Prompt
As you can see above we are passing not just the function out back into the model for further sampling but also the previous chain-of-thought (“Need to use function get_current_weather.”) to provide the model with the necessary information to continue its chain-of-thought or provide the final answer.
#### Preambles
At times the model might choose to generate a “preamble” to inform the user about the tools it is about to call. For example, when it plans to call multiple tools. If this is the case it will generate an assistant message on the `commentary` channel that, unlike the chain-of-thought, is intended to be shown to the end-user.