Vibe Coding Discoverragent
View on GitHub企业级 Agentic RAG 智能体 - 全链路覆盖文档解析、多路检索、意图识别、问题重写、会话记忆、MCP 工具调用与深度思考。面向真实业务场景，从 0 到 1 完整工程实现。
Production-grade Java Agentic RAG platform covering document ingestion, multi-channel retrieval (vector/keyword/graph/web) with RRF and rerank, intent recognition, query rewrite, session memory, MCP tool calling and a ReAct agent engine. Ships a React admin console, tracing and enterprise reliability features.
Use Cases
Enterprise knowledge base question answeringDocument ingestion and parsing pipeline (PDF/Word/PPT/web)Hybrid vector + keyword + knowledge graph + web retrieval with RRF fusion and rerankQuery rewriting, splitting and tree-based intent recognition with multi-KB routingMCP tool discovery, parameter extraction and validationReAct agent task planning and execution with human confirmationMulti-turn session memory with persistence and summarizationModel tiering, first-token probing and circuit-breaker failoverRedis fair queuing for traffic protectionRAG trace, observability and admin console managementAnswer citation, source preview and user feedback loopLearning/reference project for Java devs transitioning to AI engineering
Built With
- Language
- Java
- Frameworks
- Spring AI · Spring Boot · React · Vite · Tailwind CSS · RocketMQ · Redis · MySQL · Sa-Token · MCP Java SDK · MyBatis · Langfuse
Tags
agentic-rag · rag · mcp · spring-ai · java · multi-channel-retrieval · intent-recognition · query-rewrite · session-memory · rerank · vector-search · knowledge-graph · react-agent · deep-thinking · langfuse · enterprise