deepdoc-lib/pyproject.toml at master · xorbitsai/deepdoc-lib · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
[build-system]
requires = ["setuptools >= 77.0.3", "setuptools-scm", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "deepdoc_lib"
dynamic = ["version"]
description = "[RAGFlow](https://ragflow.io/) is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models) to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted data."
authors = [{ name = "Zhichang Yu", email = "yuzhichang@gmail.com" }]
license-files = ["LICENSE"]
readme = "README.md"
requires-python = ">=3.10,<3.14"
dependencies = [
    "datrie>=0.8.2",
    "anthropic>=0.69.0",
    "beartype>=0.18.5,<0.19.0",
    "beautifulsoup4>=4.12.0",
    "chardet>=5.2.0",
    "demjson3>=3.0.6",
    "hanziconv>=0.3.2",
    "html5lib>=1.1",
    "jinja2>=3.1.0",
    "modelscope>=1.20.0,<2.0.0",
    "markdown>=3.6",
    "nltk>=3.9.1",
    "numpy>=1.26.0,<2.0.0",
    "ollama>=0.6.1",
    "onnxruntime>=1.19.2",
    "openai>=1.45.0",
    "opencv-python>=4.10.0.84",
    "opencv-python-headless>=4.10.0.84",
    "openpyxl>=3.1.0,<4.0.0",
    "pandas>=2.2.0,<3.0.0",
    "pdfplumber>=0.10.4",
    "pillow>=11.0.0",
    "pyclipper>=1.3.0.post5",
    "pypdf>=6.0.0",
    "python-pptx>=1.0.2,<2.0.0",
    "python-docx>=1.1.2,<2.0.0",
    "pyyaml>=6.0.0",
    "requests>=2.32.2",
    "scikit-learn>=1.5.0",
    "shapely>=2.0.5",
    "six>=1.16.0",
    "strenum>=0.4.15",
    "tencentcloud-sdk-python>=3.0.1215",
    "tiktoken>=0.7.0",
    "xgboost>=1.6.0,<2.0.0",
    "xpinyin>=0.7.6",
    "zhipuai>=2.0.1",
    "google-generativeai>=0.8.1,<0.9.0",
    "trio>=0.29.0",
    "setuptools>=75.2.0,<76.0.0",
    "huggingface-hub>=0.25.0,<0.26.0",
]

[project.optional-dependencies]
gpu = [
    "onnxruntime-gpu>=1.19.2; sys_platform != 'darwin' and platform_machine == 'x86_64'",
    "torch",
]

[project.scripts]
deepdoc-download-models = "deepdoc.download_models:main"

[dependency-groups]
test = [
    "openpyxl>=3.1.5",
    "pillow>=10.4.0",
    "pytest>=8.3.5",
    "python-docx>=1.1.2",
    "python-pptx>=1.0.2",
    "requests>=2.32.2",
]

[tool.setuptools]
packages = {find = {}}
include-package-data = true

[tool.setuptools.package-data]
deepdoc = ["dict/huqie.txt"]

[tool.ruff]
line-length = 200
exclude = [".venv", "rag/svr/discord_svr.py"]

[tool.ruff.lint]
extend-select = ["ASYNC", "ASYNC1"]
ignore = ["E402"]

[tool.pytest.ini_options]
addopts = [
    "--ignore=tests/test_data",
    "--ignore=tests/test_results",
]
testpaths = ["tests"]
markers = [
    "p1: high priority test cases",
    "p2: medium priority test cases",
    "p3: low priority test cases",
]

[tool.setuptools_scm]
write_to = "deepdoc/_version.py"
fallback_version = "0.1.0"