100d1a06eb
- 后端 API（Flask + Gunicorn） - RAG 引擎（混合检索 + 云端 Reranker + 引用溯源） - 文档解析（MinerU + 多格式支持） - Docker 生产部署配置 - 排除前端项目、敏感配置、模型文件
37 lines
1.1 KiB
YAML
37 lines
1.1 KiB
YAML
version: '3.8'
|
||
|
||
services:
|
||
rag-service:
|
||
build:
|
||
context: ..
|
||
dockerfile: deploy/Dockerfile
|
||
container_name: rag-service
|
||
ports:
|
||
- "5001:5001"
|
||
volumes:
|
||
- ../knowledge/vector_store:/app/knowledge/vector_store # 向量索引（必须）
|
||
- ../.data:/app/.data # 上传文件
|
||
- ../documents:/app/documents # 源文档
|
||
- ../models:/app/models # 嵌入模型
|
||
# 生产环境不挂载 data/ 目录（不使用SQLite）
|
||
environment:
|
||
- APP_ENV=prod
|
||
- DASHSCOPE_API_KEY=${DASHSCOPE_API_KEY}
|
||
- DASHSCOPE_MODEL=${DASHSCOPE_MODEL:-mimo-v2.5}
|
||
- RERANK_USE_ONNX=${RERANK_USE_ONNX:-false}
|
||
restart: unless-stopped
|
||
# 资源限制：Embedding模型加载需要较多内存
|
||
shm_size: '256m' # Gunicorn 心跳文件需要
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
memory: 6G
|
||
reservations:
|
||
memory: 2G
|
||
healthcheck:
|
||
test: ["CMD-SHELL", "curl -f http://localhost:5001/health || exit 1"]
|
||
interval: 30s
|
||
timeout: 10s
|
||
retries: 3
|
||
start_period: 60s # 给启动和模型加载留出时间
|