FAQ-Assistant/docker-compose.yaml at main · yrarjun59/FAQ-Assistant · 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
services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD-SHELL", "ollama list || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s

  backend:
    # build: ./backend
    image: yrarjun59/faq-backend:v2
    container_name: backend
    working_dir: /app
    environment:
      - OLLAMA_BASE_URL=http://ollama:11434
      - CACHE_DIR=/app/fastembed_cache
      - LLM_MODEL=${LLM_MODEL:-llama3.2:1b}
    ports:
      - "8000:8000"
    depends_on:
      ollama:
        condition: service_healthy
    volumes:
      - ./backend/vector_db:/app/vector_db
      - ./backend/fastembed_cache:/app/fastembed_cache
    healthcheck:
      test: ["CMD-SHELL", "python3 -c \"import urllib.request; urllib.request.urlopen('http://localhost:8000/health')\""]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 60s
    # develop:
    #   watch:
    #     - action : sync
    #       path: ./backend
    #       target: /app
    #       ignore:
    #         - vector_db/
    #         - fastembed_cache/
    #         - __pycache__/


  stream:
    # build: ./stream
    image: yrarjun59/faq-frontend:v2
    container_name: stream
    working_dir: /app
    environment:
      - STELLA_API_URL=http://backend:8000
    ports:
      - "8501:8501"
    depends_on:
        backend:
          condition: service_healthy
    volumes:
      - ./stream:/app/stream
    # develop:
    #   watch:
    #     - action: sync
    #       path: ./stream
    #       target: /app
    #       ignore:
    #         - __pycache__/
    #         - "*.pyc"

volumes:
  ollama_data:
  vector_db:
  fastembed_cache: