Description: A context window is the maximum amount of text a language model can process at once when generating a response. If too much information is provided, the model will use only the most recent text that fits within that limit. For example, if an entire book were given to a Large Language Model (LLM) to summarise it would not succeed because the amount of data exceeds the capacity of the context window. However, if the request were to summarise a single page, the model would be able to complete the task because the input fits within the available window. This behaviour is not related to the amount of training data the model has seen. Instead, it is determined by how the system is designed to process user input and the limits on how much text can be considered at one time.