<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>LanceDB - 标签 -</title><link>https://oklife.me/tags/lancedb/</link><description>LanceDB - 标签 -</description><generator>Hugo -- gohugo.io</generator><language>zh-CN</language><managingEditor>contact@oklife.me (梦行志)</managingEditor><webMaster>contact@oklife.me (梦行志)</webMaster><copyright>© 2026 梦行志 | 保留所有权利</copyright><lastBuildDate>Sun, 12 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://oklife.me/tags/lancedb/" rel="self" type="application/rss+xml"/><item><title>LanceDB 实战：为 AI Agent 构建本地语义检索引擎</title><link>https://oklife.me/2026/07/12/lancedb-local-semantic-search-engine/</link><pubDate>Sun, 12 Jul 2026 00:00:00 +0000</pubDate><author>contact@oklife.me (梦行志)</author><guid>https://oklife.me/2026/07/12/lancedb-local-semantic-search-engine/</guid><description><![CDATA[<div class="featured-image">
                <img src="/images/Code-Art-Studio-images/lancedb-local-semantic-search-engine/lancedb-local-semantic-search-engine.webp" referrerpolicy="no-referrer">
            </div>AI Agent 的信息抓取能力再强，如果数据存进去只能看不能搜，那就是&quot;死数据&quot;。本文从方案选型入手，对比 Chroma、LanceDB、Qdrant 等主流向量数据库，然后手把手安装配置 LanceDB，并通过闲鱼虚拟资料语义检索的完整演示，验证本地语义检索的可行性和效果。]]></description></item></channel></rss>