extract-python 0.10.3__tar.gz → 0.10.4__tar.gz

{extract_python-0.10.3 → extract_python-0.10.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: extract-python
-Version: 0.10.3
+Version: 0.10.4
 Summary: Structured content extraction
 Project-URL: Homepage, https://github.com/ICIJ/extract-python
 Project-URL: Repository, https://github.com/ICIJ/extract-python

{extract_python-0.10.3 → extract_python-0.10.4}/pyproject.toml

@@ -51,6 +51,9 @@ required-environments = [
   "sys_platform == 'darwin' and platform_machine == 'arm64'",
   "sys_platform == 'linux'",
 ]
+exclude-dependencies = [
+  "mlx-vlm",
+]
 override-dependencies = [
   "pillow==11.3.0",
 ]

{extract_python-0.10.3 → extract_python-0.10.4}/uv.lock

@@ -26,6 +26,7 @@ conflicts = [[
 
 [manifest]
 overrides = [{ name = "pillow", specifier = "==11.3.0" }]
+excludes = ["mlx-vlm"]
 
 [[package]]
 name = "accelerate"
@@ -279,6 +280,32 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/f6/22/91616fe707a5c5510de2cac9b046a30defe7007ba8a0c04f9c08f27df312/audioop_lts-0.2.2-cp314-cp314t-win_arm64.whl", hash = "sha256:b492c3b040153e68b9fdaff5913305aaaba5bb433d8a7f73d5cf6a64ed3cc1dd", size = 25206, upload-time = "2025-08-05T16:43:16.444Z" },
 ]
 
