visibabel/docker-compose.gpu.yml at master · horribleCodes/visibabel · 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
services:
  ollama:
    image: ollama/ollama:latest
    ports:
      - "11434:11434"
    environment:
      OLLAMA_HOST: "0.0.0.0:11434"
      OLLAMA_ORIGINS: "*"
    volumes:
      # Replace with the line below to use host's Ollama cache
      - ollama_data:/root/.ollama
      # - ${HOME}/.ollama:/root/.ollama
    healthcheck:
      test: ["CMD", "ollama", "list"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s
    restart: unless-stopped
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

  ollama-init:
    image: ollama/ollama:latest
    depends_on:
      ollama:
        condition: service_healthy
    environment:
      OLLAMA_HOST: ollama:11434
    entrypoint: ["/bin/sh", "-c"]
    command:
      - |
        ollama pull glm-ocr:latest
        ollama pull kaelri/hy-mt2:1.8b
    restart: "no"

  glm-ocr:
    build: ./glm-ocr
    ports:
      - "5002:5002"
    environment:
      GLMOCR_OLLAMA_ENDPOINT: "http://ollama:11434"
    volumes:
      - glm_ocr_models:/app/models
    extra_hosts:
      - "host.docker.internal:host-gateway"
    depends_on:
      ollama:
        condition: service_healthy
    restart: unless-stopped
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

volumes:
  ollama_data:
  glm_ocr_models: