docker-compose.yml

# =============================================================================
# Docker Compose Configuration for RAG System
# =============================================================================
# This file defines the services and configuration for running the RAG system
# in a containerized environment using Docker Compose.

# =============================================================================
# COMPOSE VERSION
# =============================================================================

# Specify Docker Compose file format version
# Version 3.8 provides modern features and compatibility
version: '3.8'

# =============================================================================
# SERVICES DEFINITION
# =============================================================================

services:
  # =============================================================================
  # RAG SYSTEM SERVICE
  # =============================================================================
  
  # Main service for the RAG system application
  rag-system:
    # Build the Docker image from the current directory
    # Uses the Dockerfile in the root directory
    build: .
    
    # =============================================================================
    # NETWORK CONFIGURATION
    # =============================================================================
    
    # Port mapping: host_port:container_port
    # Maps port 8501 from the host to port 8501 in the container
    # Allows access to the Streamlit web interface from the host machine
    ports:
      - "8501:8501"
    
    # =============================================================================
    # ENVIRONMENT VARIABLES
    # =============================================================================
    
    # Set environment variables for the container
    # These override the defaults set in the Dockerfile
    environment:
      # Python path configuration
      - PYTHONPATH=/app
      
      # Streamlit server configuration
      - STREAMLIT_SERVER_PORT=8501
      - STREAMLIT_SERVER_ADDRESS=0.0.0.0
      - STREAMLIT_SERVER_HEADLESS=true
    
    # =============================================================================
    # VOLUME MOUNTING
    # =============================================================================
    
    # Mount volumes for data persistence
    # This ensures that the vector store data persists between container restarts
    volumes:
      # Mount the local vector_store directory to the container
      # Format: host_path:container_path
      - ./vector_store:/app/vector_store
    
    # =============================================================================
    # RESTART POLICY
    # =============================================================================
    
    # Container restart policy
    # unless-stopped: Restart the container unless it was explicitly stopped
    # This ensures the service stays running even after system reboots
    restart: unless-stopped
    
    # =============================================================================
    # HEALTH CHECK CONFIGURATION
    # =============================================================================
    
    # Health check to monitor service status
    healthcheck:
      # Command to test if the service is healthy
      # Uses curl to check if the Streamlit health endpoint responds
      test: ["CMD", "curl", "-f", "http://localhost:8501/_stcore/health"]
      
      # Check interval: run health check every 30 seconds
      interval: 30s
      
      # Timeout: wait up to 10 seconds for health check to complete
      timeout: 10s
      
      # Retries: attempt health check 3 times before marking as unhealthy
      retries: 3