GitLab

refactor: refactor code

feat(language-detection): add YOLOv11 language detection model

- Add YOLOv11 language detection model for PDF documents
- Implement language detection in PymuDocDataset
- Update app.py to include 'auto' language option
- Create language detection utilities and constants

feat: add get_middle_json method

refactor(magic_pdf): remove YOLO_VERBOSE setting and update YOLOv8 prediction verbosity

- Remove YOLO_VERBOSE environment variable from multiple files
- Set verbose=False in YOLOv8 prediction method to suppress logger output

fix(pdf): improve ligature handling and text extraction

- 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

docs: fix image path

feat: add batch prediction methods for YOLOv8 and Unimernet models

Docs/tune docs

remove old demo code

fix: remove deprecated code

perf(layout): optimize layout detection for PDF extraction

- 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