64 lines
1.8 KiB
YAML
64 lines
1.8 KiB
YAML
# Copyright (C) 2024 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
services:
|
|
tgi-service:
|
|
image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu
|
|
container_name: tgi-service
|
|
ports:
|
|
- "8008:80"
|
|
environment:
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
|
|
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
volumes:
|
|
- "./data:/data"
|
|
shm_size: 1g
|
|
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:
|
|
- "9000:9000"
|
|
ipc: host
|
|
environment:
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
|
|
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
restart: unless-stopped
|
|
translation-xeon-backend-server:
|
|
image: ${REGISTRY:-opea}/translation:${TAG:-latest}
|
|
container_name: translation-xeon-backend-server
|
|
depends_on:
|
|
- tgi-service
|
|
- llm
|
|
ports:
|
|
- "8888:8888"
|
|
environment:
|
|
- https_proxy=${https_proxy}
|
|
- http_proxy=${http_proxy}
|
|
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
|
|
- LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
|
|
ipc: host
|
|
restart: always
|
|
translation-xeon-ui-server:
|
|
image: ${REGISTRY:-opea}/translation-ui:${TAG:-latest}
|
|
container_name: translation-xeon-ui-server
|
|
depends_on:
|
|
- translation-xeon-backend-server
|
|
ports:
|
|
- "5173:5173"
|
|
environment:
|
|
- https_proxy=${https_proxy}
|
|
- http_proxy=${http_proxy}
|
|
- BASE_URL=${BACKEND_SERVICE_ENDPOINT}
|
|
ipc: host
|
|
restart: always
|
|
networks:
|
|
default:
|
|
driver: bridge
|