GitLab

- 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

- Update model download instructions for versions 0.9.x and later
- Simplify demo scripts by removing unnecessary model configuration
- Add visualization function to draw bounding boxes
- Update CLI help message with new URL

fix(demo): add fallback to internal model when external model data is missingIf no valid model data is provided, the system now checks if an internal model
should be used. This enhances the robustness of the demo pipeline by providing
a default behavior when essential data is not available.