- Update package sources to use Aliyun mirrors for faster downloads
- Upgrade pip and install Python packages in virtual environment
- Add python3.10-dev package to Huawei NPU Dockerfile
- Update requirements file URLs to master branch- Install specific version of torch_npu in Huawei NPU Dockerfile
- Update magic-pdf installation method
- Improve modelscope installation process
- Optimize model download and configuration update steps
- Add Dockerfile for global setup with Ubuntu base image
- Add Dockerfile for Huawei NPU setup with Ascend base image
- Update requirements file structure: - Rename requirements-docker.txt to docker/china/requirements.txt - Add new requirements files for global and Huawei NPU setups
- Install necessary packages and dependencies in both Dockerfiles- Set up virtual environment and install Python packages
- Download models and configure magic-pdf for both setups
- Add section for using NPU acceleration in both English and Chinese README files
- Update system requirements to include CANN environment for NPU support
- Enhance the "Quick Start" guide with NPU-related information- Modify hardware requirements to specify "Ascend 910b" for NPU acceleration
- 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
- Add missing 'else' statement in OCR model selection logic
- Ensure consistent formatting of 'if' statements for better readability
- Remove unnecessary empty line in the 'app.py' file
- Implement ONNXModelSingleton to manage ONNX models
- Modify ModifiedPaddleOCR to use ONNX models on ARM CPUs without CUDA
- Update RapidTableModel to use RapidOCR with ONNXRuntime on CPU
- Add rapidocr_onnxruntime dependency in setup.py
- Update the logic for inserting spaces between characters- Consider the next character's position instead of the previous one
- Adjust the spacing threshold to 25% of the average character width
- Ignore spaces at the end of lines to prevent double spaces
- 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
- Create demo.py script for PDF file processing
- Implement PDF reading, classification, and inference usingOpendatalab's magic_pdf library- Add pipelines for OCR and text modes
- Include result visualization and markdown export
- 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
myhloli