shuiyuan-rag-service

Maintain a persistent FastAPI RAG service with preloaded BGEM3 and BGE models.

69|6|Updated Mar 31, 2026

Search Tags:#fastapi #rag #embedding #reranker #http service #shuiyuan

Ready to run

npx skills add https://github.com/xhh678876/openclaw-sjtu --skill shuiyuan-rag-service

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: shuiyuan-rag-service
Source: https://github.com/xhh678876/openclaw-sjtu/tree/main/skills/shuiyuan-rag-service
Command: npx skills add https://github.com/xhh678876/openclaw-sjtu --skill shuiyuan-rag-service

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill solves slow and resource-heavy Shuiyuan Community RAG searches by maintaining a persistent HTTP service with preloaded embedding and reranking models instead of repeated cold starts.

Core Features & Use Cases

Persistent RAG Service: Runs a FastAPI-based Shuiyuan retrieval service that keeps BGEM3 embedding and BGE reranker models loaded in memory for shared access.
Service Operations: Supports health checks, search requests, statistics queries, reload workflows, and troubleshooting for RAG availability issues.
Use Case: When Shuiyuan Community search becomes unavailable or slow, use this Skill to check service status, restart the daemon, or restore retrieval capabilities for connected clients.

Quick Start

Ask the AI to start the Shuiyuan RAG service and check its HTTP health status.

Frequently Asked Questions about shuiyuan-rag-service

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I keep a FastAPI RAG service persistent to avoid slow cold starts?▼

To keep a FastAPI RAG service persistent, maintain a daemon process that preloads embedding and reranking models in memory. This avoids repeated cold starts and provides shared HTTP search endpoints for connected clients.

Why does my Shuiyuan Community search become unavailable or slow?▼

Shuiyuan Community search becomes slow or unavailable when the RAG service needs cold starts or models are unloaded. Reloading BGEM3 embedding and BGE reranker models into a persistent FastAPI service restores retrieval availability.

Can I share embedding resources across multiple clients using a single HTTP search endpoint?▼

Yes, a persistent FastAPI RAG service allows sharing embedding resources across multiple clients. By keeping BGEM3 embedding and BGE reranker models loaded in memory, connected clients can access the HTTP search endpoint simultaneously.

What are the limitations of running a persistent RAG service for local campus knowledge retrieval?▼

Limitations of a persistent RAG service include the memory overhead required to keep BGEM3 and BGE models loaded continuously. This approach is best suited for local campus knowledge retrieval scenarios requiring consistent availability rather than occasional queries.

Does the Shuiyuan RAG service support troubleshooting and reload workflows?▼

Yes, the Shuiyuan RAG service supports troubleshooting and reload workflows. It provides operational diagnostics, health monitoring, and service management commands to restart the FastAPI daemon and restore retrieval capabilities.