+[[package]]
+name = "av"
+version = "19.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/90/bc/a2a40e503250fe5d4174471911828f31658864eb69a8a7cb960c715e17b7/av-19.0.1.tar.gz", hash = "sha256:08674930eaf1af78a3ed8f93d3ba49383323b3a867e84349d9c399e36f7497da", size = 4274648, upload-time = "2026-10-03T01:48:28.575Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ec/2f/f4d219b2c72fea88bcbaea23de5b7f864ebecd348586fd2fe69f7f657147/av-19.0.1-cp312-abi3-macosx_11_0_x86_64.whl", hash = "sha256:2bd44ef4c09bb04aa6100d4c6191ddedaffef6af757ac55d5b4dc90915859299", size = 22625494, upload-time = "2026-10-03T01:47:21.866Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/75/db37bb43a12a317cc0c0b96ddabc7896f582503b377e0803d4d721969522/av-19.0.1-cp312-abi3-macosx_14_0_arm64.whl", hash = "sha256:29d85e4ee36bf8f475dad07d4f4417c07bba62535f6a7179429c357e0ca8fb0f", size = 18439188, upload-time = "2026-10-03T01:47:25.541Z" },
+    { url = "https://files.pythonhosted.org/packages/10/4b/61f138fcf21e7bb50655ed21dd7fdc7a296baf72ea3c7ad8e89cb00b69c1/av-19.0.1-cp312-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:437d4c0d5a7d771f2c3af84cd28e6aac6e173851116c60b53e81dbf1eebe4eab", size = 32676941, upload-time = "2026-10-03T01:47:29.237Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/97/5fb45934ac64e8afc2c6869a7dcb8cb2af1ddab09a725367548856cbb59f/av-19.0.1-cp312-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:1bea5b6134209305199bce7627ac3d33964de2cf2b09c77d08e7f67cf8bd4170", size = 34983451, upload-time = "2026-10-03T01:47:32.895Z" },
+    { url = "https://files.pythonhosted.org/packages/66/f2/6eee1b99ac492fa1965d6fd466ef8b644ca296b4f1dfa8c8225ab340b139/av-19.0.1-cp312-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:1de938ec0134ad88f795dfe0a2dfc2d59e9ecea39a20158d37961279a3483612", size = 41660680, upload-time = "2026-10-03T01:47:36.903Z" },
+    { url = "https://files.pythonhosted.org/packages/11/be/e4ddd0197d02a3114402f3ffde541f6c4edecd24d670bea0da1eb6f15fb2/av-19.0.1-cp312-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:bcd0af218ecbeddbb1b0c56c4278043a3d97b87f3b8e33f6f92d452c744b1b08", size = 33748455, upload-time = "2026-10-03T01:47:40.541Z" },
+    { url = "https://files.pythonhosted.org/packages/7a/41/b9af863f635f64abaf5eb734521306487fc79447f5d55d792339a81c8a4d/av-19.0.1-cp312-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:935a6b6386a6994964e324eb02af4dab01eedbcbbde23b4b21bf1dc59b004244", size = 36008899, upload-time = "2026-10-03T01:47:44.13Z" },
+    { url = "https://files.pythonhosted.org/packages/e6/dc/a87a5a5e3ac462734f9befd8bad1447301e5802d8c111e22bf708fba7af3/av-19.0.1-cp312-abi3-win_amd64.whl", hash = "sha256:906fc3db09288319a75ea23ffefb59961c7dbe0d1c074601507a89de7d8593d8", size = 28149519, upload-time = "2026-10-03T01:47:47.372Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/78/16864f1aa2c3ac5017f15132b85c6d3c74bb85caca8c45ce836ad30dfe20/av-19.0.1-cp312-abi3-win_arm64.whl", hash = "sha256:e9e1b0cae6cebd2adc2c5c6691fc890112f8f6c846b76a9135307617db1e32e9", size = 20706822, upload-time = "2026-10-03T01:47:50.72Z" },
+    { url = "https://files.pythonhosted.org/packages/78/4a/b5d7614856af72d7c18b926dda43bd227844b0b42d64e7c478b080f8d9c1/av-19.0.1-cp314-cp314t-macosx_11_0_x86_64.whl", hash = "sha256:3ef376ab828730f50b635e3541f305503adad713cb4c3eadb5ad0e4c6a6f4a72", size = 22909764, upload-time = "2026-10-03T01:47:54.032Z" },
+    { url = "https://files.pythonhosted.org/packages/b6/c9/50b2dedd4314a0ba0d78d7a7a52f7b073bc3377e5152e51d9d5627c5bcf4/av-19.0.1-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:17f2e42a1c969c78c616fe58bc69641a9df404c1ac2f01b50c1ddc22e5c31f69", size = 18718945, upload-time = "2026-10-03T01:47:58.396Z" },
+    { url = "https://files.pythonhosted.org/packages/ef/a5/eb2b6aadbda16ee676c76e43012709f0cdfe09c35bc9ad4ffb5099827e72/av-19.0.1-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:aafd294abd0e5c23e6c813b10fb4792cf1dd1002c1aead0292d195cda2ca154e", size = 36470355, upload-time = "2026-10-03T01:48:01.686Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/f0/25e7d21cc29e949118bdac6efe0ef5c5020fc4273a3ea237989728ebe816/av-19.0.1-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:400ba5234865dc370c442658efff0672c64dcad2de26a2a7c900abf16ffd9f68", size = 38457564, upload-time = "2026-10-03T01:48:05.61Z" },
+    { url = "https://files.pythonhosted.org/packages/3f/09/77fec7c8de49fb815d55de1dfac21b39fb9e6915cbd8dcd945538ebb6f44/av-19.0.1-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:5e527b9d2d23c096d2b488e19a40ceba3654ea84a3cecee1c1b46c70ceaceae2", size = 43462245, upload-time = "2026-10-03T01:48:10.674Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/1d/bb0281ada4203c5d85f7e8b045de2cadc89c3b5d0ed5705298f7a9288b1f/av-19.0.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:79136e62d4bc93db81fb63d6dd0060e86259426c071ca5157b1abe8c815c40b7", size = 37339005, upload-time = "2026-10-03T01:48:14.805Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/84/19a9d37d7546a3879d759a8957b2513a029cafb81f60218c496b1ce9d5a8/av-19.0.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:330f91c704aa822b96d9aa21382c0eb41a68531d388078d724d334faa460cbcc", size = 39466754, upload-time = "2026-10-03T01:48:18.988Z" },
+    { url = "https://files.pythonhosted.org/packages/30/c4/39d4e2b778f1e86672671e25c3fd38e8d59d59b6f65c5cd13d7fae3d88a3/av-19.0.1-cp314-cp314t-win_amd64.whl", hash = "sha256:8289295bfd2a438f2cf83c3ab426964055e441f1500410a842e7a767bdc8e51e", size = 29063526, upload-time = "2026-10-03T01:48:22.724Z" },
+    { url = "https://files.pythonhosted.org/packages/f4/7d/a20ff44c1445c09a93985418f6997e5823635848e955a7953339636a9829/av-19.0.1-cp314-cp314t-win_arm64.whl", hash = "sha256:e1f70b1bda35588aff5fc526500376afe143e33cfce5d7e30d368170c38717db", size = 21915698, upload-time = "2026-10-03T01:48:26.386Z" },
+]
+
 [[package]]
 name = "babel"
 version = "2.18.0"
@@ -691,7 +718,8 @@ wheels = [
 chunking = [
     { name = "semchunk" },
     { name = "transformers", version = "4.57.6", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-marker'" },
-    { name = "transformers", version = "5.15.1", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
+    { name = "transformers", version = "5.15.1", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "transformers", version = "5.18.0", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
     { name = "tree-sitter" },
     { name = "tree-sitter-c" },
     { name = "tree-sitter-javascript" },
@@ -714,7 +742,8 @@ dependencies = [
     { name = "torchvision", version = "0.27.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 'arm64' and sys_platform == 'darwin') or (platform_machine != 'arm64' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru') or (sys_platform != 'darwin' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
     { name = "torchvision", version = "0.27.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 'arm64' or sys_platform != 'darwin' or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
     { name = "transformers", version = "4.57.6", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-marker'" },
-    { name = "transformers", version = "5.15.1", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
+    { name = "transformers", version = "5.15.1", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "transformers", version = "5.18.0", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/69/ee/7dd19487bf333320f0fc73eddcb42347d9f266310ebb1a605f120987f7c1/docling_ibm_models-4.0.3.tar.gz", hash = "sha256:509e89af75e06b48500977dca11ecb6022e81b1526c90dd54587a60ccc82bdb6", size = 77649, upload-time = "2026-09-18T16:15:36.731Z" }
 wheels = [
@@ -773,10 +802,28 @@ feat-ocr-easyocr = [
 feat-ocr-mac = [
     { name = "ocrmac", marker = "sys_platform == 'darwin' or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
 ]
+feat-ocr-rapidocr = [
+    { name = "rapidocr" },
+]
 feat-ocr-tesserocr = [
     { name = "pandas" },
     { name = "tesserocr" },
 ]
+models-onnxruntime = [
+    { name = "onnxruntime", marker = "sys_platform == 'darwin' or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "onnxruntime-gpu", marker = "sys_platform == 'linux' or sys_platform == 'win32' or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+]
+models-vlm-inline = [
+    { name = "accelerate" },
+    { name = "einops" },
+    { name = "open-clip-torch" },
+    { name = "peft" },
+    { name = "qwen-vl-utils" },
+    { name = "timm" },
+    { name = "transformers", version = "4.57.6", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-marker'" },
+    { name = "transformers", version = "5.15.1", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "transformers", version = "5.18.0", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+]
 standard = [
     { name = "accelerate" },
     { name = "beautifulsoup4" },
@@ -957,7 +1004,10 @@ benches = [
     { name = "pypdfium2", version = "5.13.0", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
 ]
 docling = [
-    { name = "docling-slim", extra = ["feat-ocr-easyocr", "feat-ocr-mac", "feat-ocr-tesserocr", "standard"] },
+    { name = "docling-slim", extra = ["feat-ocr-easyocr", "feat-ocr-mac", "feat-ocr-rapidocr", "feat-ocr-tesserocr", "standard"] },
+]
+docling-gpu = [
+    { name = "docling-slim", extra = ["models-onnxruntime", "models-vlm-inline"] },
 ]
 marker = [
     { name = "marker-pdf" },
@@ -982,7 +1032,8 @@ dev = [
 
