<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Workflow on Apache HugeGraph</title><link>https://hugegraph.apache.org/cn/tags/workflow/</link><description>Recent content in Workflow on Apache HugeGraph</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Mon, 12 Oct 2026 03:51:58 +0800</lastBuildDate><atom:link href="https://hugegraph.apache.org/cn/tags/workflow/index.xml" rel="self" type="application/rss+xml"/><item><title>Agentic GraphRAG</title><link>https://hugegraph.apache.org/cn/blog/2025/10/29/agentic-graphrag/</link><pubDate>Wed, 29 Oct 2025 00:00:00 +0000</pubDate><guid>https://hugegraph.apache.org/cn/blog/2025/10/29/agentic-graphrag/</guid><description>&lt;h1 id="项目背景"&gt;项目背景&#10;&lt;/h1&gt;&#10;&lt;p&gt;为了应对模型训练数据和现实生活中实际数据之间存在的时效性差异问题，RAG技术应运而生。RAG，顾名思义就是通过向外部数据源获取对应的数据（Retrieval），用于增强（Argument）大模型生成（Generation）回答质量的技术。&lt;/p&gt;</description></item></channel></rss>