GenAIExamples/AudioQnA/docker_compose/amd/cpu/epyc/compose_tgi.yaml at main · letonghan/GenAIExamples · 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
# Copyright (C) 2025 Advanced Micro Devices, Inc.
# Copyright (C) 2025 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

services:
  whisper-service:
    image: ${REGISTRY:-opea}/whisper:${TAG:-latest}
    container_name: whisper-service
    ports:
      - ${WHISPER_SERVER_PORT:-7066}:7066
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
    restart: unless-stopped
  speecht5-service:
    image: ${REGISTRY:-opea}/speecht5:${TAG:-latest}
    container_name: speecht5-service
    ports:
      - ${SPEECHT5_SERVER_PORT:-7055}:7055
    ipc: host
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
    restart: unless-stopped
  tgi-service:
    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
    container_name: tgi-service
    ports:
      - ${LLM_SERVER_PORT:-3006}:80
    volumes:
      - "${MODEL_CACHE:-./data}:/data"
    shm_size: 1g
    environment:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      HF_TOKEN: ${HF_TOKEN}
      MODEL_CACHE: ${MODEL_CACHE}
      LLM_SERVER_PORT: ${LLM_SERVER_PORT}
    healthcheck:
      test:
        [
          "CMD-SHELL",
          "curl -f http://$host_ip:${LLM_SERVER_PORT}/health || exit 1",
        ]
      interval: 10s
      timeout: 10s
      retries: 100
    command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
  audioqna-epyc-backend-server:
    image: ${REGISTRY:-opea}/audioqna:${TAG:-latest}
    container_name: audioqna-epyc-backend-server
    depends_on:
      - whisper-service
      - tgi-service
      - speecht5-service
    ports:
      - "3008:8888"
    environment:
      - no_proxy=${no_proxy}
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
      - MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
      - WHISPER_SERVER_HOST_IP=${WHISPER_SERVER_HOST_IP}
      - WHISPER_SERVER_PORT=${WHISPER_SERVER_PORT}
      - LLM_SERVER_HOST_IP=${LLM_SERVER_HOST_IP}
      - LLM_SERVER_PORT=${LLM_SERVER_PORT}
      - LLM_MODEL_ID=${LLM_MODEL_ID}
      - SPEECHT5_SERVER_HOST_IP=${SPEECHT5_SERVER_HOST_IP}
      - SPEECHT5_SERVER_PORT=${SPEECHT5_SERVER_PORT}
    ipc: host
    restart: always
  audioqna-epyc-ui-server:
    image: ${REGISTRY:-opea}/audioqna-ui:${TAG:-latest}
    container_name: audioqna-epyc-ui-server
    depends_on:
      - audioqna-epyc-backend-server
    ports:
      - "5173:5173"
    environment:
      - no_proxy=${no_proxy}
      - https_proxy=${https_proxy}
      - http_proxy=${http_proxy}
      - CHAT_URL=${BACKEND_SERVICE_ENDPOINT}
    ipc: host
    restart: always

networks:
  default:
    driver: bridge