<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>VectorDatabase on SiBlog</title><link>https://sinimite.work/tags/vectordatabase/</link><description>Recent content in VectorDatabase on SiBlog</description><image><title>SiBlog</title><url>https://sinimite.work/images/og-default.svg?v=20260525-210321</url><link>https://sinimite.work/images/og-default.svg?v=20260525-210321</link></image><generator>Hugo -- 0.156.0</generator><language>zh-cn</language><lastBuildDate>Fri, 17 Jul 2026 15:40:44 +0900</lastBuildDate><atom:link href="https://sinimite.work/tags/vectordatabase/rss.xml" rel="self" type="application/rss+xml"/><item><title>RAG 检索工程：从混合检索到生产治理</title><link>https://sinimite.work/posts/rag-retrieval-engineering-guide/</link><pubDate>Fri, 17 Jul 2026 15:40:44 +0900</pubDate><guid>https://sinimite.work/posts/rag-retrieval-engineering-guide/</guid><description>一篇关于 RAG 检索层设计与落地的技术报告，涵盖 BM25、Embedding、ANN、RRF、重排、查询理解、访问控制、评测和部署实践。</description></item><item><title>RRF 在 RAG 中的作用：一种简单但并非万能的检索融合方法</title><link>https://sinimite.work/posts/rag-rrf-retrieval-fusion/</link><pubDate>Wed, 15 Jul 2026 17:37:44 +0900</pubDate><guid>https://sinimite.work/posts/rag-rrf-retrieval-fusion/</guid><description>一篇关于 Reciprocal Rank Fusion 原理、工程位置、融合选择和生产评估方法的技术参考。</description></item><item><title>RAG 检索中的 Dense + Sparse Hybrid Search</title><link>https://sinimite.work/posts/rag-dense-sparse-hybrid-search/</link><pubDate>Wed, 15 Jul 2026 17:25:30 +0900</pubDate><guid>https://sinimite.work/posts/rag-dense-sparse-hybrid-search/</guid><description>一篇关于 Dense + Sparse Hybrid Search 原理、融合方式、适用场景和评估方法的技术参考。</description></item><item><title>企业级 RAG 系统搭建指南</title><link>https://sinimite.work/posts/enterprise-rag-system-building-guide/</link><pubDate>Wed, 15 Jul 2026 16:35:23 +0900</pubDate><guid>https://sinimite.work/posts/enterprise-rag-system-building-guide/</guid><description>介绍企业级 RAG 系统的数据摄取、混合检索、权限控制、生成、评估与可观测架构。</description></item><item><title>RAG 系统全景指南：从 0 到生产级的完整设计流程</title><link>https://sinimite.work/posts/rag-system-complete-guide/</link><pubDate>Fri, 27 Mar 2026 15:06:20 +0900</pubDate><guid>https://sinimite.work/posts/rag-system-complete-guide/</guid><description>面向 AI 应用工程学习者的 RAG 全景指南，系统讲清数据摄入、分块、检索、重排序、生成、评估与生产运维，并给出从 0 到上线的实现路径。</description></item></channel></rss>