mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-08 20:58:11 +00:00
feat: equations to latex in MSWord backend (with inline groups) (#1114)
* Equation groups Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com> * fix: Proper handling of orphan IDs in layout postprocessing (#1118) * Fix the handling of orphan IDs in layout postprocessing Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update test cases Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com> * chore: bump version to 2.25.2 [skip ci] * docs: add description of DOCLING_ARTIFACTS_PATH env var (#1124) add env var in docs Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com> * fix(CLI): fix help message for abort options (#1130) fix help message Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com> * perf: New revision code formula model and document picture classifier (#1140) * new version code formula model Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * new version document picture classifier Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * new code formula model Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * restored original code formula test pdf Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> --------- Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com> * feat: Use new TableFormer model weights and default to accurate model version (#1100) * feat: New tableformer model weights [WIP] Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com> * Updated TF version Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Updated tests, after merging with Main, Switched to Accurate TF model by default Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com> Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> Co-authored-by: Maksym Lysak <mly@zurich.ibm.com> Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com> * chore: bump version to 2.26.0 [skip ci] * fix: Pass tests, update docling-core to 2.22.0 (#1150) fix: update docling-core to 2.22.0 Update dependency library docling-core to latest release 2.22.0 Fix regression tests and ground truth files Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> * Updating content hash Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com> --------- Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com> Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com> Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Co-authored-by: Christoph Auer <60343111+cau-git@users.noreply.github.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Co-authored-by: Matteo <43417658+Matteo-Omenetti@users.noreply.github.com> Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> Co-authored-by: Maksym Lysak <mly@zurich.ibm.com> Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Rafael Teixeira de Lima
committed by
GitHub
GitHub
parent
aa92a57fa9
commit
6eb718f849
100
pyproject.toml
100
pyproject.toml
@@ -2,23 +2,43 @@
|
||||
name = "docling"
|
||||
version = "2.26.0" # 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>"]
|
||||
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/DS4SD/docling"
|
||||
homepage = "https://github.com/DS4SD/docling"
|
||||
keywords= ["docling", "convert", "document", "pdf", "docx", "html", "markdown", "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"}]
|
||||
keywords = [
|
||||
"docling",
|
||||
"convert",
|
||||
"document",
|
||||
"pdf",
|
||||
"docx",
|
||||
"html",
|
||||
"markdown",
|
||||
"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]
|
||||
######################
|
||||
@@ -40,7 +60,7 @@ 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'" }
|
||||
{ version = ">=1.6.0,<1.14.0", markers = "python_version < '3.10'" },
|
||||
]
|
||||
typer = "^0.12.5"
|
||||
python-docx = "^1.1.2"
|
||||
@@ -56,21 +76,22 @@ 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'" }
|
||||
{ version = "^1.7.0", optional = true, markers = "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 }
|
||||
{ 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 },
|
||||
{ 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"
|
||||
pylatexenc = "^2.10"
|
||||
|
||||
[tool.poetry.group.dev.dependencies]
|
||||
black = {extras = ["jupyter"], version = "^24.4.2"}
|
||||
black = { extras = ["jupyter"], version = "^24.4.2" }
|
||||
pytest = "^7.2.2"
|
||||
pre-commit = "^3.7.1"
|
||||
mypy = "^1.10.1"
|
||||
@@ -93,7 +114,7 @@ types-tqdm = "^4.67.0.20241221"
|
||||
mkdocs-material = "^9.5.40"
|
||||
mkdocs-jupyter = "^0.25.0"
|
||||
mkdocs-click = "^0.8.1"
|
||||
mkdocstrings = {extras = ["python"], version = "^0.27.0"}
|
||||
mkdocstrings = { extras = ["python"], version = "^0.27.0" }
|
||||
griffe-pydantic = "^1.1.0"
|
||||
|
||||
[tool.poetry.group.examples.dependencies]
|
||||
@@ -108,8 +129,8 @@ 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"' },
|
||||
{ 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]
|
||||
@@ -117,12 +138,12 @@ 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"}
|
||||
{ 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"}
|
||||
{ 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.extras]
|
||||
@@ -147,7 +168,7 @@ include = '\.pyi?$'
|
||||
[tool.isort]
|
||||
profile = "black"
|
||||
line_length = 88
|
||||
py_version=39
|
||||
py_version = 39
|
||||
|
||||
[tool.mypy]
|
||||
pretty = true
|
||||
@@ -158,18 +179,19 @@ python_version = "3.10"
|
||||
|
||||
[[tool.mypy.overrides]]
|
||||
module = [
|
||||
"docling_parse.*",
|
||||
"pypdfium2.*",
|
||||
"networkx.*",
|
||||
"scipy.*",
|
||||
"filetype.*",
|
||||
"tesserocr.*",
|
||||
"docling_ibm_models.*",
|
||||
"easyocr.*",
|
||||
"ocrmac.*",
|
||||
"lxml.*",
|
||||
"huggingface_hub.*",
|
||||
"transformers.*",
|
||||
"docling_parse.*",
|
||||
"pypdfium2.*",
|
||||
"networkx.*",
|
||||
"scipy.*",
|
||||
"filetype.*",
|
||||
"tesserocr.*",
|
||||
"docling_ibm_models.*",
|
||||
"easyocr.*",
|
||||
"ocrmac.*",
|
||||
"lxml.*",
|
||||
"huggingface_hub.*",
|
||||
"transformers.*",
|
||||
"pylatexenc.*",
|
||||
]
|
||||
ignore_missing_imports = true
|
||||
|
||||
|
||||
Reference in New Issue
Block a user