 [package.metadata]
 requires-dist = [
-    { name = "docling-slim", extras = ["feat-ocr-easyocr", "feat-ocr-mac", "feat-ocr-tesserocr", "standard"], marker = "extra == 'docling'", specifier = "~=2.127" },
+    { name = "docling-slim", extras = ["feat-ocr-easyocr", "feat-ocr-mac", "feat-ocr-rapidocr", "feat-ocr-tesserocr", "standard"], marker = "extra == 'docling'", specifier = "~=2.127" },
+    { name = "docling-slim", extras = ["feat-ocr-nemotron", "models-onnxruntime", "models-vlm-inline"], marker = "extra == 'docling-gpu'", specifier = "~=2.127" },
     { name = "extract-core", editable = "../extract-core" },
     { name = "html2image", marker = "extra == 'benches'", specifier = "~=2.0.7" },
     { name = "icij-common", specifier = "~=0.8.2" },
@@ -996,7 +1047,7 @@ requires-dist = [
     { name = "python-pptx", marker = "extra == 'mineru'", specifier = "~=1.0" },
     { name = "six", marker = "extra == 'mineru'", specifier = "~=1.17" },
 ]
-provides-extras = ["benches", "docling", "marker", "mineru"]
+provides-extras = ["benches", "docling", "docling-gpu", "marker", "mineru"]
 
 [package.metadata.requires-dev]
 dev = [
@@ -2227,11 +2278,12 @@ dependencies = [
     { name = "safetensors", marker = "platform_machine == 'arm64' and sys_platform == 'darwin'" },
     { name = "shapely" },
     { name = "tinycss2" },
-    { name = "tokenizers" },
+    { name = "tokenizers", version = "0.22.2", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform != 'darwin' and extra == 'extra-14-extract-python-mineru') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "tokenizers", version = "0.23.2", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'darwin' and extra == 'extra-14-extract-python-mineru') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
     { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine == 'arm64' and sys_platform == 'darwin'" },
     { name = "torchvision", version = "0.27.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine == 'arm64' and sys_platform == 'darwin'" },
     { name = "tqdm" },
-    { name = "transformers", version = "5.15.1", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine == 'arm64' and sys_platform == 'darwin'" },
+    { name = "transformers", version = "5.18.0", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine == 'arm64' and sys_platform == 'darwin'" },
     { name = "typer" },
     { name = "typing-extensions" },
     { name = "uvicorn" },
@@ -2249,7 +2301,8 @@ torch = [
     { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 'arm64' and extra == 'extra-14-extract-python-mineru') or (sys_platform != 'darwin' and extra == 'extra-14-extract-python-mineru') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
     { name = "torchvision", version = "0.27.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 'arm64' and sys_platform == 'darwin' and extra == 'extra-14-extract-python-mineru') or (platform_machine != 'arm64' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru') or (sys_platform != 'darwin' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
     { name = "torchvision", version = "0.27.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 'arm64' and extra == 'extra-14-extract-python-mineru') or (sys_platform != 'darwin' and extra == 'extra-14-extract-python-mineru') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
-    { name = "transformers", version = "5.15.1", source = { registry = "https://pypi.org/simple" } },
+    { name = "transformers", version = "5.15.1", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform != 'darwin' and extra == 'extra-14-extract-python-mineru') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "transformers", version = "5.18.0", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'darwin' and extra == 'extra-14-extract-python-mineru') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
 ]
 
 [[package]]
@@ -2624,10 +2677,10 @@ name = "onnxruntime"
 version = "1.27.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "flatbuffers" },
-    { name = "numpy" },
-    { name = "packaging" },
-    { name = "protobuf" },
+    { name = "flatbuffers", marker = "sys_platform == 'darwin' or extra == 'extra-14-extract-python-mineru'" },
+    { name = "numpy", marker = "sys_platform == 'darwin' or extra == 'extra-14-extract-python-mineru'" },
+    { name = "packaging", marker = "sys_platform == 'darwin' or extra == 'extra-14-extract-python-mineru'" },
+    { name = "protobuf", marker = "sys_platform == 'darwin' or extra == 'extra-14-extract-python-mineru'" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/fb/2b/54208fd03ad410480bc17edf4869376362da8bbf46fe186ddf4cb5cc20fe/onnxruntime-1.27.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:b3e5b58b8c89c2b20e086e890aa9527377e5c240dc3ecc1640d18e07705eeb1c", size = 18432958, upload-time = "2026-06-15T22:42:53.105Z" },
@@ -2646,6 +2699,52 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b7/f6/2bac21f722aa45d876d4a51f26bd0ef30e704068a3cd5021a5a7cd784271/onnxruntime-1.27.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:370d211e1ceeac4cd5f45301655463ac59e27cdc74d9f7aeb2d19ff4b7a76715", size = 18670781, upload-time = "2026-06-15T22:43:17.151Z" },
 ]
 
