synthetic-data-generation-dspy.py

# Synthetic data generation using DSPy
from typing import List
import dspy

llm = dspy.OpenAI(model='gpt-3.5-turbo',api_key=openai_key)

dspy.settings.configure(lm=llm)

class FactGeneration(dspy.Signature):
    """Generate facts and their veracity"""
    sindex = dspy.InputField(desc="a random string")
    fact = dspy.OutputField(desc="a statement")
    veracity = dspy.OutputField(desc="a boolean True or False")

fact_generator = dspy.Predict(FactGeneration, n=15)

response = fact_generator(sindex="1")

few_shot_examples: List[dspy.Example] = [
        dspy.Example({'fact': fact, 'answer': veracity})
        for fact, veracity in zip(response.completions.fact, response.completions.veracity)
    ]