Context Window
Maximum number of tokens a model can attend to in one request.
Aperçu
The context window is the number of tokens a model can consider at once, covering the prompt and the response together. It solves the problem that a model has no memory beyond what is in front of it, so it bounds how much source material a request can carry. It exists as a hard architectural limit because attention cost grows with sequence length. It is the constraint that makes retrieval necessary rather than optional.
Graphe des technologies
Comment Context Window se rattache au reste de la pile.
Utilise et dépend de
- Agent Memory technique AI Agents Agent Memory based on Context Window High ✓ source
- Context Engineering technique Prompting Context Engineering based on Context Window High ✓ source
Appliqué à
- RAG technique Techniques Context Window used for RAG High ✓ source