]
 
+[[package]]
+name = "sympy"
+version = "1.12"
+requires_python = ">=3.8"
+summary = "Computer algebra system (CAS) in Python"
+groups = ["default"]
+dependencies = [
+    "mpmath>=0.19",
+]
+files = [
+    {file = "sympy-1.12-py3-none-any.whl", hash = "sha256:c3588cd4295d0c0f603d0f2ae780587e64e2efeedb3521e46b9bb1d08d184fa5"},
+    {file = "sympy-1.12.tar.gz", hash = "sha256:ebf595c8dac3e0fdc4152c51878b498396ec7f30e7a914d6071e674d49420fb8"},
+]
+
+[[package]]
+name = "threadpoolctl"
+version = "3.4.0"
+requires_python = ">=3.8"
+summary = "threadpoolctl"
+groups = ["default"]
+files = [
+    {file = "threadpoolctl-3.4.0-py3-none-any.whl", hash = "sha256:8f4c689a65b23e5ed825c8436a92b818aac005e0f3715f6a1664d7c7ee29d262"},
+    {file = "threadpoolctl-3.4.0.tar.gz", hash = "sha256:f11b491a03661d6dd7ef692dd422ab34185d982466c49c8f98c8f716b5c93196"},
+]
+
+[[package]]
+name = "tokenizers"
+version = "0.15.2"
+requires_python = ">=3.7"
+summary = ""
+groups = ["default"]
+dependencies = [
+    "huggingface-hub<1.0,>=0.16.4",
+]
+files = [
+    {file = "tokenizers-0.15.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:89cd1cb93e4b12ff39bb2d626ad77e35209de9309a71e4d3d4672667b4b256e7"},
+    {file = "tokenizers-0.15.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:cfed5c64e5be23d7ee0f0e98081a25c2a46b0b77ce99a4f0605b1ec43dd481fa"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:a907d76dcfda37023ba203ab4ceeb21bc5683436ebefbd895a0841fd52f6f6f2"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:20ea60479de6fc7b8ae756b4b097572372d7e4032e2521c1bbf3d90c90a99ff0"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:48e2b9335be2bc0171df9281385c2ed06a15f5cf121c44094338306ab7b33f2c"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:112a1dd436d2cc06e6ffdc0b06d55ac019a35a63afd26475205cb4b1bf0bfbff"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4620cca5c2817177ee8706f860364cc3a8845bc1e291aaf661fb899e5d1c45b0"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ccd73a82751c523b3fc31ff8194702e4af4db21dc20e55b30ecc2079c5d43cb7"},
+    {file = "tokenizers-0.15.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:107089f135b4ae7817affe6264f8c7a5c5b4fd9a90f9439ed495f54fcea56fb4"},
+    {file = "tokenizers-0.15.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:0ff110ecc57b7aa4a594396525a3451ad70988e517237fe91c540997c4e50e29"},
+    {file = "tokenizers-0.15.2-cp311-none-win32.whl", hash = "sha256:6d76f00f5c32da36c61f41c58346a4fa7f0a61be02f4301fd30ad59834977cc3"},
+    {file = "tokenizers-0.15.2-cp311-none-win_amd64.whl", hash = "sha256:cc90102ed17271cf0a1262babe5939e0134b3890345d11a19c3145184b706055"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:6a9b648a58281c4672212fab04e60648fde574877d0139cd4b4f93fe28ca8944"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:7c7d18b733be6bbca8a55084027f7be428c947ddf871c500ee603e375013ffba"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:13ca3611de8d9ddfbc4dc39ef54ab1d2d4aaa114ac8727dfdc6a6ec4be017378"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:237d1bf3361cf2e6463e6c140628e6406766e8b27274f5fcc62c747ae3c6f094"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:67a0fe1e49e60c664915e9fb6b0cb19bac082ab1f309188230e4b2920230edb3"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:4e022fe65e99230b8fd89ebdfea138c24421f91c1a4f4781a8f5016fd5cdfb4d"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:d857be2df69763362ac699f8b251a8cd3fac9d21893de129bc788f8baaef2693"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:708bb3e4283177236309e698da5fcd0879ce8fd37457d7c266d16b550bcbbd18"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:64c35e09e9899b72a76e762f9854e8750213f67567787d45f37ce06daf57ca78"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c1257f4394be0d3b00de8c9e840ca5601d0a4a8438361ce9c2b05c7d25f6057b"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:02272fe48280e0293a04245ca5d919b2c94a48b408b55e858feae9618138aeda"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:dc3ad9ebc76eabe8b1d7c04d38be884b8f9d60c0cdc09b0aa4e3bcf746de0388"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:32e16bdeffa7c4f46bf2152172ca511808b952701d13e7c18833c0b73cb5c23f"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:fb16ba563d59003028b678d2361a27f7e4ae0ab29c7a80690efa20d829c81fdb"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:2277c36d2d6cdb7876c274547921a42425b6810d38354327dd65a8009acf870c"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:1cf75d32e8d250781940d07f7eece253f2fe9ecdb1dc7ba6e3833fa17b82fcbc"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f1b3b31884dc8e9b21508bb76da80ebf7308fdb947a17affce815665d5c4d028"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b10122d8d8e30afb43bb1fe21a3619f62c3e2574bff2699cf8af8b0b6c5dc4a3"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:d88b96ff0fe8e91f6ef01ba50b0d71db5017fa4e3b1d99681cec