docling/pyproject.toml

[project]
name = "docling"
version = "2.38.1"  # DO NOT EDIT, updated automatically
description = "SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."
license = "MIT"
keywords = [
  "docling",
  "convert",
  "document",
  "pdf",
  "docx",
  "html",
  "markdown",
  "layout model",
  "segmentation",
  "table structure",
  "table former",
]
classifiers = [
  "Operating System :: MacOS :: MacOS X",
  "Operating System :: POSIX :: Linux",
  "Operating System :: Microsoft :: Windows",
  "Development Status :: 5 - Production/Stable",
  "Intended Audience :: Developers",
  "Intended Audience :: Science/Research",
  "Topic :: Scientific/Engineering :: Artificial Intelligence",
  "Programming Language :: Python :: 3",
  "Programming Language :: Python :: 3.9",
  "Programming Language :: Python :: 3.10",
  "Programming Language :: Python :: 3.11",
  "Programming Language :: Python :: 3.12",
  "Programming Language :: Python :: 3.13",
]
readme = "README.md"
authors = [
  { name = "Christoph Auer", email = "cau@zurich.ibm.com" },
  { name = "Michele Dolfi", email = "dol@zurich.ibm.com" },
  { name = "Maxim Lysak", email = "mly@zurich.ibm.com" },
  { name = "Nikos Livathinos", email = "nli@zurich.ibm.com" },
  { name = "Ahmed Nassar", email = "ahn@zurich.ibm.com" },
  { name = "Panos Vagenas", email = "pva@zurich.ibm.com" },
  { name = "Peter Staar", email = "taa@zurich.ibm.com" },
]
requires-python = '>=3.9,<4.0'
dependencies = [
  'pydantic (>=2.0.0,<3.0.0)',
  'docling-core[chunking] (>=2.29.0,<3.0.0)',
  'docling-ibm-models (>=3.4.4,<4.0.0)',
  'docling-parse (>=4.0.0,<5.0.0)',
  'filetype (>=1.2.0,<2.0.0)',
  'pypdfium2 (>=4.30.0,<5.0.0)',
  'pydantic-settings (>=2.3.0,<3.0.0)',
  'huggingface_hub (>=0.23,<1)',
  'requests (>=2.32.2,<3.0.0)',
  'easyocr (>=1.7,<2.0)',
  'certifi (>=2024.7.4)',
  'rtree (>=1.3.0,<2.0.0)',
  'typer (>=0.12.5,<0.17.0)',
  'python-docx (>=1.1.2,<2.0.0)',
  'python-pptx (>=1.0.2,<2.0.0)',
  'beautifulsoup4 (>=4.12.3,<5.0.0)',
  'pandas (>=2.1.4,<3.0.0)',
  'marko (>=2.1.2,<3.0.0)',
  'openpyxl (>=3.1.5,<4.0.0)',
  'lxml (>=4.0.0,<6.0.0)',
  'pillow (>=10.0.0,<12.0.0)',
  'tqdm (>=4.65.0,<5.0.0)',
  'pluggy (>=1.0.0,<2.0.0)',
  'pylatexenc (>=2.10,<3.0)',
  'scipy (>=1.6.0,<2.0.0)',
  # 'scipy (>=1.6.0,<2.0.0) ; python_version >= "3.10"',
  # 'scipy (>=1.6.0,<1.14.0) ; python_version < "3.10"',
]

[project.urls]
homepage = "https://github.com/docling-project/docling"
repository = "https://github.com/docling-project/docling"
issues = "https://github.com/docling-project/docling/issues"
changelog = "https://github.com/docling-project/docling/blob/main/CHANGELOG.md"

[project.entry-points.docling]
"docling_defaults" = "docling.models.plugins.defaults"

[project.scripts]
docling = "docling.cli.main:app"
docling-tools = "docling.cli.tools:app"

[project.optional-dependencies]
tesserocr = ['tesserocr (>=2.7.1,<3.0.0)']
ocrmac = ['ocrmac (>=1.0.0,<2.0.0) ; sys_platform == "darwin"']
vlm = [
  'transformers (>=4.46.0,<5.0.0)',
  'accelerate (>=1.2.1,<2.0.0)',
  'mlx-vlm >=0.1.22 ; python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64"',
]
rapidocr = [
  'rapidocr-onnxruntime (>=1.4.0,<2.0.0) ; python_version < "3.13"',
  'onnxruntime (>=1.7.0,<2.0.0)',
  # 'onnxruntime (>=1.7.0,<2.0.0) ; python_version >= "3.10"',
  # 'onnxruntime (>=1.7.0,<1.20.0) ; python_version < "3.10"',
]
asr = [
    "openai-whisper>=20240930",
]

