« Between my prompt and the LLM answer, what exactly happens? »
What is the role of vectors in an LLM?
Customer :
« Between my prompt and the LLM answer, what exactly happens? »
Me :
Great question.
The key idea is simple: an LLM does not manipulate words the way we do. It manipulates numbers.
Those numbers are organized as vectors.
A vector here is a list of values that represents a token (part of a word), a sentence, or even a full document.
What happens between your prompt and the answer When you send a prompt, the model follows a sequence of steps:
Tokenization
The text is split into units (words, subwords, punctuation). Vector conversion
Each token is converted into a numeric vector (embedding). Attention calculation
The model compares tokens to identify what matters most in context. …