<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>部署成本 on 知识铺的博客</title>
    <link>https://index.zshipu.com/geek001/tags/%E9%83%A8%E7%BD%B2%E6%88%90%E6%9C%AC/</link>
    <description>Recent content in 部署成本 on 知识铺的博客</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <lastBuildDate>Fri, 04 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://index.zshipu.com/geek001/tags/%E9%83%A8%E7%BD%B2%E6%88%90%E6%9C%AC/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>不用LLM也能做出完整聊天机器人：规则&#43;检索的实现路径</title>
      <link>https://index.zshipu.com/geek001/post/20260904/%E4%B8%8D%E7%94%A8LLM%E4%B9%9F%E8%83%BD%E5%81%9A%E5%87%BA%E5%AE%8C%E6%95%B4%E8%81%8A%E5%A4%A9%E6%9C%BA%E5%99%A8%E4%BA%BA%E8%A7%84%E5%88%99%E6%A3%80%E7%B4%A2%E7%9A%84%E5%AE%9E%E7%8E%B0%E8%B7%AF%E5%BE%84/</link>
      <pubDate>Fri, 04 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://index.zshipu.com/geek001/post/20260904/%E4%B8%8D%E7%94%A8LLM%E4%B9%9F%E8%83%BD%E5%81%9A%E5%87%BA%E5%AE%8C%E6%95%B4%E8%81%8A%E5%A4%A9%E6%9C%BA%E5%99%A8%E4%BA%BA%E8%A7%84%E5%88%99%E6%A3%80%E7%B4%A2%E7%9A%84%E5%AE%9E%E7%8E%B0%E8%B7%AF%E5%BE%84/</guid>
      <description>2026年chatbot的默认架构指向LLM驱动的流程，但dev.to这篇文章标题直白写着‘We Built a Chatbot Without an LLM: Here’s How It Works’。作者配图展示了典型LLM架构后，转而用非大模型方式搭建完整聊天机器人，这在当下形成鲜明反差。 这套方案把用户输入先交给规则引擎判断意图，再通过检</description>
    </item>
  </channel>
</rss>
