universal-doc-parser / pyproject.toml
GitHub Actions
deploy: live Hugging Face Space application
53d9817
Raw History Blame Contribute Delete
1.91 kB
[project]
name = "universal-doc-parser"
version = "1.0.3"
description = "A zero-GPU, CPU-only document ingestion engine for RAG pipelines and AI agents."
readme = "README.md"
requires-python = ">=3.11"
license = { text = "MIT" }
dependencies = [
"pydantic>=2.0",
"pypdfium2>=5.13.0",
"pdfplumber>=0.11",
"python-docx>=1.1",
"openpyxl>=3.1",
"python-magic-bin>=0.4.14; sys_platform == 'win32'",
"python-magic>=0.4.27; sys_platform != 'win32'",
"numpy>=1.24.0",
"pyarrow>=14.0.0",
"selectolax>=0.4.11",
"beautifulsoup4>=4.12.0",
"ebooklib>=0.18",
"rapidocr-onnxruntime>=1.3.0",
"opencv-python-headless>=4.8.0",
"pillow>=10.1.0",
"extract-msg>=0.48.0",
"python-pptx>=1.0.0",
"xlrd>=2.0.1",
"olefile>=0.46",
"xlwt>=1.3.0",
"mcp>=1.0.0,<2.0",
"reportlab>=5.0.1",
]
[project.urls]
Homepage = "https://github.com/Edge-Explorer/Parse-Anything-"
"Live Demo" = "https://huggingface.co/spaces/Karan6124/universal-doc-parser"
Repository = "https://github.com/Edge-Explorer/Parse-Anything-"
Documentation = "https://github.com/Edge-Explorer/Parse-Anything-#readme"
Issues = "https://github.com/Edge-Explorer/Parse-Anything-/issues"
[project.optional-dependencies]
demo = [
"gradio>=4.0.0",
"plotly>=5.0.0",
]
dev = [
"pytest>=8.0",
"pytest-cov",
"hypothesis",
"ruff>=0.4.0",
"psutil>=5.9.0",
]
ocr = [
"rapidocr-onnxruntime>=1.3.0",
"opencv-python-headless>=4.8.0",
]
enrichment = [
"onnxruntime>=1.16.0",
]
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
packages = ["universal_parser"]
[tool.pytest.ini_options]
filterwarnings = [
"ignore::UserWarning:openpyxl.",
"ignore::DeprecationWarning",
]
[tool.ruff]
line-length = 100
target-version = "py311"
[tool.ruff.lint]
select = ["E", "F", "I", "W", "UP"]
ignore = ["E501"]