[dependency-groups]
dev = [
    "pre-commit~=3.7",
    "mypy~=1.10",
    "types-setuptools~=70.3",
    "pandas-stubs~=2.1",
    "types-openpyxl~=3.1",
    "types-requests~=2.31",
    "boto3-stubs~=1.37",
    "types-urllib3~=1.26",
    "types-tqdm~=4.67",
    "coverage~=7.6",
    "pytest~=8.3",
    "pytest-cov>=6.1.1",
    "pytest-dependency~=0.6",
    "pytest-xdist~=3.3",
    "ipykernel~=6.29",
    "ipywidgets~=8.1",
    "nbqa~=1.9",
    "python-semantic-release~=7.32",
]
docs = [
  "mkdocs-material~=9.5",
  "mkdocs-jupyter~=0.25",
  "mkdocs-click~=0.8",
  "mkdocstrings[python]~=0.27",
  "griffe-pydantic~=1.1",
]
examples = [
  "datasets~=2.21",
  "python-dotenv~=1.0",
  "langchain-huggingface>=0.0.3",
  "langchain-milvus~=0.1",
  "langchain-text-splitters~=0.2",
]
constraints = [
  'onnxruntime (>=1.7.0,<2.0.0) ; python_version >= "3.10"',
  'onnxruntime (>=1.7.0,<1.20.0) ; python_version < "3.10"',
]


[tool.uv]
package = true
default-groups = "all"

[tool.uv.sources]
openai-whisper = { git = "https://github.com/openai/whisper.git", rev = "dd985ac4b90cafeef8712f2998d62c59c3e62d22" }

[tool.setuptools.packages.find]
include = ["docling*"]

[tool.ruff]
target-version = "py39"
line-length = 88
respect-gitignore = true

# extend-exclude = [
#     "tests",
# ]

[tool.ruff.format]
skip-magic-trailing-comma = false

[tool.ruff.lint]
select = [
  # "B",  # flake8-bugbear
  "C",  # flake8-comprehensions
  "C9", # mccabe
  # "D",  # flake8-docstrings
  "E",   # pycodestyle errors (default)
  "F",   # pyflakes (default)
  "I",   # isort
  "PD",  # pandas-vet
  "PIE", # pie
  # "PTH", # pathlib
  "Q", # flake8-quotes
  # "RET", # return
  "RUF", # Enable all ruff-specific checks
  # "SIM", # simplify
  "S307", # eval
  # "T20",  # (disallow print statements) keep debugging statements out of the codebase
  "W",     # pycodestyle warnings
  "ASYNC", # async
  "UP",    # pyupgrade
]

ignore = [
  "C408",   # Unnecessary `dict()` call (rewrite as a literal)
  "E501",   # Line too long, handled by ruff formatter
  "D107",   # "Missing docstring in __init__",
  "F401",   # imported but unused; consider using `importlib.util.find_spec` to test for "
  "F811",   # "redefinition of the same function"
  "PL",     # Pylint
  "RUF012", # Mutable Class Attributes
  "UP006",  # List vs list, etc
  "UP007",  # Option and Union
  "UP035",  # `typing.Set` is deprecated, use `set` instead"
]

#extend-select = []

[tool.ruff.lint.pep8-naming]
classmethod-decorators = [
  # Allow Pydantic's `@validator` decorator to trigger class method treatment.
  "pydantic.validator",
]

[tool.ruff.lint.per-file-ignores]
"__init__.py" = ["E402", "F401"]
"tests/*.py" = ["ASYNC"]         # Disable ASYNC check for tests

[tool.ruff.lint.mccabe]
max-complexity = 20

# [tool.ruff.lint.isort.sections]
# "docling" = ["docling_core", "docling_ibm_models", "docling_parse"]

[tool.ruff.lint.isort]
combine-as-imports = true
# section-order = [
#   "future",
#   "standard-library",
#   "third-party",
#   "docling",
#   "first-party",
#   "local-folder",
# ]

[tool.mypy]
pretty = true
# strict = true
no_implicit_optional = true
plugins = "pydantic.mypy"
python_version = "3.10"

[[tool.mypy.overrides]]
module = [
  "docling_parse.*",
  "pypdfium2.*",
  "networkx.*",
  "scipy.*",
  "filetype.*",
  "tesserocr.*",
  "docling_ibm_models.*",
  "easyocr.*",
  "ocrmac.*",
  "mlx_vlm.*",
  "lxml.*",
  "huggingface_hub.*",
  "transformers.*",
  "pylatexenc.*",
]
ignore_missing_imports = true

[tool.semantic_release]
# for default values check:
# https://github.com/python-semantic-release/python-semantic-release/blob/v7.32.2/semantic_release/defaults.cfg

version_source = "tag_only"
branch = "main"

# configure types which should trigger minor and patch version bumps respectively
# (note that they must be a subset of the configured allowed types):
parser_angular_allowed_types = "build,chore,ci,docs,feat,fix,perf,style,refactor,test"
parser_angular_minor_types = "feat"
parser_angular_patch_types = "fix,perf"