<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Agentic RAG on 知识铺的博客</title>
    <link>https://index.zshipu.com/geek002/tags/Agentic-RAG/</link>
    <description>Recent content in Agentic RAG on 知识铺的博客</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <lastBuildDate>Tue, 24 Sep 2024 02:35:25 +0000</lastBuildDate>
    <atom:link href="https://index.zshipu.com/geek002/tags/Agentic-RAG/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>构建Agentic RAG AI Agent智能体教程</title>
      <link>https://index.zshipu.com/geek002/post/20240918/%E6%9E%84%E5%BB%BAAgentic-RAG-AI-Agent%E6%99%BA%E8%83%BD%E4%BD%93%E6%95%99%E7%A8%8B--%E7%9F%A5%E8%AF%86%E9%93%BA/</link>
      <pubDate>Tue, 24 Sep 2024 02:35:25 +0000</pubDate>
      <guid>https://index.zshipu.com/geek002/post/20240918/%E6%9E%84%E5%BB%BAAgentic-RAG-AI-Agent%E6%99%BA%E8%83%BD%E4%BD%93%E6%95%99%E7%A8%8B--%E7%9F%A5%E8%AF%86%E9%93%BA/</guid>
      <description>什么是Agentic RAG RAG (Retrieval-Augmented Generation) 是一种结合了信息检索和生成模型的技术，旨在通过从大量文档中检索相关信息来增强大语言模型（LLM）的回答质量。经典的RAG应用范式及架构已经变得非常流行，允许开发者快速构建一个能够有效处理用户查询的应用。 经典RAG工作流程 接收用户问题 用户向系统提出一个问</description>
    </item>
  </channel>
</rss>
