GitLab

- Remove use_npu variable initialization
- Comment out device assignment and npu check
- Comment out use_npu parameter in ModifiedPaddleOCR constructor

- Update `clean_memory.py` to use `torch_npu.npu` instead of `torch.npu`
- Update `model_utils.py` to use `torch_npu.npu` instead of `torch.npu`
- Simplify NPU availability check and bfloat16 support in `pdf_parse_union_core_v2.py`

- Update clean_memory function to support both CUDA and NPU devices
- Implement get_device function to centralize device selection logic
- Modify model initialization and memory cleaning to use the selected device
- Update RapidTableModel to support both RapidOCR and PaddleOCR engines

- Add NPU support for memory cleaning and model initialization
- Optimize table model initialization and prediction process
- Update memory utils to support NPU
- Add language parameter for table model

- Comment out logging statements for title list, title completion, and length comparison
- Improve code readability and reduce clutter by removing unused debug information

- Implement llm_aided_title function to optimize document titles using LLM
- Update pdf_parse_union_core_v2.py to include title optimization
- Modify ocr_mkcontent.py to use optimized title levels- Add openai SDK dependency in setup.py

- 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

- Remove remove_overlaps_chars function
- Add check_chars_is_overlap_in_span function
- Update span processing logic to handle character overlaps- Improve efficiency and readability of overlap detection

- Implement remove_overlaps_chars function to detect and remove overlapping characters within spans
- Integrate remove_overlaps_chars function into the PDF parsing process
- Improve character-level processing and reduce redundancy in OCR results

- Add automatic conversion of uploaded files to PDF
- Update max page slider range and default value- Prevent interaction with PDF preview to avoid errors
- Increase Markdown rendering height for better visibility
- Update file change event handling for PDF conversion
- Modify supported image suffixes for file upload

- Move __use_inside_model__ and __model_mode__ from operators/__init__.py to model/__init__.py
- These variables are more appropriately located in the model module since they relate to model configuration

- 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

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

- 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

- 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

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