dependencies.txt

# Core machine learning libraries
torch>=1.10.0
transformers>=4.30.0
datasets>=2.10.0
accelerate>=0.19.0

# TinyLlama and LLM dependencies
huggingface_hub>=0.14.0
tokenizers>=0.13.0
peft>=0.4.0  # For parameter-efficient fine-tuning
bitsandbytes>=0.38.0  # For quantization support

# Web scraping and data processing
requests>=2.28.0
beautifulsoup4>=4.11.0
trafilatura>=1.4.0
lxml>=4.9.0

# PDF processing
PyPDF2>=3.0.0
pdf2image>=1.16.0
pytesseract>=0.3.10  # Requires tesseract-ocr system package

# Web application
flask>=2.2.0
flask-cors>=3.0.10
Werkzeug>=2.2.0
python-dotenv>=1.0.0

# Utilities
numpy>=1.23.0
pandas>=1.5.0
tqdm>=4.64.0
nltk>=3.7.0
rouge>=1.0.1  # For evaluation
scipy>=1.9.0
scikit-learn>=1.1.0
Pillow>=9.2.0  # For image processing

# Documentation
Markdown>=3.4.0flask_sqlalchemy
schedule