boto3>=1.28.43
Brotli>=1.1.0
click>=8.1.7
fast-langdetect<0.3.0,>=0.2.3
loguru>=0.6.0
numpy<2.0.0,>=1.21.6
pydantic>=2.7.2
PyMuPDF<=1.24.14,>=1.24.9
scikit-learn>=1.0.2
transformers
pdfminer.six==20231228
omegaconf>=2.3.0
matplotlib>=3.8.4
iopath>=0.1.9
timm==0.9.16
opencv-python>=4.6.0
fairscale>=0.4.13
ftfy>=6.2.0
albumentations>=1.4.4
wand>=0.6.13
webdataset>=0.2.86
rapidfuzz>=3.8.1
termcolor>=2.4.0
pandas>=2.2.2
evaluate>=0.4.1
rich>=13.7.1
jupyterlab>=4.1.6
tabulate>=0.9.0
nltk>=3.8.1
streamlit>=1.33.0
pypdfium2>=4.29.0
pdf2image>=1.17.0
streamlit_drawable_canvas>=0.9.3
torch<=2.3.1,>=2.2.2
torchvision<=0.18.1,>=0.17.2
ultralytics>=8.3.48
paddleocr==2.7.3
struct-eqtable==0.3.2
einops
accelerate
doclayout_yolo==0.0.2b1
rapidocr-paddle<2.0.0,>=1.4.5
rapidocr_onnxruntime<2.0.0,>=1.4.4
rapid_table<2.0.0,>=1.0.3
PyYAML
openai
detectron2
paddlepaddle==3.0.0
paddlepaddle-gpu==2.6.0
matplotlib
