https://shengxu.pages.dev/en/tags/gemini/Cloud architecture & DevOps notes by Shengxu: Kubernetes, Cilium, observability, LLM infra, AI agents.Hugo 0.153.2 & FixIt v0.4.0-alpha.3-20251225101113-8ffb9a95enFri, 23 Jan 2026 15:30:00 +0800https://shengxu.pages.dev/en/posts/building-ai-search-with-cloudflare-and-gemini/Fri, 23 Jan 2026 15:30:00 +0800https://shengxu.pages.dev/en/posts/building-ai-search-with-cloudflare-and-gemini/AIDevOps<p>In 2026, adding AI search to a personal blog is nothing new. But achieving it with <strong>zero cost</strong>, <strong>full automation</strong>, and <strong>high performance</strong> remains a technical topic worth exploring.</p> <p>This article breaks down the technical architecture behind this site&rsquo;s AI Search feature, showing how to combine <strong>Cloudflare Workers</strong>, <strong>Vectorize</strong>, <strong>D1</strong>, and <strong>Google Gemini</strong> to build a closed-loop RAG (Retrieval-Augmented Generation) system.</p> <h2 class="heading-element" id="1-core-architecture-design"><span>1. Core Architecture Design</span> <a href="#1-core-architecture-design" class="heading-mark"> <svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z"></path></svg> </a> </h2><p>Our goal is a fully automated workflow: <strong>write and deploy</strong>. The author only needs to push Markdown articles; everything else—vector generation, index updates, frontend deployment—is automated.</p>