89a85faf7bf7"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:37aaec5a52e959892870a7c47cef80c53797c0db9149d458460f4f31e2fb250e"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e2ea752f2b0fe96eb6e2f3adbbf4d72aaa1272079b0dfa1145507bd6a5d537e6"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:4b19a808d8799fda23504a5cd31d2f58e6f52f140380082b352f877017d6342b"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:64c86e5e068ac8b19204419ed8ca90f9d25db20578f5881e337d203b314f4104"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:de19c4dc503c612847edf833c82e9f73cd79926a384af9d801dcf93f110cea4e"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea09acd2fe3324174063d61ad620dec3bcf042b495515f27f638270a7d466e8b"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:cf27fd43472e07b57cf420eee1e814549203d56de00b5af8659cb99885472f1f"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:7ca22bd897537a0080521445d91a58886c8c04084a6a19e6c78c586e0cfa92a5"},
+    {file = "tokenizers-0.15.2.tar.gz", hash = "sha256:e6e9c6e019dd5484be5beafc775ae6c925f4c69a3487040ed09b45e13df2cb91"},
+]
+
+[[package]]
+name = "torch"
+version = "2.2.2"
+requires_python = ">=3.8.0"
+summary = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
+groups = ["default"]
+dependencies = [
+    "filelock",
+    "fsspec",
+    "jinja2",
+    "networkx",
+    "nvidia-cublas-cu12==12.1.3.1; platform_system == \"Linux\" and platform_machine == \"x86_64\"",
+    "nvidia-cuda-cupti-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\"",
+    "nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\"",
+    "nvidia-cuda-runtime-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\"",
+    "nvidia-cudnn-cu12==8.9.2.26; platform_system == \"Linux\" and platform_machine == \"x86_64\"",
+    "nvidia-cufft-cu12==11.0.2.54; platform_system == \"Linux\" and platform_machine == \"x86_64\"",
+    "nvidia-curand-cu12==10.3.2.106; platform_system == \"Linux\" and platform_machine == \"x86_64\"",
+    "nvidia-cusolver-cu12==11.4.5.107; platform_system == \"Linux\" and platform_machine == \"x86_64\"",
+    "nvidia-cusparse-cu12==12.1.0.106; platform_system == \"Linux\" and platform_machine == \"x86_64\"",
+    "nvidia-nccl-cu12==2.19.3; platform_system == \"Linux\" and platform_machine == \"x86_64\"",
+    "nvidia-nvtx-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\"",
+    "sympy",
+    "triton==2.2.0; platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.12\"",
+    "typing-extensions>=4.8.0",
+]
+files = [
+    {file = "torch-2.2.2-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:ad4c03b786e074f46606f4151c0a1e3740268bcf29fbd2fdf6666d66341c1dcb"},
+    {file = "torch-2.2.2-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:32827fa1fbe5da8851686256b4cd94cc7b11be962862c2293811c94eea9457bf"},
+    {file = "torch-2.2.2-cp311-cp311-win_amd64.whl", hash = "sha256:f9ef0a648310435511e76905f9b89612e45ef2c8b023bee294f5e6f7e73a3e7c"},
+    {file = "torch-2.2.2-cp311-none-macosx_10_9_x86_64.whl", hash = "sha256:95b9b44f3bcebd8b6cd8d37ec802048c872d9c567ba52c894bba90863a439059"},
+    {file = "torch-2.2.2-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:49aa4126ede714c5aeef7ae92969b4b0bbe67f19665106463c39f22e0a1860d1"},
+]
+
+[[package]]
+name = "tqdm"
+version = "4.66.2"
+requires_python = ">=3.7"
+summary = "Fast, Extensible Progress Meter"
+groups = ["default"]
+dependencies = [
+    "colorama; platform_system == \"Windows\"",
+]
+files = [
+    {file = "tqdm-4.66.2-py3-none-any.whl", hash = "sha256:1ee4f8a893eb9bef51c6e35730cebf234d5d0b6bd112b0271e10ed7c24a02bd9"},
+    {file = "tqdm-4.66.2.tar.gz", hash = "sha256:6cd52cdf0fef0e0f543299cfc96fec90d7b8a7e88745f411ec33eb44d5ed3531"},
+]
+
+[[package]]
+name = "transformers"
+version = "4.39.3"
+requires_python = ">=3.8.0"
+summary = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
+groups = ["default"]
+dependencies = [
+    "filelock",
+    "huggingface-hub<1.0,>=0.19.3",
+    "numpy>=1.17",
+    "packaging>=20.0",
+    "pyyaml>=5.1",
+    "regex!=2019.12.17",
+    "requests",
+    "safetensors>=0.4.1",
+    "tokenizers<0.19,>=0.14",
+    "tqdm>=4.27",
+]
+files = [
+    {file = "transformers-4.39.3-py3-none-any.whl", hash = "sha256:7838034a12cca3168247f9d2d1dba6724c9de3ae0f73a108258c6b8fc5912601"},
+    {file = "transformers-4.39.3.tar.gz", hash = "sha256:2586e5ff4150f122716fc40f5530e92871befc051848fbe82600969c535b762d"},
+]
+
+[[package]]
+name = "triton"
+version = "2.2.0"
+summary = "A language and compiler for custom Deep Learning operations"
+groups = ["default"]
+marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.12\""
+dependencies = [
+    "filelock",
+]
+files = [
+    {file = "triton-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:da58a152bddb62cafa9a857dd2bc1f886dbf9f9c90a2b5da82157cd2b34392b0"},
+]
+
 [[package]]
 name = "typing-extensions"
 version = "4.9.0"

