feat: add claude backend, refactor summary utilities, improve batch worker pattern, add pymupdf4llm
This commit is contained in:
@@ -684,6 +684,19 @@ wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/04/4b/29cac41a4d98d144bf5f6d33995617b185d14b22401f75ca86f384e87ff1/h11-0.16.0-py3-none-any.whl", hash = "sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86", size = 37515, upload-time = "2025-04-24T03:35:24.344Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "h2"
|
||||
version = "4.3.0"
|
||||
source = { registry = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple/" }
|
||||
dependencies = [
|
||||
{ name = "hpack" },
|
||||
{ name = "hyperframe" },
|
||||
]
|
||||
sdist = { url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/1d/17/afa56379f94ad0fe8defd37d6eb3f89a25404ffc71d4d848893d270325fc/h2-4.3.0.tar.gz", hash = "sha256:6c59efe4323fa18b47a632221a1888bd7fde6249819beda254aeca909f221bf1", size = 2152026, upload-time = "2025-08-23T18:12:19.778Z" }
|
||||
wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/69/b2/119f6e6dcbd96f9069ce9a2665e0146588dc9f88f29549711853645e736a/h2-4.3.0-py3-none-any.whl", hash = "sha256:c438f029a25f7945c69e0ccf0fb951dc3f73a5f6412981daee861431b70e2bdd", size = 61779, upload-time = "2025-08-23T18:12:17.779Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "hf-daily-papers"
|
||||
version = "0.1.0"
|
||||
@@ -693,12 +706,13 @@ dependencies = [
|
||||
{ name = "bleach" },
|
||||
{ name = "chromadb" },
|
||||
{ name = "fastapi" },
|
||||
{ name = "httpx" },
|
||||
{ name = "httpx", extra = ["http2"] },
|
||||
{ name = "itsdangerous" },
|
||||
{ name = "jinja2" },
|
||||
{ name = "pydantic" },
|
||||
{ name = "pydantic-settings" },
|
||||
{ name = "pymupdf" },
|
||||
{ name = "pymupdf4llm" },
|
||||
{ name = "python-dotenv" },
|
||||
{ name = "python-multipart" },
|
||||
{ name = "sqlalchemy" },
|
||||
@@ -724,12 +738,13 @@ requires-dist = [
|
||||
{ name = "bleach", specifier = ">=6.4.0" },
|
||||
{ name = "chromadb", specifier = ">=1.0" },
|
||||
{ name = "fastapi", specifier = ">=0.115" },
|
||||
{ name = "httpx", specifier = ">=0.28" },
|
||||
{ name = "httpx", extras = ["http2"], specifier = ">=0.28" },
|
||||
{ name = "itsdangerous", specifier = ">=2.2.0" },
|
||||
{ name = "jinja2", specifier = ">=3.1" },
|
||||
{ name = "pydantic", specifier = ">=2.0" },
|
||||
{ name = "pydantic-settings", specifier = ">=2.0" },
|
||||
{ name = "pymupdf", specifier = ">=1.25" },
|
||||
{ name = "pymupdf4llm", specifier = ">=1.27.2.3" },
|
||||
{ name = "pytest", marker = "extra == 'dev'", specifier = ">=8.0" },
|
||||
{ name = "pytest-asyncio", marker = "extra == 'dev'", specifier = ">=0.24" },
|
||||
{ name = "python-dotenv", specifier = ">=1.0" },
|
||||
@@ -778,6 +793,15 @@ wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/62/94/3b66b148778ee100dcfd69c2ca22b57b41b44d3063ceec934f209e9184ce/hf_xet-1.5.0-cp37-abi3-win_arm64.whl", hash = "sha256:b6c9df403040248c76d808d3e047d64db2d923bae593eb244c41e425cf6cd7be", size = 3806916, upload-time = "2026-05-06T06:18:21.7Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "hpack"
|
||||
version = "4.1.0"
|
||||
source = { registry = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple/" }
|
||||
sdist = { url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/2c/48/71de9ed269fdae9c8057e5a4c0aa7402e8bb16f2c6e90b3aa53327b113f8/hpack-4.1.0.tar.gz", hash = "sha256:ec5eca154f7056aa06f196a557655c5b009b382873ac8d1e66e79e87535f1dca", size = 51276, upload-time = "2025-01-22T21:44:58.347Z" }
|
||||
wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/07/c6/80c95b1b2b94682a72cbdbfb85b81ae2daffa4291fbfa1b1464502ede10d/hpack-4.1.0-py3-none-any.whl", hash = "sha256:157ac792668d995c657d93111f46b4535ed114f0c9c8d672271bbec7eae1b496", size = 34357, upload-time = "2025-01-22T21:44:56.92Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "httpcore"