+[[package]]
+name = "onnxruntime-gpu"
+version = "1.30.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "flatbuffers", marker = "(sys_platform != 'darwin' and sys_platform != 'emscripten') or (sys_platform == 'darwin' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru') or (sys_platform == 'emscripten' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "numpy", marker = "(sys_platform != 'darwin' and sys_platform != 'emscripten') or (sys_platform == 'darwin' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru') or (sys_platform == 'emscripten' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "packaging", marker = "(sys_platform != 'darwin' and sys_platform != 'emscripten') or (sys_platform == 'darwin' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru') or (sys_platform == 'emscripten' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "protobuf", marker = "(sys_platform != 'darwin' and sys_platform != 'emscripten') or (sys_platform == 'darwin' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru') or (sys_platform == 'emscripten' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+]
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/31/ae/cfec0c21d039e4125fdc333e2e2032ed0a49eb50f9dd70b7f3819b339018/onnxruntime_gpu-1.30.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:9aba23f903f434cc55d851aeb801afee19e287c202f4ab8f59d02f04caa90aed", size = 246688669, upload-time = "2026-09-10T16:13:21.504Z" },
+    { url = "https://files.pythonhosted.org/packages/07/cd/99171c84362c9a3292ec909c2e8edd922dec21d65e28e83e9d809ad178c6/onnxruntime_gpu-1.30.0-cp313-cp313-manylinux_2_34_aarch64.whl", hash = "sha256:0c68878729527a28202af6c1b7ebc2fc5a687e9f6e02bfb8796e39d1fe775fd7", size = 205732148, upload-time = "2026-09-10T15:53:16.111Z" },
+    { url = "https://files.pythonhosted.org/packages/7e/d3/50fba71f4174f25f1e677ffe4b2ebc9f6c2a2aa8093c12e82c93792fd4e8/onnxruntime_gpu-1.30.0-cp313-cp313-win_amd64.whl", hash = "sha256:cf494da233f3fc02bbeb2a3178e3ace7361b6b4fef7031b19c1e5aed5e9328ce", size = 160479611, upload-time = "2026-09-10T15:56:28.799Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/41/3ebd7b9648259adcf3abd245be862a0cb4c24d4b12f4f7b82d3e9fcf18f0/onnxruntime_gpu-1.30.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:675d519cab613bc42685ecb998f8e8e8c6d73143496681650d30ef14fedeade7", size = 246684982, upload-time = "2026-09-10T16:13:31.799Z" },
+    { url = "https://files.pythonhosted.org/packages/f5/b0/6187754ea45ce90c116730115e4d856a6107b9e708580093c112def9a567/onnxruntime_gpu-1.30.0-cp313-cp313t-manylinux_2_34_aarch64.whl", hash = "sha256:c6df4b62538f98482dd5cebc91cba668c4b82156e872517c314a383c904a191d", size = 205776779, upload-time = "2026-09-10T15:53:24.926Z" },
+    { url = "https://files.pythonhosted.org/packages/bb/75/09a6c97136c747608867a63114d988384e6ddb5507e08bbe9ced08744a4c/onnxruntime_gpu-1.30.0-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:5aacc98f394a13f4891c0a07e60479d8fb0b1ea6f3328b6b38cfc88f9dfb05ea", size = 246693192, upload-time = "2026-09-10T16:13:41.775Z" },
+    { url = "https://files.pythonhosted.org/packages/73/93/415e8100a3d7d4754f406fadbe86fa91d03058a9a6d7fa8a692722e9ceb8/onnxruntime_gpu-1.30.0-cp314-cp314-manylinux_2_34_aarch64.whl", hash = "sha256:96cb15cff2f0dffaef3ae636560145d41be47bb73e3230113f2e946ca576014b", size = 205736852, upload-time = "2026-09-10T15:53:34.204Z" },
+    { url = "https://files.pythonhosted.org/packages/50/fe/ed63f743d546fd089f98cfd415790b231ae8d3dba2208df8d22811f788a5/onnxruntime_gpu-1.30.0-cp314-cp314-win_amd64.whl", hash = "sha256:794fc118cdbf340ed02b44c7527e557ea51746002d48105d493ea41f0c9a60d0", size = 161124661, upload-time = "2026-09-10T15:56:36.489Z" },
+    { url = "https://files.pythonhosted.org/packages/75/66/11c43d3d544380271aa14fd55c1e5be65f28fac007128e369f1192c9bfa9/onnxruntime_gpu-1.30.0-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:a4dfbe80d4167ff5bc269f266778ee6d0eb771fd9f3c0c4d83757e7ae42fe3c8", size = 246687044, upload-time = "2026-09-10T16:13:52.095Z" },
+    { url = "https://files.pythonhosted.org/packages/74/3d/33878b36bc473415ff7ed92ba751a5b5181d2779c74441c3584c68261dbc/onnxruntime_gpu-1.30.0-cp314-cp314t-manylinux_2_34_aarch64.whl", hash = "sha256:13d4cf97120882739da8572ba26e2a0f39caed4c69749a147d8f1a77f74a4690", size = 205750897, upload-time = "2026-09-10T15:53:43.295Z" },
+]
+
+[[package]]
+name = "open-clip-torch"
+version = "3.3.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "ftfy" },
+    { name = "huggingface-hub", version = "0.36.2", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-marker'" },
+    { name = "huggingface-hub", version = "1.33.0", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
+    { name = "regex", version = "2024.11.6", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-marker'" },
+    { name = "regex", version = "2026.9.29", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
+    { name = "safetensors" },
+    { name = "timm" },
+    { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 'arm64' and sys_platform == 'darwin') or (platform_machine != 'arm64' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru') or (sys_platform != 'darwin' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 'arm64' or sys_platform != 'darwin' or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "torchvision", version = "0.27.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 'arm64' and sys_platform == 'darwin') or (platform_machine != 'arm64' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru') or (sys_platform != 'darwin' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "torchvision", version = "0.27.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 'arm64' or sys_platform != 'darwin' or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "tqdm" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/4a/1f/2bc9795047fa2c1ad2567ef78ce6dfc9a7b763fa534acee09a94da2a5b8f/open_clip_torch-3.3.0.tar.gz", hash = "sha256:904b1a9f909df8281bb3de60ab95491cd2994a509177ea4f9d6292a84fe24d6d", size = 1503380, upload-time = "2026-02-27T00:32:46.74Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/37/b5/41c315ccd94ca332ead3e832e83eee343ab245005c3e43d9d3e75eae34eb/open_clip_torch-3.3.0-py3-none-any.whl", hash = "sha256:c549ad5ed6bfc119cc11105033c0a2b9d7a2a4afeb40a58a09aab3da1a0043ce", size = 1547268, upload-time = "2026-02-27T00:32:44.902Z" },
+]
+
 [[package]]
 name = "openai"
 version = "1.109.1"
@@ -2828,6 +2927,31 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/bc/b9/4437bb89f04e57f48c96492a50d6168da5e201940de6620730d390449991/pdftext-0.6.3-py3-none-any.whl", hash = "sha256:528431ed8bdce39d74372cd3d27e8544af812f1f1adc81db229cf9fb48dacacb", size = 23693, upload-time = "2025-06-11T14:42:08.157Z" },
 ]
 
+[[package]]
+name = "peft"
+version = "0.21.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "accelerate" },
+    { name = "huggingface-hub", version = "0.36.2", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-marker'" },
+    { name = "huggingface-hub", version = "1.33.0", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
+    { name = "numpy" },
+    { name = "packaging" },
+    { name = "psutil" },
+    { name = "pyyaml" },
+    { name = "safetensors" },
+    { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 'arm64' and sys_platform == 'darwin') or (platform_machine != 'arm64' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru') or (sys_platform != 'darwin' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 'arm64' or sys_platform != 'darwin' or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "tqdm" },
+    { name = "transformers", version = "4.57.6", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-marker'" },
+    { name = "transformers", version = "5.15.1", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "transformers", version = "5.18.0", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/80/af/2e08abf1cd3b8792a02f5116808f2398c2f77ecdff801ced2ce16007a6f9/peft-0.21.2.tar.gz", hash = "sha256:b803ccfb3f3f316004d850284306687833a2235ea278fb56abc856203456142e", size = 983614, upload-time = "2026-10-01T10:26:36.129Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/70/0b/59441cdbfdd342ed03c08af90a2fe16173f0cd48ab219f523b39ca059a79/peft-0.21.2-py3-none-any.whl", hash = "sha256:106ab6077ff72c54d21577f9af5970e34bac7582cb14209f7b2b511e322a4eae", size = 835427, upload-time = "2026-10-01T10:26:34.085Z" },
+]
+
 [[package]]
 name = "pexpect"
 version = "4.9.0"
@@ -3706,6 +3830,21 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/81/d6/4bfbb40c9a0b42fc53c7cf442f6385db70b40f74a783130c5d0a5aa62228/pyzmq-27.1.0-cp314-cp314t-win_arm64.whl", hash = "sha256:dc5dbf68a7857b59473f7df42650c621d7e8923fb03fa74a526890f4d33cc4d7", size = 575170, upload-time = "2025-09-08T23:09:01.418Z" },
 ]
 
+[[package]]
+name = "qwen-vl-utils"
+version = "0.0.14"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "av" },
+    { name = "packaging" },
+    { name = "pillow" },
+    { name = "requests" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b6/b1/ad4fc2260a3badd278b38d642f3b987412f1f6682f0ef2b31b0572d5caa8/qwen_vl_utils-0.0.14.tar.gz", hash = "sha256:9c7cad5ae803b3a10f8bb7194deb12aeacdd032f92f4224e880c73587a7346ad", size = 8453, upload-time = "2025-09-23T09:38:57.532Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c4/43/80f67e0336cb2fc725f8e06f7fe35c1d0fe946f4d2b8b2175e797e07349e/qwen_vl_utils-0.0.14-py3-none-any.whl", hash = "sha256:5e28657bfd031e56bd447c5901b58ddfc3835285ed100f4c56580e0ade054e96", size = 8120, upload-time = "2025-09-23T09:38:56.297Z" },
+]
+
 [[package]]
 name = "rapidfuzz"
 version = "3.14.5"
@@ -4592,6 +4731,25 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/81/59/208f71d70ddc6184f79b8c6d87d46eb7d7b12c19186a817dec9c9c3f3693/tifffile-2026.6.1-py3-none-any.whl", hash = "sha256:0d7382d2769b855b81ce358528e2b40c16d48aa39031746efa81215205332a8d", size = 267108, upload-time = "2026-05-31T23:57:10.597Z" },
 ]
 
