# nginx.conf - RAG服务反向代理配置 upstream rag_backend { # 负载均衡策略:least_conn(最少连接) least_conn; # 多个RAG服务实例(可选,用于高可用) server rag-service-1:5001 max_fails=3 fail_timeout=30s; # server rag-service-2:5001 max_fails=3 fail_timeout=30s; # server rag-service-3:5001 max_fails=3 fail_timeout=30s; } server { listen 80; server_name rag.example.com; # 请求体大小限制(文档上传) client_max_body_size 100M; # 超时配置(RAG问答可能较慢) proxy_connect_timeout 120s; proxy_send_timeout 120s; proxy_read_timeout 120s; # RAG服务代理 location / { proxy_pass http://rag_backend; proxy_set_header Host $host; proxy_set_header X-Real-IP $remote_addr; proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; proxy_set_header X-Forwarded-Proto $scheme; # SSE流式响应支持 proxy_buffering off; proxy_cache off; proxy_http_version 1.1; chunked_transfer_encoding on; } # 健康检查 location /health { proxy_pass http://rag_backend/health; access_log off; } # 请求限流(防止滥用) limit_req_zone $binary_remote_addr zone=rag_limit:10m rate=10r/s; limit_req zone=rag_limit burst=20 nodelay; } # HTTPS配置(推荐) server { listen 443 ssl http2; server_name rag.example.com; ssl_certificate /etc/nginx/ssl/cert.pem; ssl_certificate_key /etc/nginx/ssl/key.pem; # 其他配置同上... }