VxThinkerFineTunedLLMV2/docker-compose.yml at dev · prodxcloud/VxThinkerFineTunedLLMV2 · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
# docker-compose.yml - Updated with Prometheus, Grafana, and Redis
services:
  fastapi:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: va_llm_specialist
    image: ${DOCKER_IMAGE:-valtunox/va_llm_specialist:latest}
    ports:
      - "${PORT:-8746}:8746"
    networks:
      - api-network
    depends_on:
      redis:
        condition: service_healthy
    environment:
      - ENVIRONMENT=${ENVIRONMENT:-production}
      - DATABASE_HOST=db.example.com
      - DATABASE_PORT=5432
      - DATABASE_NAME=cloudsystem
      - DATABASE_USER=postgres
      - DATABASE_PASSWORD=postgres
      - GOOGLE_API_KEY=${GOOGLE_API_KEY}
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
      - APOLLO_API_KEY=${APOLLO_API_KEY}
      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
      - AWS_REGION=${AWS_REGION:-us-east-1}
      - S3_BUCKET=${S3_BUCKET}
      # Redis connection (use external or local)
      - REDIS_HOST=${REDIS_HOST:-redis}
      - REDIS_PORT=${REDIS_PORT:-6379}
      - REDIS_PASSWORD=${REDIS_PASSWORD:-}
      # Prometheus metrics
      - PROMETHEUS_ENABLED=true
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8746/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 15s
    volumes:
      - ./app/data:/app/data
    depends_on:
      - redis
    restart: unless-stopped

  redis:
    image: redis:7-alpine
    container_name: va_llm_specialist_redis
    ports:
      - "6380:6379"
    volumes:
      - redis-data:/data
    networks:
      - api-network
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 3
    restart: unless-stopped

  # Prometheus - Metrics collection
  prometheus:
    image: prom/prometheus:latest
    container_name: va_llm_specialist_prometheus
    ports:
      - "9091:9090"
    networks:
      - api-network
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
      - '--storage.tsdb.retention.time=30d'
    volumes:
      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus-data:/prometheus
    restart: unless-stopped
    depends_on:
      - fastapi

  # Grafana - Metrics visualization
  grafana:
    image: grafana/grafana:latest
    container_name: va_llm_specialist_grafana
    ports:
      - "3001:3000"
    networks:
      - api-network
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
    volumes:
      - grafana-data:/var/lib/grafana
      - ./monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ./monitoring/grafana/datasources:/etc/grafana/provisioning/datasources:ro
    restart: unless-stopped
    depends_on:
      - prometheus

volumes:
  redis-data:
  prometheus-data:
  grafana-data:

networks:
  api-network:
    driver: bridge