Files
2025-04-25 23:00:36 +08:00

237 lines
7.0 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
etcd:
container_name: milvus-etcd
image: quay.io/coreos/etcd:v3.5.5
environment:
- ETCD_AUTO_COMPACTION_MODE=revision
- ETCD_AUTO_COMPACTION_RETENTION=1000
- ETCD_QUOTA_BACKEND_BYTES=4294967296
- ETCD_SNAPSHOT_COUNT=50000
volumes:
- ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/etcd:/etcd
command: etcd -advertise-client-urls=http://127.0.0.1:2379 -listen-client-urls http://0.0.0.0:2379 --data-dir /etcd
healthcheck:
test: ["CMD", "etcdctl", "endpoint", "health"]
interval: 30s
timeout: 20s
retries: 3
minio:
container_name: milvus-minio
image: minio/minio:RELEASE.2023-03-20T20-16-18Z
environment:
MINIO_ACCESS_KEY: minioadmin
MINIO_SECRET_KEY: minioadmin
ports:
- "${MINIO_PORT1:-5044}:9001"
- "${MINIO_PORT2:-5043}:9000"
volumes:
- ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/minio:/minio_data
command: minio server /minio_data --console-address ":9001"
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
interval: 30s
timeout: 20s
retries: 3
milvus-standalone:
container_name: milvus-standalone
image: milvusdb/milvus:v2.4.6
command: ["milvus", "run", "standalone"]
security_opt:
- seccomp:unconfined
environment:
ETCD_ENDPOINTS: etcd:2379
MINIO_ADDRESS: minio:9000
volumes:
- ${DOCKER_VOLUME_DIRECTORY:-.}/milvus.yaml:/milvus/configs/milvus.yaml
- ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/milvus:/var/lib/milvus
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:9091/healthz"]
interval: 30s
start_period: 90s
timeout: 20s
retries: 3
ports:
- "19530:19530"
- "${MILVUS_STANDALONE_PORT:-9091}:9091"
depends_on:
- "etcd"
- "minio"
dataprep-milvus-service:
image: ${REGISTRY:-opea}/dataprep:${TAG:-latest}
container_name: dataprep-milvus-server
ports:
- "${DATAPREP_PORT:-11101}:5000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_MILVUS"
MILVUS_HOST: ${host_ip}
MILVUS_PORT: 19530
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
EMBEDDING_MODEL_ID: ${EMBEDDING_MODEL_ID}
LOGFLAG: ${LOGFLAG}
healthcheck:
test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
interval: 10s
timeout: 5s
retries: 50
restart: unless-stopped
depends_on:
milvus-standalone:
condition: service_healthy
etcd:
condition: service_healthy
minio:
condition: service_healthy
retriever:
image: ${REGISTRY:-opea}/retriever:${TAG:-latest}
container_name: retriever-milvus-server
depends_on:
- milvus-standalone
ports:
- "7000:7000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
MILVUS_HOST: ${host_ip}
MILVUS_PORT: 19530
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_MILVUS"
restart: unless-stopped
tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
container_name: tei-embedding-server
ports:
- "6006:80"
volumes:
- "${MODEL_CACHE:-./data}:/data"
shm_size: 1g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
container_name: tei-reranking-server
ports:
- "8808:80"
volumes:
- "${MODEL_CACHE:-./data}:/data"
shm_size: 1g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
vllm-service:
image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
container_name: vllm-service
ports:
- "9009:80"
volumes:
- "${MODEL_CACHE:-./data}:/root/.cache/huggingface/hub"
shm_size: 128g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LLM_MODEL_ID: ${LLM_MODEL_ID}
VLLM_TORCH_PROFILER_DIR: "/mnt"
healthcheck:
test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80
chatqna-xeon-backend-server:
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-xeon-backend-server
depends_on:
tei-embedding-service:
condition: service_started
dataprep-milvus-service:
condition: service_healthy
retriever:
condition: service_started
tei-reranking-service:
condition: service_started
vllm-service:
condition: service_healthy
ports:
- "8888:8888"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=chatqna-xeon-backend-server
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- RETRIEVER_SERVICE_HOST_IP=retriever
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
- RERANK_SERVER_HOST_IP=tei-reranking-service
- RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-80}
- LLM_SERVER_HOST_IP=vllm-service
- LLM_SERVER_PORT=80
- LLM_MODEL=${LLM_MODEL_ID}
- LOGFLAG=${LOGFLAG}
ipc: host
restart: always
chatqna-xeon-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-xeon-ui-server
depends_on:
- chatqna-xeon-backend-server
ports:
- "5173:5173"
ipc: host
restart: always
chatqna-xeon-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: chatqna-xeon-nginx-server
depends_on:
- chatqna-xeon-backend-server
- chatqna-xeon-ui-server
ports:
- "${NGINX_PORT:-80}:80"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- FRONTEND_SERVICE_IP=chatqna-xeon-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-xeon-backend-server
- BACKEND_SERVICE_PORT=8888
- DATAPREP_SERVICE_IP=dataprep-milvus-service
- DATAPREP_SERVICE_PORT=5000
ipc: host
restart: always
networks:
default:
driver: bridge