liveBook · Manning

Output format description

As explained in Building LLM Applications with DSPy

A prompt component that specifies the required form, style, length, or encoding of a language model's output.

An output format description tells a language model how its response should be shaped, including writing style, length, and encoding. Formats may include JSON, YAML, CSV, other text or binary forms, or code with a specified language and conventions. section 2.1.2

The output should be a JSON with the following structure:
{reasoning: "", intent: ""}

A customer-intent prompt can require a JSON object with reasoning and intent fields. section 2.1.2

How Building LLM Applications with DSPy covers it

How deep it goes
Names formatting dimensions and examples such as JSON, YAML, and CSV, without describing enforcement.
Examples
Uses JSON, YAML, CSV, and code-language conventions as format choices.
What you can do after
Apply it by specifying a desired writing style, length, or structured format such as JSON.
How it connects
Pairs with task descriptions, context, input/output descriptions, demonstrations, and constraints in prompt design.
Cover of Building LLM Applications with DSPy
liveBookmanning.com
Read Building LLM Applications with DSPy on liveBook Get the book at manning.com

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.