The 15-Day AI/ML Interview Bootcamp
Day 13 — LLMs in practice: tokenisation, prompting, embeddings, vector search, and RAG
How large language models are trained and used — tokenisation, context windows, sampling, prompting, embeddings and cosine similarity, vector search, retrieval-augmented generation, hallucination and evals — with a mini RAG pipeline built from scratch and the LLM questions every AI interview asks.
This morning you asked a chat assistant how to get a refund on a developer tool you pay for. It answered in two crisp sentences, named a command-line flag, and sounded completely sure. The flag doesn't exist. Then you pasted the tool's FAQ into the chat, asked again, and got the right answer with the relevant line quoted back at you. Same model, same question — one invented, one grounded. And then an interviewer, later in the week: "Your team wants a support bot on top of an LLM. How do you stop it making things up?" Today you and I build the thing that made the second answer possible. Not the…
In this lesson
Unlock the rest of The 15-Day AI/ML Interview Bootcamp
Day 13 — LLMs in practice: tokenisation, prompting, embeddings, vector search, and RAG is part of the full course. One payment unlocks every lesson, every other course, and every premium article — for life.