Context window
The maximum amount of text (measured in tokens) a model can process in a single exchange — including the instructions, the conversation history and the injected documents. When the conversation exceeds it, the model "forgets" the oldest part unless a memory mechanism exists.
- Appeared
- A concept from the earliest LLMs; windows grew sharply from 2023.
- Tactics
- We manage the window by summarizing history and through selective [RAG](#rag), so only the relevant context fits — keeping [latency](#latenta) low.
Related terms
“Context window” is part of Glossary · AI Chatbot — part of the Atlas, Websem's reference of AI search, marketing and data terms.