requirements.txt

# =============================================================================
# RAG Chatbot with Vector Database - Requirements
# =============================================================================
# Production-ready dependencies for medical document analysis and Q&A

# Core ML/AI Framework
torch>=2.0.0                    # PyTorch for model inference
transformers>=4.30.0            # Hugging Face transformers
huggingface_hub>=0.20.0        # Hugging Face Hub API (for Inference API)
accelerate>=0.20.0              # Model loading optimization
safetensors>=0.3.0              # Safe model loading

# Vector Database & Embeddings
chromadb>=0.4.0                 # Vector database for fast retrieval
sentence-transformers>=2.2.0   # Semantic embeddings (all-MiniLM-L6-v2)

# Data Processing
pandas>=1.3.0                   # Data manipulation and CSV handling
numpy>=1.21.0                   # Numerical computing
scikit-learn>=1.0.0             # ML utilities and TF-IDF

# Text Analysis & Readability
textstat>=0.7.0                 # Flesch-Kincaid Grade Level calculation
nltk>=3.8.0                     # Natural language processing utilities

# Document Processing (Core)
pypdf>=3.0.0                    # PDF document parsing
python-docx>=0.8.11             # DOCX document parsing

# Optional Document Processing
rank-bm25>=0.2.2                # BM25 retrieval algorithm (alternative to TF-IDF)

# Utilities & Progress
tqdm>=4.65.0                    # Progress bars
pathlib2>=2.3.0                 # Enhanced path handling (if needed)

# Web Interface
gradio==4.44.1                  # Gradio web interface for chatbot (updated for Spaces compatibility)

# Development & Testing (Optional)
pytest>=7.0.0                   # Testing framework
black>=22.0.0                   # Code formatting
flake8>=4.0.0                   # Code linting

# Performance Monitoring (Optional)
psutil>=5.8.0                   # System resource monitoring
memory-profiler>=0.60.0         # Memory usage profiling

# =============================================================================
# Installation Notes:
# =============================================================================
# 1. Install with: pip install -r requirements.txt
# 2. For Apple Silicon: PyTorch will automatically use MPS acceleration
# 3. Optional packages can be installed separately if needed
# 4. Model files (~6GB) will be downloaded on first run
# =============================================================================