pyproject.toml

@@ -18,6 +18,7 @@ dependencies = [
     "aiolimiter>=1.1.0",
     "yarl>=1.9.4",
     "loguru>=0.7.2",
+    "sentence-transformers>=2.6.1",
 ]
 requires-python = "==3.11.*"
 readme = "README.md"

src/de_quoi_parle_le_monde/main.py

@@ -2,14 +2,15 @@ import asyncio
 
 from de_quoi_parle_le_monde.http import HttpClient
 from de_quoi_parle_le_monde.storage import Storage
-from de_quoi_parle_le_monde.snapshot_worker import download_all
+from de_quoi_parle_le_monde.snapshot_worker import download_all, compute_embeddings
 
 
 async def main():
     http_client = HttpClient()
     storage = await Storage.create()
 
-    await download_all(http_client, storage, 10, [18])
+    # await download_all(http_client, storage, 10, [18])
+    await compute_embeddings(storage)
 
 
 asyncio.run(main())

src/de_quoi_parle_le_monde/snapshot_worker.py

@@ -3,6 +3,7 @@ import asyncio
 from attrs import frozen
 import traceback
 from loguru import logger
+from sentence_transformers import SentenceTransformer
 
 from de_quoi_parle_le_monde.http import HttpClient
 from de_quoi_parle_le_monde.internet_archive import (
@@ -106,3 +107,19 @@ async def download_all(
         return await asyncio.gather(
             *[worker.handle_snap(c, d) for d in dts for c in media_collection.values()]
         )
+
+
+@frozen
+class EmbeddingsWorker:
+    storage: Storage
+    model: SentenceTransformer
+
+    @staticmethod
+    def create(storage, model_path):
+        model = SentenceTransformer(model_path)
+        return EmbeddingsWorker(storage, model)
+
+
+async def compute_embeddings(storage: Storage):
+    worker = EmbeddingsWorker.create(storage, "dangvantuan/sentence-camembert-large")
+    return worker

src/de_quoi_parle_le_monde/storage.py

@@ -194,6 +194,22 @@ class Storage:
                 """
             )
 
+            await conn.execute(
+                """
+                CREATE TABLE IF NOT EXISTS articles_embeddings (
+                    id INTEGER PRIMARY KEY AUTOINCREMENT,
+                    featured_article_snapshot_id INTEGER REFERENCES featured_article_snapshots (id) ON DELETE CASCADE,
+                    title_embedding BLOB
+                );
+                """
+            )
+            await conn.execute(
+                """
+                CREATE UNIQUE INDEX IF NOT EXISTS articles_embeddings_unique_idx_featured_article_snapshot_id
+                ON articles_embeddings (featured_article_snapshot_id);
+            """
+            )
+
     async def add_site(self, name: str, original_url: str) -> int:
         return await self._insert_or_get(
             self._insert_stmt("sites", ["name", "original_url"]),