radis/docker-compose.dev.yml at main · openradx/radis · 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
x-app: &default-app
  build:
    target: development
  pull_policy: build
  environment:
    DJANGO_INTERNAL_IPS: ${DJANGO_INTERNAL_IPS:?}
    DJANGO_SETTINGS_MODULE: radis.settings.development
    FORCE_DEBUG_TOOLBAR: ${FORCE_DEBUG_TOOLBAR:-true}
    REMOTE_DEBUGGING_ENABLED: ${REMOTE_DEBUGGING_ENABLED:-false}
    REMOTE_DEBUGGING_PORT: ${REMOTE_DEBUGGING_PORT:-5678}
  develop:
    watch:
      - action: sync
        path: .
        target: /app
        ignore:
          - .git/
          - .venv/
          - node_modules/
      - action: rebuild
        path: ./pyproject.toml

x-llm: &llm
  hostname: llm.local
  ports:
    - ${LLM_SERVICE_DEV_PORT:-8080}:8080
  environment:
    HF_TOKEN: ${HF_TOKEN:-}
    HTTP_PROXY: ${HTTP_PROXY:-}
    HTTPS_PROXY: ${HTTPS_PROXY:-}
    LLAMA_ARG_HF_REPO: ${LLM_MODEL_NAME}
    LLAMA_ARG_CTX_SIZE: 8192
    LLAMA_ARG_N_PARALLEL: 2
    LLAMA_ARG_ENDPOINT_METRICS: 1
    LLAMA_ARG_PORT: 8080
    LLAMA_ARG_N_GPU_LAYERS: 99
    NO_PROXY: ${NO_PROXY:-}
  volumes:
    - models_data:/models

services:
  init:
    <<: *default-app
    profiles:
      - never

  web:
    <<: *default-app
    image: radis_dev-web:latest
    ports:
      - ${WEB_DEV_PORT:-8000}:8000
      - ${REMOTE_DEBUGGING_PORT:-5678}:5678
    command: >
      bash -c "
        wait-for-it -s postgres.local:5432 -t 60 &&
        ./manage.py migrate &&
        ./manage.py create_superuser &&
        ./manage.py create_example_users &&
        ./manage.py create_example_groups &&
        ./manage.py populate_example_reports --lng ${EXAMPLE_REPORTS_LANGUAGE:-en} &&
        ./manage.py retry_stalled_jobs &&
        ./manage.py runserver 0.0.0.0:8000
      "
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health/"]

  default_worker:
    <<: *default-app
    image: radis_dev-default_worker:latest
    command: >
      bash -c "
        wait-for-it -s postgres.local:5432 -t 60 &&
        ./manage.py bg_worker -l debug -q default --autoreload
      "

  llm_worker:
    <<: *default-app
    image: radis_dev-llm_worker:latest
    command: >
      bash -c "
        wait-for-it -s postgres.local:5432 -t 60 &&
        ./manage.py bg_worker -l debug -q llm --autoreload
      "

  postgres:
    environment:
      POSTGRES_PASSWORD: postgres
    ports:
      - ${POSTGRES_DEV_PORT:-5432}:5432

  llm_cpu:
    <<: *llm
    image: ghcr.io/ggml-org/llama.cpp:server-b5170
    profiles:
      - cpu

  llm_gpu:
    <<: *llm
    image: ghcr.io/ggml-org/llama.cpp:server-cuda-b5170
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities:
                - gpu
    profiles:
      - gpu

volumes:
  models_data: