Concepts

Context Window

The maximum amount of text (tokens) an AI model can 'remember' or process in a single interaction.

Detailed Explanation

The context window is the maximum number of tokens an LLM can take as input and hold in its working memory during a single prompt generation cycle. If a conversation or document exceeds the context window, the model will 'forget' the earliest parts of the input. Modern models boast massive context windows, such as Google's Gemini 1.5 Pro, which can handle over 1 million tokens.

Related Terms

Large Language Model (LLM)

A type of foundational AI model trained on vast amounts of text to understand and generate human language.

Token

The basic unit of data processed by an LLM, typically representing a word or part of a word.

Back to Glossary