For software engineers who know what an index is and what an embedding is. Start Here: A Question You Think You Already Know the Answer To You have a chunks table with 50,000 rows. Each row has a text column and a vector column — a list of 1536 floating point numbers representing the semantic meaning of that text. A user query arrives. You embed it into another 1536-dimensional vector. Now you want the most semantically similar chunks. ...

I wanted a blog that was fast, free to host, and didn’t require me to manage a server. This post is a step-by-step account of how I built exactly that — using Hugo to generate the site and Cloudflare Pages to serve it. No prior experience needed. If you can use a terminal and have a GitHub account, you can follow along. First, understand what you’re building Before touching any tools, it helps to understand what’s actually happening. ...