IMPETUS-ExpertAgent/docker-compose.yml at main · Applied-Artificial-Intelligence-Eurecat/IMPETUS-ExpertAgent · 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
services:
  api:
    container_name: impetus-agent-api
    build:
      context: backend/
      dockerfile: Dockerfile
    image: impetus-agent-api:1.0
    command: uvicorn src.api.main:app --host 0.0.0.0 --port 8080 --reload --log-level debug
    ports:
      - "10009:8080/tcp"
    logging:
      driver: "json-file"
      options:
        max-size: "500M"
        max-file: "2"
    restart: always
    volumes:
      - ./backend:/app
    networks:
      - app-network
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 2s
    env_file:
      - backend/.env
    cap_add:
      - SYS_RESOURCE
    ulimits:
      memlock:
        soft: 65979612
        hard: 65979612
    runtime: nvidia
    environment:
      USE_MLOCK: 0
      NVIDIA_DRIVER_CAPABILITIES: "compute,utility"
      NVIDIA_VISIBLE_DEVICES: all

    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

  text-generation:
    image: ghcr.io/huggingface/text-generation-inference:2.2.0
    container_name: TGI
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
      - ./TGI_data:/data
    ports:
      - "10010:80"
    restart: always
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    shm_size: '1g'
    command:
      - --model-id
      - mistralai/Mistral-7B-Instruct-v0.2
      - --max-batch-size
      - "4"

    networks:
      - app-network


networks:
  app-network: