<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>知识库 - Tag - 编程心语</title><link>https://www.ithome.me/tags/%E7%9F%A5%E8%AF%86%E5%BA%93/</link><description>知识库 - Tag - 编程心语</description><generator>Hugo -- gohugo.io</generator><language>zh-CN</language><lastBuildDate>Fri, 12 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.ithome.me/tags/%E7%9F%A5%E8%AF%86%E5%BA%93/" rel="self" type="application/rss+xml"/><item><title>LangChain + ChromaDB 实战：构建本地知识库 RAG 问答系统</title><link>https://www.ithome.me/post/2026/06/12/langchain-chromadb-rag-%E7%9F%A5%E8%AF%86%E5%BA%93%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/</link><pubDate>Fri, 12 Jun 2026 00:00:00 +0000</pubDate><author>Simon</author><guid>https://www.ithome.me/post/2026/06/12/langchain-chromadb-rag-%E7%9F%A5%E8%AF%86%E5%BA%93%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/</guid><description>前言 大语言模型（LLM）虽然强大，但存在两个核心痛点：知识截断和幻觉问题。模型的训练数据有截止日期，且无法准确回答其训练数据之外的问题。RA</description></item></channel></rss>