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: AutoOCR model selecting the best OCR model available and deprecating the usage of EasyOCR (#2391)

Browse Source 
* add auto ocr model

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Apply suggestions from code review

Co-authored-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>

* add final log warning

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* propagate default options

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* allow rapidocr models download

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* remove modelscope

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
This commit is contained in:
Michele Dolfi
2025-10-10 16:11:39 +02:00
committed by GitHub
parent cce18b2ff7
commit f7244a4333
9 changed files with 307 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
pyproject.toml
View File

@@ -52,7 +52,8 @@ dependencies = [
'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)',
'ocrmac (>=1.0.0,<2.0.0) ; sys_platform == "darwin"',
'rapidocr (>=3.3,<4.0.0) ; python_version < "3.14"',
'certifi (>=2024.7.4)',
'rtree (>=1.3.0,<2.0.0)',
'typer (>=0.12.5,<0.20.0)',
@@ -88,6 +89,7 @@ docling = "docling.cli.main:app"
docling-tools = "docling.cli.tools:app"
[project.optional-dependencies]
easyocr = ['easyocr (>=1.7,<2.0)']
tesserocr = ['tesserocr (>=2.7.1,<3.0.0)']
ocrmac = ['ocrmac (>=1.0.0,<2.0.0) ; sys_platform == "darwin"']
vlm = [
@@ -100,7 +102,6 @@ vlm = [
rapidocr = [
'rapidocr (>=3.3,<4.0.0) ; python_version < "3.14"',
'onnxruntime (>=1.7.0,<2.0.0)',
"modelscope>=1.29.0",
# 'onnxruntime (>=1.7.0,<2.0.0) ; python_version >= "3.10"',
# 'onnxruntime (>=1.7.0,<1.20.0) ; python_version < "3.10"',
]
@@ -143,6 +144,7 @@ examples = [
"langchain-huggingface>=0.0.3",
"langchain-milvus~=0.1",
"langchain-text-splitters~=0.2",
"modelscope>=1.29.0",
]
constraints = [
'onnxruntime (>=1.7.0,<2.0.0) ; python_version >= "3.10"',
@@ -252,6 +254,7 @@ module = [
"docling_ibm_models.*",
"easyocr.*",
"ocrmac.*",
"onnxruntime.*",
"mlx_vlm.*",
"lxml.*",
"huggingface_hub.*",