docker-compose.yml

version: '3.8'

services:
  # llama.cpp server - LLM inference engine
  llama-server:
    image: ghcr.io/ggerganov/llama.cpp:server
    container_name: intellistant-llama
    volumes:
      - ./models:/models:ro
    command: >
      --model /models/qwen2.5-coder-3b/instruct-q4_k_m.gguf
      --host 0.0.0.0
      --port 8080
      --n-gpu-layers 99
      --ctx-size 4096
      --threads 4
    ports:
      - "8080:8080"
    networks:
      - intellistant-network
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    deploy:
      resources:
        limits:
          memory: 8G
        reservations:
          memory: 4G

  # Intellistant API Server
  intellistant-api:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: intellistant-api
    depends_on:
      llama-server:
        condition: service_healthy
    environment:
      - LLAMA_HOST=llama-server
      - LLAMA_PORT=8080
      - API_PORT=8000
    ports:
      - "8000:8000"
    volumes:
      - ./logs:/app/logs
      - ./data:/app/data
    networks:
      - intellistant-network
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 10s
      timeout: 5s
      retries: 3
      start_period: 10s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 500M
        reservations:
          memory: 100M

  # Intellistant CLI (optional, for interactive use)
  intellistant-cli:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: intellistant-cli
    depends_on:
      llama-server:
        condition: service_healthy
    environment:
      - LLAMA_HOST=llama-server
      - LLAMA_PORT=8080
    command: ./intellistant_cli
    stdin_open: true
    tty: true
    networks:
      - intellistant-network
    profiles:
      - cli

networks:
  intellistant-network:
    driver: bridge

volumes:
  models:
  logs:
  data: