LLMs

An LLM is a large neural network trained on huge amounts of text to predict and generate language.

A token is the small chunk of text — often a word or word-piece — that an LLM actually reads, counts, and predicts.

Tokenization is the process of splitting text into tokens using a learned subword vocabulary before a model can read it.

The context window is the maximum number of tokens an LLM can consider at once — its working memory for a single request.

Sampling is how an LLM picks the next token from its probabilities; temperature, top-p, and top-k control how random or focused that choice is.

Structured output makes an LLM return data in a strict format like JSON that follows a schema, so software can reliably use its answers.

Function calling lets an LLM request that your code run a real tool by emitting a structured call, then use the result to answer.

Prompt engineering is the craft of writing clear instructions, context, and examples so an LLM reliably produces the output you want.

Reasoning models spend extra decode tokens thinking before they answer; a short prompt can still cost a lot.

Streaming sends tokens as they are generated so users see the first word fast; TTFT is wait-to-first-token, TPOT is later gaps.

Small language models (about 1–8B parameters) win on device, privacy, cost, and easy tasks; route hard turns to a larger model.