requirements.txt

# Maternal Health RAG Chatbot Requirements

# Core libraries for document processing and RAG
unstructured[local-inference]>=0.14.9 # For local, high-quality PDF processing
pdfplumber>=0.11.0
pillow>=10.0.0
langchain-community>=0.0.38
langchain-text-splitters>=0.0.1
sentence-transformers>=2.2.2
faiss-cpu>=1.7.4
accelerate>=0.24.0
gradio>=4.0.0
groq>=0.4.0

# Data handling and utilities
pandas>=2.0.0
beautifulsoup4>=4.12.0
python-dotenv>=1.0.0
tqdm>=4.66.0

# Core ML/AI libraries
numpy>=1.24.0
scikit-learn>=1.3.0
openai>=1.0.0
langchain>=0.1.0
langchain-openai>=0.0.5
torch>=2.0.0
torchvision

# Testing and code quality
pytest>=7.0.0
pytest-cov>=4.0.0
black>=23.0.0
flake8>=6.0.0

# Web app and visualization
streamlit>=1.28.0
pymupdf>=1.23.0
tabulate>=0.9.0
openpyxl>=3.1.0
matplotlib>=3.7.0
requests>=2.31.0
aiohttp>=3.9.0

# Additional dependencies for embedding evaluation
# python-magic-bin>=0.4.14 # Removed due to incompatibility on macOS ARM
# spacy>=3.7.0
# scispacy>=0.5.0

# For API
fastapi
uvicorn[standard]
python-dotenv

# For PDF processing
pypdfium2

# New dependencies
markdown
tenacity