Same topic, related formats. Practice these next.
Semantic boundaries, downstream context size, and embedding latency are real chunking decisions. The LLM tokenizer's scheme and vocabulary size are not chunking concerns at all.
Picture cutting a long book into bookmarks for a librarian who only ever reads the bookmarked passages. You care about where you cut, ideally between chapters so each bookmark is a coherent thought. You care about how big each cut is, since the librarian can only hold a few at a time. You care about how long it takes to bookmark every page, since you might have a million pages. You do not care which font the printer used to typeset the words. The font is the tokenizer. It matters when the words get read out loud later, but it does not change where you should cut the book.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.
Everything important, quickly.
Name the three real tradeoffs, explain why each one shapes chunk design, then dismantle the two distractors by showing the layering: chunks are stored as text or vectors, the LLM tokenizer operates downstream on whatever wins retrieval. Close by naming the tradeoffs the question omits, such as overlap and hierarchical chunking.
Real products, models, and research that use this idea.
What an interviewer would ask next. Try answering before peeking at the approach.
Red flags and common mistakes that signal junior thinking. Click to expand.
Treating tokenizer details as chunking concerns. Chunks are stored as text or pre-embedded vectors. The downstream model retokenises whatever context wins the retrieval, so the tokenizer choice does not shape chunk design.
The night-before-the-interview bullets. Scan these on the way to the call.
Primary sources. Skim if you want the original framing.