Pure DSPy Synthetic Prompt Optimization.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, it should be different than old data"""
    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)
    ]


# Synthetic Prompt Optimization
from dspy.teleprompt import BootstrapFewShot
from dspy.evaluate import answer_exact_match

text = "Barack Obama was not President of the USA"

# define the fact as input to the lie detector
trainset = [x.with_inputs('fact') for x in few_shot_examples]

# define the signature to be used in by the lie detector module
# for the evaluation, you need to define an answer field
class Veracity(dspy.Signature):
  "Evaluate the veracity of a statement"
  fact = dspy.InputField(desc="a statement")
  answer = dspy.OutputField(desc="an assessment of the veracity of the statement")

class lie_detector(dspy.Module):
  def __init__(self):
    super().__init__()
    self.lie_identification = dspy.ChainOfThought(Veracity)

  def forward(self, fact):
    return self.lie_identification(fact=fact)

teleprompter = BootstrapFewShot(metric=answer_exact_match)

compiled_lie_detector = teleprompter.compile(lie_detector(), trainset=trainset)

response = compiled_lie_detector(fact=text)

print(f"The statement '{text}' is  {response.answer}.")