GitLab

- Add LLM-aided formula and text correction functionality
- Update config reader to include LLM-aided settings
- Create new LLM-aided processing module
- Update main processing script to incorporate LLM-aided corrections
- Modify download scripts to check for new config version

- Move ligature replacement function to pdf_parse_union_core_v2.py
- Optimize ligature replacement using a more efficient approach
- Modify text extraction flags to preserve ligatures in PDF content
- Remove unnecessary function from ocr_mkcontent.py

- Add initial setup for layout detection
- Implement conditional cropping for tall images
- Skip cropping for wide images to improve performance
- Reuse Image object across layout detection steps

Docs/refactor en docs

master->dev

Release 0.10.6

Dev->release

build(docker): add torch and torchvision dependencies

- Add torch>=2.2.2,<=2.3.1 to requirements-docker.txt- Add torchvision>=0.17.2,<=0.18.1 to requirements-docker.txt

Release 0.10.6

refactor(draw_bbox): remove redundant '_line_sort' suffix from output filename

refactor(draw_bbox): remove redundant '_line_sort' suffix from output  filename

- Updated the filename generation logic in the draw_bbox function
- Removed the unnecessary '_line_sort' suffix from the output PDF filename

- Remove unused import of ocr_model_init from magic_pdf.model.sub_modules.model_init
- Keep existing functionality and structure intact

fix: dup classify pdf type & improve layout detection for DocLayout_YOLO model 

feat(layout): improve layout detection for DocLayout_YOLO model

- Implement image cropping and pasting technique to enhance layout detection
- Adjust detected polygons to original image coordinates
- Add comments for better code readability

fix: dup classify pdf type

build(deps): update torch and torchvision version requirements

build(deps): update torch and torchvision version requirements

- Specify torch==2.3.1 and torchvision==0.18.1 for Windows CUDA installation
- Add torch and torchvision version constraints in setup.py:
  - torch>=2.2.2,<=2.3.1
  - torchvision>=0.17.2,<=0.18.1
- Update installation instructions in both English and Chinese README files

fix(detect_invalid_chars):fix the stack error caused by multiple memory releases in PyMuPDF

- Uncomment pdfminer.six in requirements.txt
- Specify version 20231228 for pdfminer.six

- Change import paths from paddleocr.ppocr to ppocr for utility functions
- Update import paths for logging and utility modules in ppocr_273_mod.py- Modify import paths for tablemaster_paddle.py to use ppstructure instead of paddleocr.ppstructure

- Replace MuPDF with pdfminer for detecting invalid characters in PDFs
- Uncomment and update the detect_invalid_chars function to use pdfminer
- Update the check_invalid_chars function in pdf_meta_scan.py to use the new implementation

- Change import path for TableSystem from 'ppstructure.table.predict_table' to 'paddleocr.ppstructure.table.predict_table'
- Change import path for init_args from 'ppstructure.utility' to 'paddleocr.ppstructure.utility'