fa9699fa3c
* fix(tests): Adjust the test data to match the new version of LayoutPredictor from docling-ibm-models Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> * chore: Update poetry to use `docling-ibm-models` at version `v1.2.0` Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> --------- Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
147 lines
4.3 KiB
TOML
147 lines
4.3 KiB
TOML
[tool.poetry]
|
|
name = "docling"
|
|
version = "1.12.1" # DO NOT EDIT, updated automatically
|
|
description = "Docling PDF conversion package"
|
|
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>", "Peter Staar <taa@zurich.ibm.com>"]
|
|
license = "MIT"
|
|
readme = "README.md"
|
|
repository = "https://github.com/DS4SD/docling"
|
|
homepage = "https://github.com/DS4SD/docling"
|
|
keywords= ["docling", "convert", "document", "pdf", "layout model", "segmentation", "table structure", "table former"]
|
|
classifiers = [
|
|
"License :: OSI Approved :: MIT License",
|
|
"Operating System :: MacOS :: MacOS X",
|
|
"Operating System :: POSIX :: Linux",
|
|
"Development Status :: 5 - Production/Stable",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Science/Research",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
"Programming Language :: Python :: 3"
|
|
]
|
|
packages = [{include = "docling"}]
|
|
|
|
[tool.poetry.dependencies]
|
|
python = "^3.10"
|
|
pydantic = "^2.0.0"
|
|
docling-core = "^1.3.0"
|
|
docling-ibm-models = "^1.2.0"
|
|
deepsearch-glm = "^0.21.0"
|
|
filetype = "^1.2.0"
|
|
pypdfium2 = "^4.30.0"
|
|
pydantic-settings = "^2.3.0"
|
|
huggingface_hub = ">=0.23,<1"
|
|
requests = "^2.32.3"
|
|
easyocr = "^1.7"
|
|
docling-parse = "^1.2.0"
|
|
certifi = ">=2024.7.4"
|
|
rtree = "^1.3.0"
|
|
scipy = "^1.14.1"
|
|
pyarrow = "^16.1.0"
|
|
|
|
#########
|
|
# extras:
|
|
#########
|
|
python-dotenv = { version = "^1.0.1", optional = true }
|
|
llama-index-embeddings-huggingface = { version = "^0.3.1", optional = true }
|
|
llama-index-llms-huggingface-api = { version = "^0.2.0", optional = true }
|
|
llama-index-vector-stores-milvus = { version = "^0.2.1", optional = true }
|
|
langchain-huggingface = { version = "^0.0.3", optional = true}
|
|
langchain-milvus = { version = "^0.1.4", optional = true }
|
|
langchain-text-splitters = { version = "^0.2.4", optional = true }
|
|
|
|
##############
|
|
# constraints:
|
|
##############
|
|
torch = [
|
|
{version = "^2.2.2", optional = true, markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'"},
|
|
{version = "~2.2.2", optional = true, markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'"}
|
|
]
|
|
torchvision = [
|
|
{version = "^0", optional = true, markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'"},
|
|
{version = "~0.17.2", optional = true, markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'"}
|
|
]
|
|
typer = "^0.12.5"
|
|
|
|
[tool.poetry.group.dev.dependencies]
|
|
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 = "^2.2.2.240909"
|
|
ipykernel = "^6.29.5"
|
|
ipywidgets = "^8.1.5"
|
|
nbqa = "^1.9.0"
|
|
|
|
[tool.poetry.group.examples.dependencies]
|
|
datasets = "^2.21.0"
|
|
|
|
[tool.poetry.extras]
|
|
examples = [
|
|
"python-dotenv",
|
|
# LlamaIndex examples:
|
|
"llama-index-embeddings-huggingface",
|
|
"llama-index-llms-huggingface-api",
|
|
"llama-index-vector-stores-milvus",
|
|
# LangChain examples:
|
|
"langchain-huggingface",
|
|
"langchain-milvus",
|
|
"langchain-text-splitters",
|
|
]
|
|
|
|
|
|
[tool.poetry.scripts]
|
|
docling = "docling.cli.main:app"
|
|
|
|
[build-system]
|
|
requires = ["poetry-core"]
|
|
build-backend = "poetry.core.masonry.api"
|
|
|
|
[tool.black]
|
|
line-length = 88
|
|
target-version = ["py310"]
|
|
include = '\.pyi?$'
|
|
|
|
[tool.isort]
|
|
profile = "black"
|
|
line_length = 88
|
|
py_version=311
|
|
|
|
[tool.mypy]
|
|
pretty = true
|
|
# strict = true
|
|
no_implicit_optional = true
|
|
python_version = "3.10"
|
|
|
|
[[tool.mypy.overrides]]
|
|
module = [
|
|
"docling_parse.*",
|
|
"pypdfium2.*",
|
|
"networkx.*",
|
|
]
|
|
ignore_missing_imports = true
|
|
|
|
[tool.flake8]
|
|
max-line-length = 88
|
|
extend-ignore = ["E203", "E501"]
|
|
|
|
[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"
|