workerAI/docker-compose.yml at main · mtecnic/workerAI · 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
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
version: '3.8'

services:
  # vLLM Service - LLM inference server
  vllm:
    image: vllm/vllm-openai:latest
    container_name: workerai-vllm
    ports:
      - "8000:8000"
    volumes:
      - ./models:/root/.cache/huggingface
    environment:
      - HUGGING_FACE_HUB_TOKEN=${HUGGING_FACE_HUB_TOKEN:-}
    command: >
      --model meta-llama/Llama-3-70B-Instruct
      --host 0.0.0.0
      --port 8000
      --enable-auto-tool-choice
      --tool-call-parser hermes
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s
    networks:
      - workerai-network

  # workerAI Application
  workerai:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: workerai-app
    ports:
      - "8001:8001"  # Prometheus metrics
      - "8002:8002"  # Health checks
    volumes:
      - ./data:/app/data
      - ./workspace:/app/workspace
      - ./logs:/app/logs
      - ./models:/app/models
    environment:
      # vLLM Configuration
      - VLLM_BASE_URL=http://vllm:8000/v1
      - VLLM_API_KEY=EMPTY
      - VLLM_MODEL_NAME=meta-llama/Llama-3-70B-Instruct

      # Application Configuration
      - ENVIRONMENT=production
      - LOG_LEVEL=INFO
      - LOG_JSON_FORMAT=true
      - VERBOSE=false

      # Timeouts and Limits
      - LLM_TIMEOUT_SECONDS=60
      - LLM_CONNECT_TIMEOUT=10
      - LLM_READ_TIMEOUT=120
      - LLM_MAX_RETRIES=3
      - MAX_ITERATIONS=20

      # Circuit Breaker
      - CIRCUIT_BREAKER_FAIL_MAX=5
      - CIRCUIT_BREAKER_TIMEOUT_SECONDS=60

      # Web Scraping
      - WEB_REQUESTS_PER_MINUTE=30
      - WEB_REQUESTS_PER_DOMAIN_PER_MINUTE=10
      - PLAYWRIGHT_HEADLESS=true

      # Paths
      - WORKING_DIRECTORY=/app/workspace
      - CHROMA_PERSIST_DIRECTORY=/app/data/chroma_db
      - EMBEDDING_MODEL_CACHE_DIR=/app/models
      - LOG_FILE=/app/logs/workerai.log

      # Email (optional - set if using email tools)
      - SMTP_SERVER=${SMTP_SERVER:-smtp.gmail.com}
      - SMTP_PORT=${SMTP_PORT:-587}
      - SMTP_USERNAME=${SMTP_USERNAME:-}
      - SMTP_PASSWORD=${SMTP_PASSWORD:-}
      - IMAP_SERVER=${IMAP_SERVER:-imap.gmail.com}
      - IMAP_PORT=${IMAP_PORT:-993}
      - IMAP_USERNAME=${IMAP_USERNAME:-}
      - IMAP_PASSWORD=${IMAP_PASSWORD:-}
    depends_on:
      vllm:
        condition: service_healthy
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8002/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s
    networks:
      - workerai-network

  # Prometheus (optional - for metrics collection)
  prometheus:
    image: prom/prometheus:latest
    container_name: workerai-prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus-data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
    networks:
      - workerai-network
    profiles:
      - monitoring

  # Grafana (optional - for metrics visualization)
  grafana:
    image: grafana/grafana:latest
    container_name: workerai-grafana
    ports:
      - "3000:3000"
    volumes:
      - grafana-data:/var/lib/grafana
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_PASSWORD:-admin}
    networks:
      - workerai-network
    profiles:
      - monitoring

networks:
  workerai-network:
    driver: bridge

volumes:
  prometheus-data:
  grafana-data: