0PricingLogin▼
AI Prompt Engineering · Lesson

Defining Signatures and Modules

Signature syntax, ChainOfThought, ReAct, and custom DSPy modules.

Signatures Are Typed Contracts

A DSPy signature is a Python class that declares the inputs and outputs of a reasoning step. Think of it as a typed function contract for your LLM call.

The docstring becomes the task description. Field annotations tell DSPy what to produce. You never write the actual prompt text — DSPy derives it from this declaration.

Defining a Basic Signature

A minimal signature subclasses dspy.Signature and annotates fields as InputField or OutputField. The class docstring provides the task instruction.

import dspy

class QASignature(dspy.Signature):
    """Answer the question based on the given context."""
    context: str = dspy.InputField(desc='Relevant background text')
    question: str = dspy.InputField(desc='The question to answer')
    answer: str = dspy.OutputField(desc='A concise answer')

# Inspect what DSPy sees
print(QASignature.instructions)  # The docstring
print(list(QASignature.input_fields.keys()))   # ['context', 'question']
print(list(QASignature.output_fields.keys()))  # ['answer']

All lessons in this course

  1. Introduction to DSPy Framework
  2. Defining Signatures and Modules
  3. Compiling and Optimizing Prompts
  4. Evaluating DSPy Pipelines
← Back to AI Prompt Engineering