Prediction

As explained in Building LLM Applications with DSPy

A DSPy prediction is the structured object representing a language model's output, with fields specified by a signature.

Prediction(
    answer='The capital of France is Paris.'
)

How Building LLM Applications with DSPy covers it

How deep it goes

Defines the output object and field access, without detailing its implementation.

Examples

Shows a question-answering result with an answer field containing the capital of France.

What it assumes

Relies on a signature to specify the prediction’s output fields.

What you can do after

Understand how to retrieve signature-defined output fields using bracket or dot notation.

How it connects

Connects predictions to signatures, language models, and DSPy programs.

liveBookmanning.com

Read Building LLM Applications with DSPy on liveBook Get the book at manning.com

Related concepts

• DSPy programproduced by · A DSPy program is an executable composition of one or more module instances that can be called with inputs declared by a signature.
• dotted notationused by · Dotted notation is syntax that uses periods to access or invoke members, qualify names, or represent hierarchical paths.
• metric functionused by · A metric function is a function that evaluates a language-model prediction against an example and optionally a call trace to produce an assessment score.
• square bracketsused by · Square brackets are paired punctuation marks used in programming-language syntax to delimit expressions or constructs, including indexing and collection literals.

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.