requirements.txt

# =============================================================================
# RAG System Dependencies for Hugging Face Spaces Deployment
# =============================================================================
# This file contains all the Python packages required for the RAG system
# to function properly in a Docker container environment.

# =============================================================================
# CORE WEB FRAMEWORK
# =============================================================================

# Streamlit - Modern web framework for data applications
# Provides the interactive web interface for the RAG system
streamlit==1.28.1

# =============================================================================
# DEEP LEARNING & AI FRAMEWORKS
# =============================================================================

# PyTorch - Deep learning framework for model inference
# Required for running the language models (Qwen, distilgpt2)
torch==2.1.0

# Transformers - Hugging Face library for pre-trained models
# Provides access to language models and tokenizers
transformers>=4.36.0

# =============================================================================
# EMBEDDING & VECTOR SEARCH
# =============================================================================

# Sentence Transformers - Library for sentence embeddings
# Used for converting text to vector representations
sentence-transformers==2.2.2

# FAISS CPU - Facebook AI Similarity Search for vector indexing
# Provides efficient similarity search for document retrieval
faiss-cpu==1.7.4

# =============================================================================
# MACHINE LEARNING & DATA PROCESSING
# =============================================================================

# Scikit-learn - Machine learning utilities
# Used for data preprocessing and BM25 implementation
scikit-learn==1.3.2

# Rank BM25 - Implementation of BM25 ranking algorithm
# Provides keyword-based sparse retrieval functionality
rank-bm25==0.2.2

# =============================================================================
# DOCUMENT PROCESSING
# =============================================================================

# PyPDF - Modern PDF processing library
# Used for extracting text and metadata from PDF documents
pypdf==3.17.1

# =============================================================================
# DATA MANIPULATION & ANALYSIS
# =============================================================================

# Pandas - Data manipulation and analysis library
# Used for data structure management and processing
pandas==2.1.3

# NumPy - Numerical computing library
# Provides mathematical operations and array handling
numpy==1.24.3

# =============================================================================
# UTILITIES & LOGGING
# =============================================================================

# Loguru - Advanced logging library
# Provides structured logging with better formatting and features
loguru==0.7.2

# TQDM - Progress bar library
# Shows progress for long-running operations
tqdm==4.66.1

# =============================================================================
# MODEL OPTIMIZATION & DEPLOYMENT
# =============================================================================

# Accelerate - Hugging Face library for model optimization
# Helps with model loading and inference optimization
accelerate==0.24.1

# Hugging Face Hub - Library for accessing Hugging Face models
# Provides utilities for downloading and managing models
huggingface-hub==0.19.4

# =============================================================================
# GUARD RAIL DEPENDENCIES
# =============================================================================

# Additional libraries for enhanced security and validation
# These are optional but recommended for production deployments