WriteBot/docker-compose.gpu.yml at main · ariedotcodotnz/WriteBot · 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
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
# Docker Compose for WriteBot with GPU support
# Optimized for NVIDIA RTX 50/40/30 series GPUs
#
# Prerequisites:
# 1. Install NVIDIA Container Toolkit: https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html
# 2. Verify with: docker run --rm --gpus all nvidia/cuda:12.3.1-base-ubuntu22.04 nvidia-smi
#
# Usage:
#   docker-compose -f docker-compose.gpu.yml up -d
#
# To use with main docker-compose.yml (override):
#   docker-compose -f docker-compose.yml -f docker-compose.gpu.yml up -d

version: '3.8'

services:
  writebot:
    build:
      context: .
      dockerfile: Dockerfile.gpu
    container_name: writebot-app-gpu
    restart: unless-stopped
    ports:
      - "5000:5000"
    environment:
      - FLASK_APP=webapp.app:app
      - FLASK_ENV=production
      - SECRET_KEY=${SECRET_KEY}
      - DATABASE_URL=${DATABASE_URL:-sqlite:///instance/writebot.db}
      - CACHE_TYPE=${CACHE_TYPE:-simple}
      - RATELIMIT_STORAGE_URL=${RATELIMIT_STORAGE_URL:-memory://}
      # GPU-specific environment variables
      - TF_CPP_MIN_LOG_LEVEL=2
      - TF_FORCE_GPU_ALLOW_GROWTH=true
      - TF_ENABLE_TF32=1
      - CUDA_VISIBLE_DEVICES=0
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
    volumes:
      # Persist database and uploads
      - ./webapp/instance:/app/webapp/instance
      - ./webapp/logs:/app/webapp/logs
      - ./model/data:/app/model/data
    depends_on:
      - redis
    networks:
      - writebot-network
    # GPU configuration for Docker
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    # Alternative GPU configuration (for older Docker versions)
    # runtime: nvidia
    healthcheck:
      test: ["CMD", "python", "-c", "import requests; requests.get('http://localhost:5000/api/health', timeout=5)"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s

  # Celery worker with GPU support
  celery-worker:
    build:
      context: .
      dockerfile: Dockerfile.gpu
    container_name: writebot-celery-worker-gpu
    restart: unless-stopped
    command: celery -A webapp.celery_app:celery_app worker --loglevel=info --concurrency=1 --max-tasks-per-child=50
    environment:
      - FLASK_APP=webapp.app:app
      - FLASK_ENV=production
      - SECRET_KEY=${SECRET_KEY}
      - DATABASE_URL=${DATABASE_URL:-sqlite:///instance/writebot.db}
      - REDIS_URL=redis://redis:6379/0
      - CELERY_BROKER_URL=redis://redis:6379/0
      - CELERY_RESULT_BACKEND=redis://redis:6379/0
      - TF_CPP_MIN_LOG_LEVEL=2
      - TF_FORCE_GPU_ALLOW_GROWTH=true
      - TF_ENABLE_TF32=1
      - CUDA_VISIBLE_DEVICES=0
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
    volumes:
      - ./webapp/instance:/app/webapp/instance
      - ./webapp/logs:/app/webapp/logs
      - ./model/data:/app/model/data
      - task-results:/tmp/writebot_task_results
    depends_on:
      - redis
    networks:
      - writebot-network
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
        limits:
          memory: 8G

  # Celery Flower for monitoring
  celery-flower:
    build:
      context: .
      dockerfile: Dockerfile.gpu
    container_name: writebot-celery-flower
    restart: unless-stopped
    command: celery -A webapp.celery_app:celery_app flower --port=5555
    ports:
      - "5555:5555"
    environment:
      - REDIS_URL=redis://redis:6379/0
      - CELERY_BROKER_URL=redis://redis:6379/0
      - CELERY_RESULT_BACKEND=redis://redis:6379/0
    depends_on:
      - redis
      - celery-worker
    networks:
      - writebot-network

  redis:
    image: redis:7-alpine
    container_name: writebot-redis
    restart: unless-stopped
    ports:
      - "6379:6379"
    volumes:
      - redis-data:/data
    networks:
      - writebot-network
    command: redis-server --appendonly yes --maxmemory 512mb --maxmemory-policy allkeys-lru
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 3s
      retries: 3

  nginx:
    image: nginx:alpine
    container_name: writebot-nginx
    restart: unless-stopped
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./deploy/nginx.conf:/etc/nginx/nginx.conf:ro
      - ./deploy/ssl:/etc/nginx/ssl:ro
      - ./webapp/static:/usr/share/nginx/html/static:ro
    depends_on:
      - writebot
    networks:
      - writebot-network
    healthcheck:
      test: ["CMD", "nginx", "-t"]
      interval: 30s
      timeout: 10s
      retries: 3

volumes:
  redis-data:
    driver: local
  task-results:
    driver: local

networks:
  writebot-network:
    driver: bridge