GitLab

- Enhance the logging of execution times by adding more detailed function identification
- Implement class name and module name inclusion for better traceability

- Remove PIL usage across multiple files
- Convert image processing functions to use NumPy arrays
- Update crop_img function to work with NumPy arrays
- Modify image loading and resizing to use NumPy and OpenCV
- Clean up unused imports and comments related to PIL

- Add performance_stats module to measure and print execution time statistics
- Implement measure_time decorator to track execution time of key functions
- Remove multi-threading in pdf parsing for better resource management
- Optimize pdf parsing logic for improved performance

- Increase batch size from 8 to 256 for language detection inference
- Add timing measurement for language detection process

- Add a check to return 0 when either bbox1_area or bbox2_area is zero
- This prevents division by zero errors when calculating IoU

- Add `remove_invalid_surrogates` function to filter out invalid UTF-16 surrogate pairs
- Integrate the new function into the `detect_lang` workflow
- Include a test case with UTF-16 surrogates to verify the fix

- Merge title blocks that are close to each other horizontally
- Adjust line insertion logic for title blocks- Increase image size and decrease confidence threshold for layout detection
- Update DocLayoutYOLO model weights
- Refactor drawing of bounding boxes for different block types

- Add MPS support for Apple Silicon devices
- Implement empty_cache() for MPS devices
- Set PYTORCH_ENABLE_MPS_FALLBACK environment variable
- Adjust MFR model device allocation for MPS

- Improve language detection by removing newline characters from the input text
- Add error handling and fallback mechanism to deal with text containing control characters

- Add `draw_char_bbox` function to `draw_bbox.py` for drawing character bounding boxes
- Integrate `draw_char_bbox` into `common.py` for use in PDF processing pipeline
- Include option to draw character bounding boxes in debug mode

- 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

- 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

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

- 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

- Replace pdfminer with PyMuPDF for character detection
- Implement new method detect_invalid_chars_by_pymupdf
- Update check_invalid_chars in pdf_meta_scan.py to use new method
- Add __replace_0xfffd function in pdf_parse_union_core_v2.py to handle special characters
- Remove unused imports and update requirements.txt

- Remove unused imports from commons.py
- Delete unused functions related to AWS and S3 operations
- Update import statements in other modules to reflect changes in commons.py
- Remove redundant code and improve code readability

- Implement new text extraction method (txt_spans_extract_v2) to enhance accuracy
- Add character filling in spans for better text reconstruction
- Introduce empty span handling using OCR for missed text
- Optimize span filtering and overlap removal