|
||||
version = "1.0.9"
|
||||
@@ -842,6 +866,11 @@ wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad", size = 73517, upload-time = "2024-12-06T15:37:21.509Z" },
|
||||
]
|
||||
|
||||
[package.optional-dependencies]
|
||||
http2 = [
|
||||
{ name = "h2" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "huggingface-hub"
|
||||
version = "1.16.1"
|
||||
@@ -862,6 +891,15 @@ wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/49/79/621a7dbb80c70974f73a597275351ebe03ce5bc65cb5f8f4acb5859252bc/huggingface_hub-1.16.1-py3-none-any.whl", hash = "sha256:64340de934b9ce37857ef85a82de72f5629e8a270f9119eabb12bf495eb53c22", size = 668176, upload-time = "2026-05-21T18:39:58.596Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "hyperframe"
|
||||
version = "6.1.0"
|
||||
source = { registry = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple/" }
|
||||
sdist = { url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/02/e7/94f8232d4a74cc99514c13a9f995811485a6903d48e5d952771ef6322e30/hyperframe-6.1.0.tar.gz", hash = "sha256:f630908a00854a7adeabd6382b43923a4c4cd4b821fcb527e6ab9e15382a3b08", size = 26566, upload-time = "2025-01-22T21:41:49.302Z" }
|
||||
wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/48/30/47d0bf6072f7252e6521f3447ccfa40b421b6824517f82854703d0f5a98b/hyperframe-6.1.0-py3-none-any.whl", hash = "sha256:b03380493a519fce58ea5af42e4a42317bf9bd425596f7a0835ffce80f1a42e5", size = 13007, upload-time = "2025-01-22T21:41:47.295Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "idna"
|
||||
version = "3.18"
|
||||
@@ -1223,6 +1261,15 @@ wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/81/08/7036c080d7117f28a4af526d794aab6a84463126db031b007717c1a6676e/multidict-6.7.1-py3-none-any.whl", hash = "sha256:55d97cc6dae627efa6a6e548885712d4864b81110ac76fa4e534c03819fa4a56", size = 12319, upload-time = "2026-01-26T02:46:44.004Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "networkx"
|
||||
version = "3.6.1"
|
||||
source = { registry = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple/" }
|
||||
sdist = { url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/6a/51/63fe664f3908c97be9d2e4f1158eb633317598cfa6e1fc14af5383f17512/networkx-3.6.1.tar.gz", hash = "sha256:26b7c357accc0c8cde558ad486283728b65b6a95d85ee1cd66bafab4c8168509", size = 2517025, upload-time = "2025-12-08T17:02:39.908Z" }
|
||||
wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/9e/c9/b2622292ea83fbb4ec318f5b9ab867d0a28ab43c5717bb85b0a5f6b3b0a4/networkx-3.6.1-py3-none-any.whl", hash = "sha256:d47fbf302e7d9cbbb9e2555a0d267983d2aa476bac30e90dfbe5669bd57f3762", size = 2068504, upload-time = "2025-12-08T17:02:38.159Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "numpy"
|
||||
version = "2.4.6"
|
||||
@@ -1842,6 +1889,39 @@ wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/53/a4/b9e91aac82293f9c954654c85581ee8212b5b05efadc534b581141241e6f/pymupdf-1.27.2.3-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:77691604c5d1d0233827139bbcdea61fd57879c84712b8e49b1f45520f7ab9c2", size = 25000393, upload-time = "2026-04-24T14:11:01.669Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pymupdf-layout"
|
||||
version = "1.27.2.3"
|
||||
source = { registry = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple/" }
|
||||
dependencies = [
|
||||
{ name = "networkx" },
|
||||
{ name = "numpy" },
|
||||
{ name = "onnxruntime" },
|
||||
{ name = "pymupdf" },
|
||||
{ name = "pyyaml" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/bc/ee/067726c3ee5574ad5c605d00d7419e264ef509d626a726f99388111f8216/pymupdf_layout-1.27.2.3-cp310-abi3-macosx_10_9_x86_64.whl", hash = "sha256:75c2ab3c0e8830ac2bc50cfd32d375a30768a2610dac72a02f08265336e0834f", size = 15799844, upload-time = "2026-04-24T14:11:13.177Z" },
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/0a/ba/46a7a36474722f9280d885f6eec878561a257d9378e52590b43d32ffb96c/pymupdf_layout-1.27.2.3-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:5656b09669dcd7c51f539afb6fdaf853602bab4cbc20479ee5ee1a85a4e32b60", size = 15795220, upload-time = "2026-04-24T14:11:23.17Z" },
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/84/87/bfdcca67346052943a4549814f2009b38f4d15ec025798cdf7dfa5f57c84/pymupdf_layout-1.27.2.3-cp310-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:fcf03aa815cbceebdb3263dd6a190de4547c46b1d168928836ec38738afe127d", size = 15805240, upload-time = "2026-04-24T14:11:33.465Z" },
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/32/e9/7ce6eaf97cebd46c3808593282e9eb99a60cddd6183e25a636980d5c7986/pymupdf_layout-1.27.2.3-cp310-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:303b9414216dfaf711ec7d807b6f1e4c3e0a92bbb4569340fcedd9d5593d16ca", size = 15806269, upload-time = "2026-04-24T14:11:43.481Z" },
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/bf/61/3b2417d8f2cdfaa0f4749cd9dafa3379cb5cdaddf4233165f1ff81953c30/pymupdf_layout-1.27.2.3-cp310-abi3-win_amd64.whl", hash = "sha256:503b64d9b6b31ea3af79ef85cf7d36950c5048af468cb297684d2953553c62ad", size = 15809163, upload-time = "2026-04-24T14:11:53.956Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pymupdf4llm"
|
||||
version = "1.27.2.3"
|
||||
source = { registry = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple/" }
|
||||
dependencies = [
|
||||
{ name = "pymupdf" },
|
||||
{ name = "pymupdf-layout" },
|
||||
{ name = "tabulate" },
|
||||
]
|
||||
sdist = { url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/87/c0/e3830452d82032c3d82a9879616c05bf0c51e0dea03c1d80d57b3a6ec0d1/pymupdf4llm-1.27.2.3.tar.gz", hash = "sha256:42ec1a47ddc62be3f4f40c116d27618611c6f9fa366719016d9ddc3f3a3dc22b", size = 1406297, upload-time = "2026-04-24T14:13:18.843Z" }
|
||||
wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/e6/38/84bf29f4dd72e6c450546df6ca8f53021f764fd945ba67dcc235d39bc20e/pymupdf4llm-1.27.2.3-py3-none-any.whl", hash = "sha256:bd724b79fa3f06a5b28d7a65f7acfa8de56e04bdb603ac2d6dff315e0d151aaa", size = 77348, upload-time = "2026-04-24T14:11:04.305Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pypika"
|
||||
version = "0.51.1"
|
||||
@@ -2202,6 +2282,15 @@ wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/1c/54/196d0c1db10af76baa4f64894448505d60d3cdf70ef92cbb35f46a4e4c71/starlette-1.2.1-py3-none-any.whl", hash = "sha256:4de0082d08c8f6764a85a54cf1120d6939507a19905c7768acad2a9f875d2b89", size = 73350, upload-time = "2026-05-31T01:07:50.09Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tabulate"
|
||||
version = "0.10.0"
|
||||
source = { registry = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple/" }
|
||||
sdist = { url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/46/58/8c37dea7bbf769b20d58e7ace7e5edfe65b849442b00ffcdd56be88697c6/tabulate-0.10.0.tar.gz", hash = "sha256:e2cfde8f79420f6deeffdeda9aaec3b6bc5abce947655d17ac662b126e48a60d", size = 91754, upload-time = "2026-03-04T18:55:34.402Z" }
|
||||
wheels = [
|
||||
{ url = "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/99/55/db07de81b5c630da5cbf5c7df646580ca26dfaefa593667fc6f2fe016d2e/tabulate-0.10.0-py3-none-any.whl", hash = "sha256:f0b0622e567335c8fabaaa659f1b33bcb6ddfe2e496071b743aa113f8774f2d3", size = 39814, upload-time = "2026-03-04T18:55:31.284Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tenacity"
|
||||
version = "9.1.4"
|
||||
|
||||
Reference in New Issue
Block a user