Vectors, embeddings, and search: an intuition-first guide

PS : You can find this fully animated article with concrete examples on my blog : https://nicolas.nz/blog/vectors-embeddings-and-search Vectors, embeddings, and search When we talk about AI, search, or LLMs, it often sounds like magic. You type words. Something understands them. It finds meaning, not just keywords. But under the hood, there’s no magic. There are vectors. Lots of them. Not symbols, not rules, not hidden dictionaries. Just numbers arranged in space. When I built my previous blog, I used vectors to power article recommendations (surfacing related content based on what you'd just read). I never really went deep on how any of it worked. This article is me fixing that. No heavy math. Just mental models you can actually feel. Text isn’t what models read It’s tempting to imagine models reading raw text, but they don’t. Language is broken down into smaller pieces called tokens . You might wonder why this step even matters. Bear with me, it'll make sense in a minute. At this sta