sample-managed-llm-template/compose.yaml at main · DefangSamples/sample-managed-llm-template · 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
name: managed-llm
services:
  app:
    build:
      context: ./app
      dockerfile: Dockerfile
    ports:
    - 8000:8000
    restart: always
    environment:
    - LLM_URL=http://llm/api/v1/
    - LLM_MODEL=default
    - OPENAI_API_KEY=FAKE_TOKEN
    healthcheck:
      test:
      - CMD
      - python3
      - -c
      - import sys, urllib.request; urllib.request.urlopen(sys.argv[1]).read()
      - http://localhost:8000/
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 5s
    depends_on:
    - llm
    networks:
    - default
    - private
    deploy:
      resources:
        reservations:
          cpus: '0.5'
          memory: 512M
  llm:
    x-defang-llm: true
    image: docker.io/defangio/openai-access-gateway:latest
    ports:
    - target: 80
      published: 80
      protocol: tcp
      mode: host
    networks:
    - private
    environment:
    - OPENAI_API_KEY=FAKE_TOKEN
    deploy:
      resources:
        reservations:
          cpus: '0.5'
          memory: 512M
networks:
  default: null
  private: null