mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-08 12:48:28 +00:00
feat: simplify dependencies, switch to uv (#1700)
* refactor with uv Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * constraints for onnxruntime Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * more constraints Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
GitHub
318
pyproject.toml
318
pyproject.toml
@@ -1,20 +1,8 @@
|
||||
[tool.poetry]
|
||||
[project]
|
||||
name = "docling"
|
||||
version = "2.35.0" # 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."
|
||||
authors = [
|
||||
"Christoph Auer <cau@zurich.ibm.com>",
|
||||
"Michele Dolfi <dol@zurich.ibm.com>",
|
||||
"Maxim Lysak <mly@zurich.ibm.com>",
|
||||
"Nikos Livathinos <nli@zurich.ibm.com>",
|
||||
"Ahmed Nassar <ahn@zurich.ibm.com>",
|
||||
"Panos Vagenas <pva@zurich.ibm.com>",
|
||||
"Peter Staar <taa@zurich.ibm.com>",
|
||||
]
|
||||
license = "MIT"
|
||||
readme = "README.md"
|
||||
repository = "https://github.com/docling-project/docling"
|
||||
homepage = "https://github.com/docling-project/docling"
|
||||
keywords = [
|
||||
"docling",
|
||||
"convert",
|
||||
@@ -29,149 +17,137 @@ keywords = [
|
||||
"table former",
|
||||
]
|
||||
classifiers = [
|
||||
"License :: OSI Approved :: MIT License",
|
||||
"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",
|
||||
]
|
||||
packages = [{ include = "docling" }]
|
||||
|
||||
[tool.poetry.dependencies]
|
||||
######################
|
||||
# actual dependencies:
|
||||
######################
|
||||
python = "^3.9"
|
||||
pydantic = "^2.0.0"
|
||||
docling-core = {version = "^2.31.2", extras = ["chunking"]}
|
||||
docling-ibm-models = "^3.4.0"
|
||||
docling-parse = "^4.0.0"
|
||||
filetype = "^1.2.0"
|
||||
pypdfium2 = "^4.30.0"
|
||||
pydantic-settings = "^2.3.0"
|
||||
huggingface_hub = ">=0.23,<1"
|
||||
requests = "^2.32.2"
|
||||
easyocr = "^1.7"
|
||||
tesserocr = { version = "^2.7.1", optional = true }
|
||||
certifi = ">=2024.7.4"
|
||||
rtree = "^1.3.0"
|
||||
scipy = [
|
||||
{ version = "^1.6.0", markers = "python_version >= '3.10'" },
|
||||
{ version = ">=1.6.0,<1.14.0", markers = "python_version < '3.10'" },
|
||||
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" },
|
||||
]
|
||||
typer = ">=0.12.5,<0.16.0"
|
||||
python-docx = "^1.1.2"
|
||||
python-pptx = "^1.0.2"
|
||||
beautifulsoup4 = "^4.12.3"
|
||||
pandas = "^2.1.4"
|
||||
marko = "^2.1.2"
|
||||
openpyxl = "^3.1.5"
|
||||
lxml = ">=4.0.0,<6.0.0"
|
||||
ocrmac = { version = "^1.0.0", markers = "sys_platform == 'darwin'", optional = true }
|
||||
rapidocr-onnxruntime = { version = "^1.4.0", optional = true, markers = "python_version < '3.13'" }
|
||||
onnxruntime = [
|
||||
# 1.19.2 is the last version with python3.9 support,
|
||||
# see https://github.com/microsoft/onnxruntime/releases/tag/v1.20.0
|
||||
{ version = ">=1.7.0,<1.20.0", optional = true, markers = "python_version < '3.10'" },
|
||||
{ version = "^1.7.0", optional = true, markers = "python_version >= '3.10'" },
|
||||
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,<0.16.0)',
|
||||
'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)',
|
||||
'click (<8.2.0)',
|
||||
'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"',
|
||||
]
|
||||
|
||||
transformers = [
|
||||
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^4.46.0", optional = true },
|
||||
{ markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~4.42.0", optional = true },
|
||||
]
|
||||
accelerate = [
|
||||
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^1.2.1", optional = true },
|
||||
]
|
||||
pillow = ">=10.0.0,<12.0.0"
|
||||
tqdm = "^4.65.0"
|
||||
pluggy = "^1.0.0"
|
||||
pylatexenc = "^2.10"
|
||||
click = "<8.2.0"
|
||||
[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"
|
||||
|
||||
[tool.poetry.group.dev.dependencies]
|
||||
python = "^3.9.2"
|
||||
black = { extras = ["jupyter"], version = "^24.4.2" }
|
||||
pytest = "^7.2.2"
|
||||
pre-commit = "^3.7.1"
|
||||
mypy = "^1.10.1"
|
||||
isort = "^5.10.1"
|
||||
python-semantic-release = "^7.32.2"
|
||||
flake8 = "^6.0.0"
|
||||
pyproject-flake8 = "^6.0.0"
|
||||
pytest-xdist = "^3.3.1"
|
||||
types-requests = "^2.31.0.2"
|
||||
flake8-pyproject = "^1.2.3"
|
||||
pylint = "^2.17.5"
|
||||
pandas-stubs = "^2.1.4.231227"
|
||||
ipykernel = "^6.29.5"
|
||||
ipywidgets = "^8.1.5"
|
||||
nbqa = "^1.9.0"
|
||||
types-openpyxl = "^3.1.5.20241114"
|
||||
types-tqdm = "^4.67.0.20241221"
|
||||
coverage = "^7.6.2"
|
||||
pytest-cov = "^6.0.0"
|
||||
[project.entry-points.docling]
|
||||
"docling_defaults" = "docling.models.plugins.defaults"
|
||||
|
||||
[tool.poetry.group.docs.dependencies]
|
||||
mkdocs-material = "^9.5.40"
|
||||
mkdocs-jupyter = "^0.25.0"
|
||||
mkdocs-click = "^0.8.1"
|
||||
mkdocstrings = { extras = ["python"], version = "^0.27.0" }
|
||||
griffe-pydantic = "^1.1.0"
|
||||
|
||||
[tool.poetry.group.examples.dependencies]
|
||||
datasets = "^2.21.0"
|
||||
python-dotenv = "^1.0.1"
|
||||
langchain-huggingface = "^0.0.3"
|
||||
langchain-milvus = "^0.1.4"
|
||||
langchain-text-splitters = "^0.2.4"
|
||||
|
||||
[tool.poetry.group.constraints]
|
||||
optional = true
|
||||
|
||||
[tool.poetry.group.constraints.dependencies]
|
||||
numpy = [
|
||||
{ version = ">=1.24.4,<3.0.0", markers = 'python_version >= "3.10"' },
|
||||
{ version = ">=1.24.4,<2.1.0", markers = 'python_version < "3.10"' },
|
||||
]
|
||||
|
||||
[tool.poetry.group.mac_intel]
|
||||
optional = true
|
||||
|
||||
[tool.poetry.group.mac_intel.dependencies]
|
||||
torch = [
|
||||
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^2.2.2" },
|
||||
{ markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~2.2.2" },
|
||||
]
|
||||
torchvision = [
|
||||
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^0" },
|
||||
{ markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~0.17.2" },
|
||||
]
|
||||
|
||||
|
||||
[tool.poetry.group.lm.dependencies]
|
||||
peft = "^0.15.2"
|
||||
backoff = "^2.2.1"
|
||||
|
||||
[tool.poetry.extras]
|
||||
tesserocr = ["tesserocr"]
|
||||
ocrmac = ["ocrmac"]
|
||||
vlm = ["transformers", "accelerate"]
|
||||
rapidocr = ["rapidocr-onnxruntime", "onnxruntime"]
|
||||
|
||||
[tool.poetry.scripts]
|
||||
[project.scripts]
|
||||
docling = "docling.cli.main:app"
|
||||
docling-tools = "docling.cli.tools:app"
|
||||
|
||||
[tool.poetry.plugins."docling"]
|
||||
"docling_defaults" = "docling.models.plugins.defaults"
|
||||
[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"',
|
||||
]
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry-core"]
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
[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.setuptools.packages.find]
|
||||
include = ["docling*"]
|
||||
|
||||
[tool.ruff]
|
||||
target-version = "py39"
|
||||
@@ -187,51 +163,51 @@ 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
|
||||
# "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"
|
||||
"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",
|
||||
# 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
|
||||
"tests/*.py" = ["ASYNC"] # Disable ASYNC check for tests
|
||||
|
||||
[tool.ruff.lint.mccabe]
|
||||
max-complexity = 20
|
||||
|
||||
Reference in New Issue
Block a user