plano/demos/function_calling/docker-compose.yaml

x-variables: &common-vars
  environment:
    - MODE=${MODE:-cloud}  # Set the default mode to 'cloud', others values are local-gpu, local-cpu


services:

  arch:
    build:
      context: ../../
      dockerfile: arch/Dockerfile
    ports:
      - "10000:10000"
      - "19901:9901"
    volumes:
      - ./generated/envoy.yaml:/etc/envoy/envoy.yaml
      - /etc/ssl/cert.pem:/etc/ssl/cert.pem
      - ./arch_log:/var/log/
      - ./arch_config.yaml:/root/arch_config.yaml
    depends_on:
      # config_generator:
      #   condition: service_completed_successfully
      model_server:
        condition: service_healthy
    environment:
      - LOG_LEVEL=debug

  model_server:
    build:
      context: ../../model_server
      dockerfile: Dockerfile
    ports:
      - "18081:80"
    healthcheck:
        test: ["CMD", "curl" ,"http://localhost/healthz"]
        interval: 5s
        retries: 20
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
      - ./arch_config.yaml:/root/arch_config.yaml
    << : *common-vars
    environment:
      - OLLAMA_ENDPOINT=${OLLAMA_ENDPOINT:-host.docker.internal}
      - FC_URL=${FC_URL:-empty}
      - OLLAMA_MODEL=Arch-Function-Calling-3B-Q4_K_M
      - MODE=${MODE:-cloud}
      # uncomment following line to use ollama endpoint that is hosted by docker
      # - OLLAMA_ENDPOINT=ollama
      # - OLLAMA_MODEL=Arch-Function-Calling-1.5B:Q4_K_M
  api_server:
    build:
      context: api_server
      dockerfile: Dockerfile
    ports:
      - "18083:80"
    healthcheck:
        test: ["CMD", "curl" ,"http://localhost:80/healthz"]
        interval: 5s
        retries: 20

  ollama:
    image: ollama/ollama
    container_name: ollama
    volumes:
      - ./ollama:/root/.ollama
    restart: unless-stopped
    ports:
      - '11434:11434'
    profiles:
      - manual

  open_webui:
    image: ghcr.io/open-webui/open-webui:${WEBUI_DOCKER_TAG-main}
    container_name: open-webui
    volumes:
      - ./open-webui:/app/backend/data
    # depends_on:
      # - ollama
    ports:
      - 18090:8080
    environment:
      - OLLAMA_BASE_URL=http://${OLLAMA_ENDPOINT:-host.docker.internal}:11434
      - WEBUI_AUTH=false
    extra_hosts:
      - host.docker.internal:host-gateway
    restart: unless-stopped
    profiles:
      - monitoring

  chatbot_ui:
    build:
      context: ../../chatbot_ui
      dockerfile: Dockerfile
    ports:
      - "18080:8080"
    environment:
      - OPENAI_API_KEY=${OPENAI_API_KEY:?error}
      - MISTRAL_API_KEY=${MISTRAL_API_KEY:?error}
      - CHAT_COMPLETION_ENDPOINT=http://arch:10000/v1

  prometheus:
    image: prom/prometheus
    container_name: prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yaml'
    ports:
      - 9090:9090
    restart: unless-stopped
    volumes:
      - ./prometheus:/etc/prometheus
      - ./prom_data:/prometheus
    profiles:
      - monitoring

  grafana:
    image: grafana/grafana
    container_name: grafana
    ports:
      - 3000:3000
    restart: unless-stopped
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=grafana
    volumes:
      - ./grafana:/etc/grafana/provisioning/datasources
      - ./grafana/dashboard.yaml:/etc/grafana/provisioning/dashboards/main.yaml
      - ./grafana/dashboards:/var/lib/grafana/dashboards
    profiles:
      - monitoring