Beginner · Generative AI

Completion

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. The text a language model generates in response to a prompt.

Technical Definition

The text a language model generates in response to a prompt.

How it works

Originally LLMs literally completed a partial text; chat models now produce structured responses, but the underlying mechanism is still autoregressive next-token generation. API responses include the completion plus metadata like token counts and finish reason.

Related Concepts

• Large Language Model (LLM) — A massive neural network trained on vast text corpora to understand and generate human language with remarkable fluency.
• Prompt — The input text — instructions, context, examples — given to a language model to elicit a response.
• Sampling — The process of choosing the next token from the probability distribution a model outputs.