https://www.fernandoux.com/tags/context/Recent content in Context on Fernando RuizHugoen-ushttps://www.fernandoux.com/en/wiki/ai/context-window/Mon, 01 Jan 0001 00:00:00 +0000https://www.fernandoux.com/en/wiki/ai/context-window/<div class="info-panel"> <div class="info-header"> <span class="material-symbols-outlined info-panel-icon">info</span> <span class="info-panel-label">Quick Definition</span> </div> <div class="info-content"> The <strong>context window</strong> is the maximum number of [[tokens|tokens]] a model can handle in a single request. It includes the instructions, the conversation history, the documents and tools you pass in, and also the response the model generates. </div> </div> <h2 id="what-is-a-context-window">What is a context window?</h2> <p>A language model remembers nothing between one call and the next. Everything it needs to answer has to travel in the request: the system message, earlier turns, attached files and the current question. The context window is the maximum size of that package.</p>