67 lines
1.9 KiB
YAML
67 lines
1.9 KiB
YAML
# docker-compose.yml — md-vector-db 本地开发与生产部署
|
||
version: "3.8"
|
||
|
||
services:
|
||
md-vector-db:
|
||
build:
|
||
context: .
|
||
dockerfile: Dockerfile
|
||
image: md-vector-db:latest
|
||
container_name: md-vector-db
|
||
restart: unless-stopped
|
||
ports:
|
||
- "${MD_VECTOR_PORT:-8000}:8000"
|
||
volumes:
|
||
# 持久化 ChromaDB 数据
|
||
- ./data:/app/data
|
||
# 挂载配置文件
|
||
- ./config.yaml:/app/config.yaml:ro
|
||
# 挂载待入库文档目录
|
||
- ${MD_VECTOR_DOCS_DIR:-./md_docs}:/app/md_docs:ro
|
||
environment:
|
||
- MD_VECTOR_CONFIG=/app/config.yaml
|
||
- MD_VECTOR_DB_DATA_DIR=/app/data
|
||
- MD_VECTOR_API_KEY=${MD_VECTOR_API_KEY:-}
|
||
- EMBED_API_KEY=${EMBED_API_KEY:-}
|
||
- CORS_ORIGINS=${CORS_ORIGINS:-http://localhost:3000}
|
||
- MAX_REQUEST_BODY_SIZE=${MAX_REQUEST_BODY_SIZE:-10485760}
|
||
env_file:
|
||
- .env
|
||
healthcheck:
|
||
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/api/v1/health')"]
|
||
interval: 30s
|
||
timeout: 10s
|
||
retries: 3
|
||
start_period: 60s
|
||
|
||
# 可选：GPU 版本（需 nvidia-container-toolkit）
|
||
md-vector-db-gpu:
|
||
profiles: ["gpu"]
|
||
build:
|
||
context: .
|
||
dockerfile: Dockerfile
|
||
image: md-vector-db:latest
|
||
container_name: md-vector-db-gpu
|
||
restart: unless-stopped
|
||
ports:
|
||
- "${MD_VECTOR_PORT:-8000}:8000"
|
||
volumes:
|
||
- ./data:/app/data
|
||
- ./config.yaml:/app/config.yaml:ro
|
||
- ${MD_VECTOR_DOCS_DIR:-./md_docs}:/app/md_docs:ro
|
||
environment:
|
||
- MD_VECTOR_CONFIG=/app/config.yaml
|
||
- MD_VECTOR_DB_DATA_DIR=/app/data
|
||
- MD_VECTOR_API_KEY=${MD_VECTOR_API_KEY:-}
|
||
- EMBED_API_KEY=${EMBED_API_KEY:-}
|
||
- CORS_ORIGINS=${CORS_ORIGINS:-http://localhost:3000}
|
||
env_file:
|
||
- .env
|
||
deploy:
|
||
resources:
|
||
reservations:
|
||
devices:
|
||
- driver: nvidia
|
||
count: 1
|
||
capabilities: [gpu]
|