# =============================================================================
# RAG System Dockerfile for Hugging Face Spaces
# =============================================================================
# This Dockerfile creates a containerized environment for the RAG system
# with all necessary dependencies and configurations for deployment.

# =============================================================================
# BASE IMAGE SELECTION
# =============================================================================

# Use Python 3.10 slim image for optimal size and compatibility
# Slim images contain only essential packages, reducing container size
FROM python:3.10-slim

# =============================================================================
# WORKING DIRECTORY SETUP
# =============================================================================

# Set the working directory inside the container
# All subsequent commands will be executed from this directory
WORKDIR /app
ENV PYTHONUNBUFFERED=1 \
    PORT=8000 \
    HF_HOME=/home/user/huggingface

# =============================================================================
# SYSTEM DEPENDENCIES INSTALLATION
# =============================================================================

# Install system-level dependencies required for Python packages
# build-essential: Required for compiling some Python packages
# curl: Used for health checks and potential downloads
RUN apt-get update && apt-get install -y \
    build-essential \
    curl \
    && rm -rf /var/lib/apt/lists/*

# =============================================================================
# PYTHON DEPENDENCIES INSTALLATION
# =============================================================================

# Copy requirements file first for better Docker layer caching
# This ensures that dependencies are only reinstalled if requirements.txt changes
COPY requirements.txt .

# Install Python dependencies with optimized settings
# --no-cache-dir: Reduces image size by not caching downloaded packages
# --upgrade pip: Ensures we have the latest pip version
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt

# =============================================================================
# APPLICATION FILES COPY
# =============================================================================

# Copy all application files to the container
# This includes Python scripts, configuration files, and documentation
COPY . .

# =============================================================================
# DIRECTORY CREATION
# =============================================================================

# Create vector store directory for FAISS index persistence
# This directory will store the vector embeddings and metadata
RUN mkdir -p vector_store

# =============================================================================
# TEST DATA SETUP
# =============================================================================

# Copy all PDF documents for testing and demonstration
# These files will be automatically loaded when the system starts
COPY *.pdf /app/

# =============================================================================
# ENVIRONMENT VARIABLES CONFIGURATION
# =============================================================================

# Set Python path to include the application directory
ENV PYTHONPATH=/app

# Streamlit server configuration for containerized deployment
ENV STREAMLIT_SERVER_PORT=8501
ENV STREAMLIT_SERVER_ADDRESS=0.0.0.0
ENV STREAMLIT_SERVER_HEADLESS=true
ENV STREAMLIT_SERVER_ENABLE_CORS=false
ENV STREAMLIT_SERVER_ENABLE_XSRF_PROTECTION=false
ENV STREAMLIT_LOGGER_LEVEL=debug

# =============================================================================
# NETWORK CONFIGURATION
# =============================================================================

# Expose port 8501 for Streamlit web interface
# This port will be accessible from outside the container
EXPOSE 8501

# =============================================================================
# HEALTH CHECK CONFIGURATION
# =============================================================================

# Health check to monitor application status
# Uses curl to check if the Streamlit health endpoint is responding
HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health

# =============================================================================
# APPLICATION STARTUP
# =============================================================================

# Start the Streamlit application with proper configuration
# --server.port: Specifies the port for the web interface
# --server.address: Binds to all network interfaces for container access
CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]