liveBook · Manning

Input-output description

As explained in Building LLM Applications with DSPy

A prompt component that specifies what information is given to a language model and what it is expected to return.

An input-output description states what information the model will receive and what response it should return. Clarity matters even when both are simple. section 2.1.2

Example:
Customer message: I want to end my subscription
Example Output:
{Reasoning: "The main object is subscription and the main action is ending hence the user wants to cancel his subscription"
Intent: "Cancel Subscription"}

A customer message requesting subscription cancellation is paired with an appropriate intent response. section 2.1.2

How Building LLM Applications with DSPy covers it

How deep it goes
Defines the component and stresses clarity, without prescribing a fixed template.
Examples
Pairs a subscription-cancellation customer message with an intent response.
What you can do after
Apply it by stating the supplied information and expected response clearly, even for simple exchanges.
How it connects
Distinguishes input and response details from task descriptions, context, output formats, demonstrations, and constraints.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Building LLM Applications with DSPy. The section links point to the parts of the book it draws on.