解决企业RAG系统检索不准、幻觉多、延迟高的问题
Higress-RAG: A Holistic Optimization Framework for Enterprise Retrieval-Augmented Generation via Dual Hybrid Retrieval, Adaptive Routing, and CRAG
- 采用双混合检索+自适应路由，提升复杂查询准确率
- 50毫秒低延迟语义缓存，减少重复计算
- 全链路优化适合企业级AI落地，抗幻觉能力强
大型语言模型（LLMs）在企业知识管理中的应用因检索增强生成（RAG）范式而加速，该范式通过外部非参数数据补充模型记忆。然而，从概念验证到生产级RAG系统的过渡面临三大挑战：复杂查询的检索精度低、生成阶段幻觉率高、实时应用延迟不可接受。本文提出Higress RAG MCP服务器，一种面向企业场景的全新架构，通过“全链路优化”策略解决上述瓶颈。基于模型上下文协议（MCP），系统构建分层架构，集成自适应路由、语义缓存、双混合检索与纠错式RAG（CRAG）。关键技术包括：支持结构感知的数据分割器（Higress-Native Splitter）、使用倒数排名融合（RRF）整合密集与稀疏检索信号，以及具备动态阈值的50ms低延迟语义缓存机制。在特定领域技术文档和博客数据集上的实验验证了系统架构的鲁棒性。结果表明，通过优化从查询重写到生成后纠错的整个检索生命周期，Higress RAG提供了一种可扩展、抗幻觉的企业级AI部署方案。
原文摘要 · Abstract (English)
The integration of Large Language Models (LLMs) into enterprise knowledge management systems has been catalyzed by the Retrieval-Augmented Generation (RAG) paradigm, which augments parametric memory with non-parametric external data. However, the transition from proof-of-concept to production-grade RAG systems is hindered by three persistent challenges: low retrieval precision for complex queries, high rates of hallucination in the generation phase, and unacceptable latency for real-time applications. This paper presents a comprehensive analysis of the Higress RAG MCP Server, a novel, enterprise-centric architecture designed to resolve these bottlenecks through a "Full-Link Optimization" strategy. Built upon the Model Context Protocol (MCP), the system introduces a layered architecture that orchestrates a sophisticated pipeline of Adaptive Routing, Semantic Caching, Hybrid Retrieval, and Corrective RAG (CRAG). We detail the technical implementation of key innovations, including the Higress-Native Splitter for structure-aware data ingestion, the application of Reciprocal Rank Fusion (RRF) for merging dense and sparse retrieval signals, and a 50ms-latency Semantic Caching mechanism with dynamic thresholding. Experimental evaluations on domain-specific Higress technical documentation and blogs verify the system's architectural robustness. The results demonstrate that by optimizing the entire retrieval lifecycle - from pre-retrieval query rewriting to post-retrieval corrective evaluation - the Higress RAG system offers a scalable, hallucination-resistant solution for enterprise AI deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。