mirror of
https://github.com/docling-project/docling-jobkit.git
synced 2026-05-17 13:10:46 +00:00
github-actions[bot]
250 lines
6.5 KiB
TOML
250 lines
6.5 KiB
TOML
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[project]
|
|
name = "docling-jobkit"
|
|
version = "1.18.1" # DO NOT EDIT, updated automatically
|
|
description = "Running a distributed job processing documents with Docling."
|
|
readme = "README.md"
|
|
license = "MIT"
|
|
authors = [
|
|
{name="Michele Dolfi", email="dol@zurich.ibm.com"},
|
|
{name="Viktor Kuropiatnyk", email="vku@zurich.ibm.com"},
|
|
{name="Tiago Santana", email="Tiago.Santana@ibm.com"},
|
|
{name="Cesar Berrospi Ramis", email="ceb@zurich.ibm.com"},
|
|
{name="Panos Vagenas", email="pva@zurich.ibm.com"},
|
|
{name="Christoph Auer", email="cau@zurich.ibm.com"},
|
|
{name="Peter Staar", email="taa@zurich.ibm.com"},
|
|
]
|
|
maintainers = [
|
|
{name="Michele Dolfi", email="dol@zurich.ibm.com"},
|
|
{name="Cesar Berrospi Ramis", email="ceb@zurich.ibm.com"},
|
|
{name="Panos Vagenas", email="pva@zurich.ibm.com"},
|
|
{name="Christoph Auer", email="cau@zurich.ibm.com"},
|
|
{name="Peter Staar", email="taa@zurich.ibm.com"},
|
|
]
|
|
classifiers = [
|
|
"Operating System :: OS Independent",
|
|
"Development Status :: 5 - Production/Stable",
|
|
"Intended Audience :: Developers",
|
|
"Typing :: Typed",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
"Programming Language :: Python :: 3.14",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
"Topic :: Scientific/Engineering :: Information Analysis",
|
|
"Topic :: Software Development :: Build Tools",
|
|
"Topic :: Software Development :: Libraries :: Python Modules",
|
|
]
|
|
requires-python = ">=3.10"
|
|
dependencies = [
|
|
"docling>=2.88.0,<3.0.0",
|
|
"pydantic~=2.10",
|
|
"pydantic-settings~=2.4",
|
|
"boto3~=1.35",
|
|
"pandas~=2.2",
|
|
"httpx>=0.28,<1",
|
|
"typer>=0.12.5,<1",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
vlm = [
|
|
"docling[vlm]>=2.73.0,<3.0.0",
|
|
]
|
|
onnxruntime = [
|
|
"docling[onnxruntime]>=2.73.0,<3.0.0",
|
|
]
|
|
# asr = [
|
|
# "docling[asr]~=2.53",
|
|
# ]
|
|
kfp = [
|
|
"kfp[kubernetes]>=2.10.0",
|
|
]
|
|
rq = [
|
|
"rq~=2.4",
|
|
"msgpack~=1.1",
|
|
]
|
|
ray = [
|
|
"ray[serve]~=2.30 ; python_version < '3.14'",
|
|
"redis[hiredis]>=4.2,<8.0.0",
|
|
"msgpack~=1.1",
|
|
"psutil>=6.0.0",
|
|
"codeflare-sdk>=0.20.0; python_version >= '3.11' and python_version < '3.14'",
|
|
]
|
|
gdrive = [
|
|
"google-api-python-client>=2.183.0",
|
|
"google-auth-oauthlib>=1.2.2",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"coverage>=7.8.0",
|
|
"mypy~=1.11",
|
|
"pre-commit~=3.8",
|
|
"pytest~=8.3",
|
|
"pytest-asyncio~=0.24",
|
|
"pytest-check~=2.4",
|
|
"pytest-cov>=6.1.1",
|
|
"python-semantic-release~=7.32",
|
|
"boto3-stubs[s3]~=1.35",
|
|
"ruff>=0.9.6",
|
|
"types-pyyaml>=6.0.12.20250915",
|
|
"aiohttp>=3.13.3",
|
|
"types-psutil>=7.2.2.20260130",
|
|
]
|
|
|
|
[tool.uv.sources]
|
|
# docling = { git = "https://github.com/docling-project/docling/", rev = "main" }
|
|
# docling = { path = "../docling", editable = true }
|
|
|
|
|
|
[tool.uv]
|
|
package = true
|
|
|
|
[tool.hatch.build.targets.sdist]
|
|
include = ["docling_jobkit"]
|
|
|
|
[project.scripts]
|
|
docling-ray-job = "docling_jobkit.ray_job.main:main"
|
|
docling-jobkit-local = "docling_jobkit.cli.local:app"
|
|
docling-jobkit-multiproc = "docling_jobkit.cli.multiproc:app"
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/docling-project/docling-jobkit"
|
|
Documentation = "https://docling-project.github.io/docling/usage/jobkit/"
|
|
Repository = "https://github.com/docling-project/docling-jobkit"
|
|
Issues = "https://github.com/docling-project/docling-jobkit/issues"
|
|
Changelog = "https://github.com/docling-project/docling-jobkit/blob/main/CHANGELOG.md"
|
|
|
|
[tool.ruff]
|
|
target-version = "py310"
|
|
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
|
|
]
|
|
|
|
ignore = [
|
|
"E501", # Line too long, handled by ruff formatter
|
|
"D107", # "Missing docstring in __init__",
|
|
"F811", # "redefinition of the same function"
|
|
"PL", # Pylint
|
|
"RUF012", # Mutable Class Attributes
|
|
]
|
|
|
|
[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", "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.mypy]
|
|
pretty = true
|
|
# strict = true
|
|
no_implicit_optional = true
|
|
plugins = "pydantic.mypy"
|
|
python_version = "3.10"
|
|
|
|
[[tool.mypy.overrides]]
|
|
module = [
|
|
"boto3.*",
|
|
"botocore.*",
|
|
"easyocr.*",
|
|
"tesserocr.*",
|
|
"rapidocr_onnxruntime.*",
|
|
"kfp.*",
|
|
"kfp_server_api.*",
|
|
"pandas.*",
|
|
"msgpack.*",
|
|
"mlx_vlm.*",
|
|
"googleapiclient.*",
|
|
"google_auth_oauthlib.*",
|
|
"ray.*",
|
|
"codeflare_sdk.*",
|
|
]
|
|
ignore_missing_imports = true
|
|
|
|
# Skip ray_job module on Python 3.14+ where ray is not supported
|
|
[[tool.mypy.overrides]]
|
|
module = "docling_jobkit.ray_job.*"
|
|
ignore_errors = true
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
asyncio_default_fixture_loop_scope = "function"
|
|
minversion = "8.2"
|
|
testpaths = [
|
|
"tests",
|
|
]
|
|
addopts = "-rA --color=yes --tb=short --maxfail=5"
|
|
markers = [
|
|
"asyncio",
|
|
]
|
|
|
|
[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"
|