pyproject.toml

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "docling-sdg"
version = "0.4.0"  # DO NOT EDIT, updated automatically
description = "Docling for Synthetic Data Generation (SDG) provides a set of tools to create artificial data from documents, leveraging generative AI and docling's parsing capabilities."
license = "MIT"
authors = [
    {name="Cesar Berrospi Ramis", email="ceb@zurich.ibm.com"},
    {name="Rafael Teixeira de Lima", email="rtdl@ibm.com"},
    {name="Tim Strohmeyer", email="Tim.Strohmeyer@ibm.com"},
    {name="Panos Vagenas", email="pva@zurich.ibm.com"},
    {name="Michele Dolfi", email="dol@zurich.ibm.com"},
    {name="Peter Staar", email="taa@zurich.ibm.com"},
 ]
maintainers = [
    {name="Cesar Berrospi Ramis", email="ceb@zurich.ibm.com"},
    {name="Tim Strohmeyer", email="Tim.Strohmeyer@ibm.com"},
    {name="Michele Dolfi", email="dol@zurich.ibm.com"},
    {name="Peter Staar", email="taa@zurich.ibm.com"},
]
readme = "README.md"
keywords = ["docling", "document understanding", "artificial intelligence", "AI", "sdg", "synthetic data generation", "llm", "large language models", "prompt engineering"]
classifiers=[
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "Natural Language :: English",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Scientific/Engineering :: Information Analysis",
    "Topic :: Software Development :: Build Tools",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Typing :: Typed",
]
requires-python = ">=3.10,<3.13"
dependencies = [
    "docling>=2.26.0",
    "docling-core[chunking]>=2.23.0",
    "llama-index-core>=0.12.25",
    "llama-index-llms-ibm>=0.3.3",
    "pydantic>=2.0.0",
    "semchunk>=2.2.2",
    "transformers>=4.42.4",
    "typer>=0.12.5",
    "typing-extensions>=4.12.2",
    "llama-index-llms-openai-like (>=0.3.4,<0.4.0)",
    "llama-index-embeddings-huggingface>=0.5.5",
]

[dependency-groups]
dev = [
    "mypy>=1.15.0",
    "pre-commit>=4.1.0",
    "pytest>=8.3.5",
    "pytest-cov>=6.1.1",
    "python-semantic-release~=7.32",
    "ruff>=0.10.0",
]

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

[project.urls]
Homepage = "https://github.com/docling-project/docling-sdg"
Repository = "https://github.com/docling-project/docling-sdg"
Issues = "https://github.com/docling-project/docling-sdg/issues"
Changelog = "https://github.com/docling-project/docling-sdg/blob/main/CHANGELOG.md"

[tool.hatch.build.targets.sdist]
include = ["docling_sdg"]

[tool.uv]
package = true

[tool.ruff]
line-length = 88
target-version = "py310"
fix = true
respect-gitignore = true

[tool.ruff.format]
# Like Black, use double quotes for strings.
quote-style = "double"

# Like Black, indent with spaces, rather than tabs.
indent-style = "space"

# Like Black, respect magic trailing commas.
skip-magic-trailing-comma = false

# Like Black, automatically detect the appropriate line ending.
line-ending = "auto"

# Format docstrings
docstring-code-format = true

[tool.ruff.lint]
select = [
    # flake8-bugbear
    "B",
    # McCabe
    "C",
    # pydocstyle
    "D",
    # pycodestyle
    "E",
    # Pyflakes
    "F",
    # isort
    "I",
    # pycodestyle warnings
    "W"
]
ignore = ["D100", "D101", "D102", "D103", "D104", "D105", "D107", "B008"]

[tool.ruff.lint.extend-per-file-ignores]
"__init__.py" = [
    # Module imported but unused
    "F401",
]

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

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

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

[tool.ruff.lint.pydocstyle]
convention = "google"

[tool.ruff.lint.mccabe]
max-complexity = 15

[tool.mypy]
pretty = true
strict = true
no_implicit_optional = true
implicit_reexport = true
namespace_packages = true
show_error_codes = true
python_version = "3.10"
plugins = ["pydantic.mypy"]

[[tool.mypy.overrides]]
module = [
    "transformers.*",
    "llama_index.*",
    "tqdm.*",
]
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"