docker-compose.yml

version: '3.8'

services:
  # Ollama service for local LLM inference
  ollama:
    image: ollama/ollama:latest
    container_name: rag-ollama
    volumes:
      - ollama_data:/root/.ollama
    ports:
      - "11434:11434"
    environment:
      - OLLAMA_HOST=0.0.0.0
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
      interval: 30s
      timeout: 10s
      retries: 5
    restart: unless-stopped
    # Uncomment for GPU support
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu]

  # RAG Application
  rag-app:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: rag-terminal
    ports:
      - "7860:7860"
    volumes:
      # Persist embeddings and vector store
      - ./rag_data:/app/rag_data
      - ./.embedding_cache:/app/.embedding_cache
      # Mount documents directory (read-only)
      - ~/Documents/Books:/app/documents:ro
    environment:
      # Ollama configuration
      - OLLAMA_BASE_URL=http://ollama:11434
      - OLLAMA_MODEL=${OLLAMA_MODEL:-smollm2:360m}
      - OLLAMA_MODEL_CLOUD=${OLLAMA_MODEL_CLOUD:-gpt-oss:20b-cloud}
      - OLLAMA_API_KEY=${OLLAMA_API_KEY}
      
      # Embedding configuration
      - EMBEDDING_METHOD=${EMBEDDING_METHOD:-huggingface}
      - HF_TOKEN=${HF_TOKEN}
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - VOYAGE_API_KEY=${VOYAGE_API_KEY}
      - HF_EMBEDDING_MODEL=${HF_EMBEDDING_MODEL:-BAAI/bge-base-en-v1.5}
      
      # Document configuration
      - SAMPLE_DOCUMENT_PATH=${SAMPLE_DOCUMENT_PATH:-/app/documents/Atomic_Habits_James_Clear.pdf}
      - SAVE_DIR=/app/rag_data
      - CHUNK_SIZE=${CHUNK_SIZE:-1000}
      - CHUNK_OVERLAP=${CHUNK_OVERLAP:-200}
      - TOP_K=${TOP_K:-5}
      
      # Token limits
      - TOKEN_LIMIT_BASE=${TOKEN_LIMIT_BASE:-512}
      - TOKEN_LIMIT_PER_SOURCE=${TOKEN_LIMIT_PER_SOURCE:-200}
      - TOKEN_LIMIT_MAX=${TOKEN_LIMIT_MAX:-2048}
      
      # Gradio configuration
      - GRADIO_SERVER_NAME=0.0.0.0
      - GRADIO_SERVER_PORT=7860
      - GRADIO_SHARE=${GRADIO_SHARE:-false}
    depends_on:
      ollama:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:7860/"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s
    restart: unless-stopped

volumes:
  ollama_data:
    driver: local

networks:
  default:
    name: rag-network