<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>RAG on Mi&amp;Bee Blog</title><link>/tags/rag/</link><description>Recent content in RAG on Mi&amp;Bee Blog</description><generator>Hugo -- gohugo.io</generator><language>zh-CN</language><managingEditor>蓝宝石的傻话</managingEditor><lastBuildDate>Sun, 10 Nov 2024 00:00:00 +0000</lastBuildDate><atom:link href="/tags/rag/rss.xml" rel="self" type="application/rss+xml"/><item><title>上下文工程：让 AI 拥有正确的知识</title><link>/posts/aihelper/context-engineering-guide/</link><pubDate>Sun, 10 Nov 2024 00:00:00 +0000</pubDate><guid>/posts/aihelper/context-engineering-guide/</guid><description>&lt;h2 id="什么是上下文工程"&gt;什么是上下文工程？&lt;/h2&gt;
&lt;p&gt;2025 年 6 月，Andrej Karpathy 在 OpenAI 工程博客上给出了上下文工程的定义：&lt;strong&gt;&amp;ldquo;the delicate art and science of filling the context window with just the right information for the model to take the next step.&amp;rdquo;&lt;/strong&gt;&lt;/p&gt;
&lt;p&gt;这一定义非常精辟。与提示工程（Prompt Engineering）的核心区别在于：&lt;/p&gt;</description></item></channel></rss>