mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 12:48:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Integrate ListItemMarkerProcessor into document assembly (#1825)

Browse Source 
* Integrate ListItemMarkerProcessor into document assembly

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update to final version

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update all test cases

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Upgrade deps

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-07-01 10:04:58 +02:00
committed by GitHub
parent bdfee4e2d0
commit 56a0e104f7
24 changed files with 739 additions and 1675 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
pyproject.toml
View File

@@ -45,8 +45,8 @@ requires-python = '>=3.9,<4.0'
dependencies = [
'pydantic (>=2.0.0,<3.0.0)',
'docling-core[chunking] (>=2.39.0,<3.0.0)',
'docling-ibm-models (>=3.4.4,<4.0.0)',
'docling-parse (>=4.0.0,<5.0.0)',
'docling-ibm-models (>=3.6.0,<4)',
'filetype (>=1.2.0,<2.0.0)',
'pypdfium2 (>=4.30.0,<5.0.0)',
'pydantic-settings (>=2.3.0,<3.0.0)',
@@ -91,7 +91,7 @@ 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"',
'mlx-vlm (>=0.1.22,<0.2) ; 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"',