Files
GenAIExamples/AudioQnA/docker_compose/intel/cpu/xeon/compose.yaml
lvliang-intel 0306c620b5 Update TGI CPU image to latest official release 2.4.0 (#1035)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-11-04 11:28:43 +08:00

98 lines
2.6 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
whisper-service:
image: ${REGISTRY:-opea}/whisper:${TAG:-latest}
container_name: whisper-service
ports:
- "7066:7066"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
restart: unless-stopped
asr:
image: ${REGISTRY:-opea}/asr:${TAG:-latest}
container_name: asr-service
ports:
- "3001:9099"
ipc: host
environment:
ASR_ENDPOINT: ${ASR_ENDPOINT}
speecht5-service:
image: ${REGISTRY:-opea}/speecht5:${TAG:-latest}
container_name: speecht5-service
ports:
- "7055:7055"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
restart: unless-stopped
tts:
image: ${REGISTRY:-opea}/tts:${TAG:-latest}
container_name: tts-service
ports:
- "3002:9088"
ipc: host
environment:
TTS_ENDPOINT: ${TTS_ENDPOINT}
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-service
ports:
- "3006:80"
volumes:
- "./data:/data"
shm_size: 1g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
llm:
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-server
depends_on:
- tgi-service
ports:
- "3007:9000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
audioqna-xeon-backend-server:
image: ${REGISTRY:-opea}/audioqna:${TAG:-latest}
container_name: audioqna-xeon-backend-server
depends_on:
- asr
- llm
- tts
ports:
- "3008:8888"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- ASR_SERVICE_HOST_IP=${ASR_SERVICE_HOST_IP}
- ASR_SERVICE_PORT=${ASR_SERVICE_PORT}
- LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
- LLM_SERVICE_PORT=${LLM_SERVICE_PORT}
- TTS_SERVICE_HOST_IP=${TTS_SERVICE_HOST_IP}
- TTS_SERVICE_PORT=${TTS_SERVICE_PORT}
ipc: host
restart: always
networks:
default:
driver: bridge