boto3>=1.28.43
Brotli>=1.1.0
click>=8.1.7
PyMuPDF>=1.24.9,<1.24.14
loguru>=0.6.0
numpy>=1.21.6,<2.0.0
fast-langdetect>=0.2.3
scikit-learn>=1.0.2
transformers>=4.37.2  # Updated for LayoutLMv3
pdfminer.six==20231228
unimernet==0.2.3
doclayout_yolo==0.0.2b1
matplotlib
ultralytics>=8.3.48
paddleocr==2.7.3
paddlepaddle-gpu @ https://paddle-whl.bj.bcebos.com/stable/cu118/paddlepaddle-gpu/paddlepaddle_gpu-3.0.0b1-cp310-cp310-linux_x86_64.whl
struct-eqtable==0.3.2
detectron2 @ https://wheels-1251341229.cos.ap-shanghai.myqcloud.com/assets/whl/detectron2/detectron2-0.6-cp310-cp310-linux_x86_64.whl
magic-pdf>=1.0.1
torch>=2.2.2,<=2.3.1
torchvision>=0.17.2,<=0.18.1
rapid-table>=1.0.3,<2.0.0
rapidocr-paddle
rapidocr-onnxruntime
gradio-pdf>=0.0.21
openai
telebot
requests
PyPDF2>=3.0.0  # Updated for better PDF parsing
Pillow>=10.0.0  # Required for image processing
pytesseract>=0.3.10  # Optional for OCR capabilities
python-Levenshtein>=0.21.1  # For text similarity comparison
pdf2image>=1.16.3  # For PDF to image conversion
layoutlmv3 @ git+https://github.com/microsoft/unilm.git#subdirectory=layoutlmv3  # For LayoutLMv3