Signed-off-by: Xinyao Wang <xinyao.wang@intel.com> Signed-off-by: chensuyue <suyue.chen@intel.com>
158 lines
4.5 KiB
YAML
158 lines
4.5 KiB
YAML
# Copyright (C) 2024 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
services:
|
|
redis-vector-db:
|
|
image: redis/redis-stack:7.2.0-v9
|
|
container_name: redis-vector-db
|
|
ports:
|
|
- "6379:6379"
|
|
- "8001:8001"
|
|
dataprep-redis-service:
|
|
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
|
|
container_name: dataprep-redis-server
|
|
depends_on:
|
|
- redis-vector-db
|
|
- tei-embedding-service
|
|
ports:
|
|
- "6007:6007"
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
REDIS_URL: ${REDIS_URL}
|
|
INDEX_NAME: ${INDEX_NAME}
|
|
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
|
|
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
tei-embedding-service:
|
|
image: ${REGISTRY:-opea}/tei-gaudi:${TAG:-latest}
|
|
container_name: tei-embedding-gaudi-server
|
|
ports:
|
|
- "8090:80"
|
|
volumes:
|
|
- "./data:/data"
|
|
runtime: habana
|
|
cap_add:
|
|
- SYS_NICE
|
|
ipc: host
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
HABANA_VISIBLE_DEVICES: all
|
|
OMPI_MCA_btl_vader_single_copy_mechanism: none
|
|
MAX_WARMUP_SEQUENCE_LENGTH: 512
|
|
INIT_HCCL_ON_ACQUIRE: 0
|
|
ENABLE_EXPERIMENTAL_FLAGS: true
|
|
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
|
|
embedding:
|
|
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
|
|
container_name: embedding-tei-server
|
|
depends_on:
|
|
- tei-embedding-service
|
|
ports:
|
|
- "6000:6000"
|
|
ipc: host
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
|
|
restart: unless-stopped
|
|
retriever:
|
|
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
|
|
container_name: retriever-redis-server
|
|
depends_on:
|
|
- redis-vector-db
|
|
ports:
|
|
- "7000:7000"
|
|
ipc: host
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
REDIS_URL: ${REDIS_URL}
|
|
INDEX_NAME: ${INDEX_NAME}
|
|
restart: unless-stopped
|
|
tgi-service:
|
|
image: ghcr.io/huggingface/tgi-gaudi:2.0.1
|
|
container_name: tgi-gaudi-server
|
|
ports:
|
|
- "8005:80"
|
|
volumes:
|
|
- "./data:/data"
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
HF_HUB_DISABLE_PROGRESS_BARS: 1
|
|
HF_HUB_ENABLE_HF_TRANSFER: 0
|
|
HABANA_VISIBLE_DEVICES: all
|
|
OMPI_MCA_btl_vader_single_copy_mechanism: none
|
|
runtime: habana
|
|
cap_add:
|
|
- SYS_NICE
|
|
ipc: host
|
|
command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
|
|
llm:
|
|
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
|
|
container_name: llm-tgi-gaudi-server
|
|
depends_on:
|
|
- tgi-service
|
|
ports:
|
|
- "9000:9000"
|
|
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}
|
|
HF_HUB_DISABLE_PROGRESS_BARS: 1
|
|
HF_HUB_ENABLE_HF_TRANSFER: 0
|
|
restart: unless-stopped
|
|
chaqna-gaudi-backend-server:
|
|
image: ${REGISTRY:-opea}/chatqna-without-rerank:${TAG:-latest}
|
|
container_name: chatqna-gaudi-backend-server
|
|
depends_on:
|
|
- redis-vector-db
|
|
- tei-embedding-service
|
|
- embedding
|
|
- retriever
|
|
- tgi-service
|
|
- llm
|
|
ports:
|
|
- "8888:8888"
|
|
environment:
|
|
- no_proxy=${no_proxy}
|
|
- https_proxy=${https_proxy}
|
|
- http_proxy=${http_proxy}
|
|
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
|
|
- EMBEDDING_SERVICE_HOST_IP=${EMBEDDING_SERVICE_HOST_IP}
|
|
- RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
|
|
- LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
|
|
ipc: host
|
|
restart: always
|
|
chaqna-gaudi-ui-server:
|
|
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
|
|
container_name: chatqna-gaudi-ui-server
|
|
depends_on:
|
|
- chaqna-gaudi-backend-server
|
|
ports:
|
|
- "5173:5173"
|
|
environment:
|
|
- no_proxy=${no_proxy}
|
|
- https_proxy=${https_proxy}
|
|
- http_proxy=${http_proxy}
|
|
- CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
|
|
- UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
|
|
- GET_FILE=${DATAPREP_GET_FILE_ENDPOINT}
|
|
- DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
|
|
ipc: host
|
|
restart: always
|
|
|
|
networks:
|
|
default:
|
|
driver: bridge
|