+[[package]]
+name = "timm"
+version = "1.0.30"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "huggingface-hub", version = "0.36.2", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-marker'" },
+    { name = "huggingface-hub", version = "1.33.0", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
+    { name = "pyyaml" },
+    { name = "safetensors" },
+    { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 'arm64' and sys_platform == 'darwin') or (platform_machine != 'arm64' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru') or (sys_platform != 'darwin' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 'arm64' or sys_platform != 'darwin' or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "torchvision", version = "0.27.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 'arm64' and sys_platform == 'darwin') or (platform_machine != 'arm64' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru') or (sys_platform != 'darwin' and extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "torchvision", version = "0.27.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 'arm64' or sys_platform != 'darwin' or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/0e/ab/49041213990e48edcb6013463b18ef86d8d3c5d6ac5b408802c480443025/timm-1.0.30.tar.gz", hash = "sha256:1444a3af7e17fdba5440ac2bcf6e4b728da96dd62289ed9e1bcba31a545f5935", size = 2534738, upload-time = "2026-09-22T20:46:13.9Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f5/85/b897716d0fa016af23b11e6526f5ef76d2013e8bc36b9c7ce15d9200e456/timm-1.0.30-py3-none-any.whl", hash = "sha256:c8e27adf6801a2fdfb570dbbdd171f2f084756eefc673df8cfaab06bd14864f3", size = 2668917, upload-time = "2026-09-22T20:46:12.11Z" },
+]
+
 [[package]]
 name = "tinycss2"
 version = "1.5.1"
@@ -4608,9 +4766,23 @@ wheels = [
 name = "tokenizers"
 version = "0.22.2"
 source = { registry = "https://pypi.org/simple" }
+resolution-markers = [
+    "python_full_version >= '3.14' and sys_platform == 'win32'",
+    "python_full_version >= '3.14' and sys_platform == 'emscripten'",
+    "python_full_version >= '3.14' and platform_machine != 'arm64' and sys_platform == 'darwin'",
+    "python_full_version >= '3.14' and platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "(python_full_version >= '3.14' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.14' and sys_platform != 'darwin' and sys_platform != 'emscripten' and sys_platform != 'linux' and sys_platform != 'win32')",
+    "python_full_version < '3.14' and sys_platform == 'win32'",
+    "python_full_version < '3.14' and sys_platform == 'emscripten'",
+    "python_full_version < '3.14' and platform_machine != 'arm64' and sys_platform == 'darwin'",
+    "python_full_version < '3.14' and platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "(python_full_version < '3.14' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.14' and sys_platform != 'darwin' and sys_platform != 'emscripten' and sys_platform != 'linux' and sys_platform != 'win32')",
+    "python_full_version >= '3.14' and platform_machine == 'arm64' and sys_platform == 'darwin'",
+    "python_full_version < '3.14' and platform_machine == 'arm64' and sys_platform == 'darwin'",
+]
 dependencies = [
     { name = "huggingface-hub", version = "0.36.2", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-marker'" },
-    { name = "huggingface-hub", version = "1.33.0", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
+    { name = "huggingface-hub", version = "1.33.0", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/73/6f/f80cfef4a312e1fb34baf7d85c72d4411afde10978d4657f8cdd811d3ccc/tokenizers-0.22.2.tar.gz", hash = "sha256:473b83b915e547aa366d1eee11806deaf419e17be16310ac0a14077f1e28f917", size = 372115, upload-time = "2026-01-05T10:45:15.988Z" }
 wheels = [
@@ -4631,6 +4803,39 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/72/f4/0de46cfa12cdcbcd464cc59fde36912af405696f687e53a091fb432f694c/tokenizers-0.22.2-cp39-abi3-win_arm64.whl", hash = "sha256:9ce725d22864a1e965217204946f830c37876eee3b2ba6fc6255e8e903d5fcbc", size = 2612133, upload-time = "2026-01-05T10:45:17.232Z" },
 ]
 
+[[package]]
+name = "tokenizers"
+version = "0.23.2"
+source = { registry = "https://pypi.org/simple" }
+resolution-markers = [
+    "python_full_version >= '3.14' and platform_machine != 'arm64' and sys_platform == 'darwin'",
+    "python_full_version < '3.14' and platform_machine != 'arm64' and sys_platform == 'darwin'",
+    "python_full_version >= '3.14' and platform_machine == 'arm64' and sys_platform == 'darwin'",
+    "python_full_version < '3.14' and platform_machine == 'arm64' and sys_platform == 'darwin'",
+]
+dependencies = [
+    { name = "huggingface-hub", version = "1.33.0", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/18/1e/bc6587c5ab643b2e17776cace9070a2ae73549c86bffac9934a600bf3c31/tokenizers-0.23.2.tar.gz", hash = "sha256:7f0f085686b9de0d0079e6f874ae053600db64c5d13049e0bbc0119926d25aac", size = 385745, upload-time = "2026-09-03T08:55:42.89Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/4d/ed/8a443528baa6fac8dfe8c3b75b038c63ac92bb539bcabe311e227c718173/tokenizers-0.23.2-cp310-abi3-macosx_10_12_x86_64.whl", hash = "sha256:85a9a357a3764aecc904ee76bdaf8cf1ad8e5a67a1b929a487c4a39b49ed0e90", size = 3148852, upload-time = "2026-09-03T08:55:30.874Z" },
+    { url = "https://files.pythonhosted.org/packages/67/49/22da045a91732384d3a3771816bf188dc5a1f702c32e635afa7c679c0bef/tokenizers-0.23.2-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:986670e43691469dcee610ea0f846f91a8f84e91fc6f7a48d4c064414c0ec2bf", size = 3101593, upload-time = "2026-09-03T08:55:28.587Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/4d/8f569ed49372a3ed8e57099bd515055fd48d7c95912c4307cda6973c2168/tokenizers-0.23.2-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a37039b5dfc4af84eb3ef0a92f4307e28936c8f9adccba2629d36f652e9bf7a2", size = 3516830, upload-time = "2026-09-03T08:55:14.741Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/de/e2f14c8919d5bf51874051d00d6c7b7e0e8bde6c6a2dbeddda7f642896ff/tokenizers-0.23.2-cp310-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7b7e37ba198f24150f523e1242e83c4970de4a525480586be5dcc24d9add32c5", size = 3407975, upload-time = "2026-09-03T08:55:16.842Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/bd/93c69152d02ef06ce47aed8b2bf4952dcf733c935a62791873932b2934d9/tokenizers-0.23.2-cp310-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:43e4f2071e3cc8d5d86421c874aebc82659bb51a68bcdef5a0da75ee89511ccb", size = 3748165, upload-time = "2026-09-03T08:55:24.769Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/b7/56b84b80bc96942bba8eb23751a9e8a1fce4faaf4390425e7083f721c98c/tokenizers-0.23.2-cp310-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:325fee2e0418a9dc6c9ecf736a5f5f0db7875183ace9549ae339da76f7a1fbb7", size = 4024165, upload-time = "2026-09-03T08:55:18.806Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/8a/0175e216f005c2fe08238292663aa41e4c802b216e71047a69a0e9fc6fa3/tokenizers-0.23.2-cp310-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:950d7c9426fa72406a0ffeacdbc0bb9985f5db20eb8b263f29c79aaf83105703", size = 3591899, upload-time = "2026-09-03T08:55:22.752Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/ca/ca6b93c7820df123b2662a9469e8facc826ccc94e98fdd0d615f6431e73a/tokenizers-0.23.2-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:41c2f84d172449b4dadb9cdc508e3e364076613c35b16e76ecfe47a60d1e3305", size = 3386843, upload-time = "2026-09-03T08:55:26.584Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/a4/4f9106d317b14a80aefea9f0e3a8d07ef25f856a7607eb7f5ab894281fcb/tokenizers-0.23.2-cp310-abi3-manylinux_2_31_riscv64.whl", hash = "sha256:12f0835dc2ee694746a76adf7b1567d4346a4a502ebe93fb1f5f80ea49799b78", size = 3577314, upload-time = "2026-09-03T08:55:20.825Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/6a/1552b70fb0d9ab074fd3fc961435d01364e79c9058481822c3af6e8d402c/tokenizers-0.23.2-cp310-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:eb2f9c8a24da020ea8c11a01a19c1c2547912d92121ae4a01cfbca46125dee40", size = 9967367, upload-time = "2026-09-03T08:55:33.188Z" },
+    { url = "https://files.pythonhosted.org/packages/06/01/3ccb3a956c7528b2507b8a9714155c4baf86af593039db6ea375dd0c96c3/tokenizers-0.23.2-cp310-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:f486f402f6f9abee5bb032553736813af0c710a86b2e0ca592634c55cea1f835", size = 9811886, upload-time = "2026-09-03T08:55:35.642Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/73/7038e612d48bda1599457f712f6bd3854eae1a9dc9c13aa47f835349db48/tokenizers-0.23.2-cp310-abi3-musllinux_1_2_i686.whl", hash = "sha256:bef235815a067b2648caf6dcc7a71091b0b0fff9ee8057f6451eb9335fae52ef", size = 10146224, upload-time = "2026-09-03T08:55:38.391Z" },
+    { url = "https://files.pythonhosted.org/packages/b5/d8/8e9e4e0b287a338d8f88976729628c9d22e8a54cfaf9777018a7f7cb58a0/tokenizers-0.23.2-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:5c56bda1511921587789163e524d196ed8284174ac23abd7685d5ea8da6c4718", size = 10256304, upload-time = "2026-09-03T08:55:40.977Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/1f/c79a01f671a49728ebb0b61f7ff9ea45663b66cab40bc0858e9859b25c16/tokenizers-0.23.2-cp310-abi3-win32.whl", hash = "sha256:debf978920d93ba9c219bd67cc4bbfaf912c9039e41e7a28b91ec15e3728c95a", size = 2592809, upload-time = "2026-09-03T08:55:48.02Z" },
+    { url = "https://files.pythonhosted.org/packages/db/f7/0a69ac6b82dbccf3f71add938a161c497952749294b8dd6dfe03a819dc40/tokenizers-0.23.2-cp310-abi3-win_amd64.whl", hash = "sha256:2e96f5699d5249c9c64aa8412e044f727aae3a4098cf830f9901ec1afc361cde", size = 2863236, upload-time = "2026-09-03T08:55:46.193Z" },
+    { url = "https://files.pythonhosted.org/packages/d7/b0/dee84cb44175be1b4c35bd2f770727494e78f0bb38e571a623ade94dbebb/tokenizers-0.23.2-cp310-abi3-win_arm64.whl", hash = "sha256:e49c394456dd9985787fec76132438ba3fb8911f857b1bf3d40119f9292d41aa", size = 2729352, upload-time = "2026-09-03T08:55:44.345Z" },
+]
+
 [[package]]
 name = "tomlkit"
 version = "0.14.0"
@@ -4830,7 +5035,7 @@ dependencies = [
     { name = "regex", version = "2024.11.6", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-marker'" },
     { name = "requests", marker = "extra == 'extra-14-extract-python-marker'" },
     { name = "safetensors", marker = "extra == 'extra-14-extract-python-marker'" },
-    { name = "tokenizers", marker = "extra == 'extra-14-extract-python-marker'" },
+    { name = "tokenizers", version = "0.22.2", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-marker'" },
     { name = "tqdm", marker = "extra == 'extra-14-extract-python-marker'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/c4/35/67252acc1b929dc88b6602e8c4a982e64f31e733b804c14bc24b47da35e6/transformers-4.57.6.tar.gz", hash = "sha256:55e44126ece9dc0a291521b7e5492b572e6ef2766338a610b9ab5afbb70689d3", size = 10134912, upload-time = "2026-01-16T10:38:39.284Z" }
@@ -4845,33 +5050,55 @@ source = { registry = "https://pypi.org/simple" }
 resolution-markers = [
     "python_full_version >= '3.14' and sys_platform == 'win32'",
     "python_full_version >= '3.14' and sys_platform == 'emscripten'",
-    "python_full_version >= '3.14' and platform_machine != 'arm64' and sys_platform == 'darwin'",
     "python_full_version >= '3.14' and platform_machine == 'aarch64' and sys_platform == 'linux'",
     "(python_full_version >= '3.14' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.14' and sys_platform != 'darwin' and sys_platform != 'emscripten' and sys_platform != 'linux' and sys_platform != 'win32')",
     "python_full_version < '3.14' and sys_platform == 'win32'",
     "python_full_version < '3.14' and sys_platform == 'emscripten'",
-    "python_full_version < '3.14' and platform_machine != 'arm64' and sys_platform == 'darwin'",
     "python_full_version < '3.14' and platform_machine == 'aarch64' and sys_platform == 'linux'",
     "(python_full_version < '3.14' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.14' and sys_platform != 'darwin' and sys_platform != 'emscripten' and sys_platform != 'linux' and sys_platform != 'win32')",
-    "python_full_version >= '3.14' and platform_machine == 'arm64' and sys_platform == 'darwin'",
-    "python_full_version < '3.14' and platform_machine == 'arm64' and sys_platform == 'darwin'",
 ]
 dependencies = [
-    { name = "huggingface-hub", version = "1.33.0", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
-    { name = "numpy", marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
-    { name = "packaging", marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
-    { name = "pyyaml", marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
-    { name = "regex", version = "2026.9.29", source = { registry = "https://pypi.org/simple" }, marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
-    { name = "safetensors", marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
-    { name = "tokenizers", marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
-    { name = "tqdm", marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
-    { name = "typer", marker = "extra == 'extra-14-extract-python-mineru' or extra != 'extra-14-extract-python-marker'" },
+    { name = "huggingface-hub", version = "1.33.0", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "numpy", marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "packaging", marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "pyyaml", marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "regex", version = "2026.9.29", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "safetensors", marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "tokenizers", version = "0.22.2", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "tqdm", marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "typer", marker = "(sys_platform != 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/2a/92/c50c61da7046bbb59a4d011291aeadcfb4d7980ab36fdb31e93823a3fb93/transformers-5.15.1.tar.gz", hash = "sha256:27c996bd9075ddc82d40f8590dfdc81ea45f611bfca477e0db5d7fd257a482f7", size = 9378434, upload-time = "2026-08-19T11:28:20.33Z" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/41/c4/a12e1d9b387fb0c40a57116db82b457e8c771cb419163cda29204d74a595/transformers-5.15.1-py3-none-any.whl", hash = "sha256:b7cdf238ff583e3a58dbc7fa34da1aaf091ce063141f65a30538160bd5afe93f", size = 11749582, upload-time = "2026-08-19T11:28:16.726Z" },
 ]
 
+[[package]]
+name = "transformers"
+version = "5.18.0"
+source = { registry = "https://pypi.org/simple" }
+resolution-markers = [
+    "python_full_version >= '3.14' and platform_machine != 'arm64' and sys_platform == 'darwin'",
+    "python_full_version < '3.14' and platform_machine != 'arm64' and sys_platform == 'darwin'",
+    "python_full_version >= '3.14' and platform_machine == 'arm64' and sys_platform == 'darwin'",
+    "python_full_version < '3.14' and platform_machine == 'arm64' and sys_platform == 'darwin'",
+]
+dependencies = [
+    { name = "huggingface-hub", version = "1.33.0", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "numpy", marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "packaging", marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "pyyaml", marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "regex", version = "2026.9.29", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "safetensors", marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "tokenizers", version = "0.23.2", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "tqdm", marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+    { name = "typer", marker = "(sys_platform == 'darwin' and extra != 'extra-14-extract-python-marker') or (extra == 'extra-14-extract-python-marker' and extra == 'extra-14-extract-python-mineru')" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/9e/6e/5a50ca8aff5fdd4ff21271198d2fb9e1f11bcd0ea279576199c0caa34cba/transformers-5.18.0.tar.gz", hash = "sha256:d89c206e42e841af7cd314b3d2b21c03e977d819cdb4aef65ada048769a644df", size = 10028745, upload-time = "2026-09-30T16:46:00.575Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2d/3b/f84d7d12886147c5267216ed6c57d1163e68d24a89b2ad29d835a7089463/transformers-5.18.0-py3-none-any.whl", hash = "sha256:d79e5a515a572ee3deb33eb0d578be47d91e70c75d54cf21bf6eede6edef14a9", size = 12579646, upload-time = "2026-09-30T16:45:57.51Z" },
+]
+
 [[package]]
 name = "tree-sitter"
 version = "0.25.2"