Dspy Bootstrap Fewshot Agent Skill

import dspy
from dspy.teleprompt import BootstrapFewShot

# Configure LMs
dspy.configure(lm=dspy.LM("openai/gpt-4o-mini"))

class QA(dspy.Module):
    def __init__(self):
        self.generate = dspy.ChainOfThought("question -> answer")
    
    def forward(self, question):
        return self.generate(question=question)

def validate_answer(example, pred, trace=None):
    return example.answer.lower() in pred.answer.lower()

optimizer = BootstrapFewShot(
    metric=validate_answer,
    max_bootstrapped_demos=4,
    max_labeled_demos=4,
    teacher_settings={'lm': dspy.LM("openai/gpt-4o")}
)

compiled_qa = optimizer.compile(QA(), trainset=trainset)

# Use optimized program
result = compiled_qa(question="What is photosynthesis?")

# Save for production (state-only, recommended)
compiled_qa.save("qa_optimized.json", save_program=False)

import dspy
from dspy.teleprompt import BootstrapFewShot
from dspy.evaluate import Evaluate
import logging

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

class ProductionQA(dspy.Module):
    def __init__(self):
        self.cot = dspy.ChainOfThought("question -> answer")
    
    def forward(self, question: str):
        try:
            return self.cot(question=question)
        except Exception as e:
            logger.error(f"Generation failed: {e}")
            return dspy.Prediction(answer="Unable to answer")

def robust_metric(example, pred, trace=None):
    if not pred.answer or pred.answer == "Unable to answer":
        return 0.0
    return float(example.answer.lower() in pred.answer.lower())

def optimize_with_bootstrap(trainset, devset):
    """Full optimization pipeline with validation."""
    
    # Baseline
    baseline = ProductionQA()
    evaluator = Evaluate(devset=devset, metric=robust_metric, num_threads=4)
    baseline_score = evaluator(baseline)
    logger.info(f"Baseline: {baseline_score:.2%}")
    
    # Optimize
    optimizer = BootstrapFewShot(
        metric=robust_metric,
        max_bootstrapped_demos=4,
        max_labeled_demos=4
    )
    
    compiled = optimizer.compile(baseline, trainset=trainset)
    optimized_score = evaluator(compiled)
    logger.info(f"Optimized: {optimized_score:.2%}")
    
    if optimized_score > baseline_score:
        compiled.save("production_qa.json", save_program=False)
        return compiled
    
    logger.warning("Optimization didn't improve; keeping baseline")
    return baseline