inferno-ai 0.10.3

Enterprise AI/ML model runner with automatic updates, real-time monitoring, and multi-interface support
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
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147

version: '3.8'

services:
  # Inferno AI/ML inference server
  inferno:
    build:
      context: ..
      dockerfile: Dockerfile
    container_name: inferno-server
    ports:
      - "8080:8080"    # HTTP API
      - "9090:9090"    # Prometheus metrics
    volumes:
      - ./models:/app/models
      - ./config:/app/config
      - ./logs:/app/logs
    environment:
      - INFERNO_LOG_LEVEL=info
      - INFERNO_LOG_FORMAT=json
      - INFERNO_MODELS_DIR=/app/models
      - INFERNO_CACHE_DIR=/app/cache
      - INFERNO_BIND_ADDRESS=0.0.0.0
      - INFERNO_PORT=8080
      - INFERNO_PROMETHEUS_ENABLED=true
      - INFERNO_PROMETHEUS_PORT=9090
      - INFERNO_OTEL_ENABLED=true
      - INFERNO_OTEL_ENDPOINT=http://jaeger:14268/api/traces
      - INFERNO_GRAFANA_ENABLED=true
      - INFERNO_GRAFANA_ENDPOINT=http://grafana:3000
    networks:
      - inferno-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  # Prometheus for metrics collection
  prometheus:
    image: prom/prometheus:latest
    container_name: inferno-prometheus
    ports:
      - "9091:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--storage.tsdb.retention.time=200h'
      - '--web.enable-lifecycle'
    networks:
      - inferno-network
    restart: unless-stopped

  # Grafana for visualization
  grafana:
    image: grafana/grafana:latest
    container_name: inferno-grafana
    ports:
      - "3000:3000"
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning
      - ./grafana/dashboards:/var/lib/grafana/dashboards
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin
      - GF_USERS_ALLOW_SIGN_UP=false
    networks:
      - inferno-network
    restart: unless-stopped
    depends_on:
      - prometheus

  # Jaeger for distributed tracing
  jaeger:
    image: jaegertracing/all-in-one:latest
    container_name: inferno-jaeger
    ports:
      - "16686:16686"  # Jaeger UI
      - "14268:14268"  # Jaeger collector HTTP
      - "14250:14250"  # Jaeger collector gRPC
    environment:
      - COLLECTOR_OTLP_ENABLED=true
    networks:
      - inferno-network
    restart: unless-stopped

  # Redis for caching (optional)
  redis:
    image: redis:alpine
    container_name: inferno-redis
    ports:
      - "6379:6379"
    volumes:
      - redis_data:/data
    networks:
      - inferno-network
    restart: unless-stopped
    command: redis-server --appendonly yes

  # Load balancer (for multiple Inferno instances)
  nginx:
    image: nginx:alpine
    container_name: inferno-nginx
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./nginx.conf:/etc/nginx/nginx.conf
      - ./ssl:/etc/nginx/ssl
    networks:
      - inferno-network
    restart: unless-stopped
    depends_on:
      - inferno

  # Model downloader (init container)
  model-downloader:
    image: alpine/curl:latest
    container_name: inferno-model-downloader
    volumes:
      - ./models:/models
    command: |
      sh -c "
        echo 'Downloading sample models...'
        mkdir -p /models
        # Download a sample GGUF model (replace with actual model URLs)
        # curl -L -o /models/llama-2-7b-chat.gguf 'https://example.com/llama-2-7b-chat.gguf'
        echo 'Model download complete'
      "
    networks:
      - inferno-network

volumes:
  prometheus_data:
  grafana_data:
  redis_data:

networks:
  inferno-network:
    driver: bridge