# Core dependencies
streamlit
langchain
langchain-openai
openai>=1.10.0,<2.0.0
pydantic>=2.5.2,<3.0.0

# PDF and document processing
PyMuPDF
pdf2image
python-docx
PyPDF2

# Image processing and OCR
Pillow
pytesseract
opencv-python-headless
easyocr
paddleocr
paddlepaddle

# Machine Learning and Computer Vision
ultralytics
torch==2.1.0+cpu
torchvision==0.16.0+cpu
-f https://download.pytorch.org/whl/torch_stable.html

# Natural Language Processing
langdetect
langid

# AWS Integration
boto3

# Utility libraries
numpy
shapely
python-bidi
pyyaml
python-dotenv

# DocTR (Document Text Recognition)
python-doctr
fasttext_langdetect==1.0.5
langchain_community
opencv_contrib_python
pandas
supabase==2.5.1
tqdm==4.66.1