Dspy Simba Optimizer

import dspy

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

# Program to optimize
class QAPipeline(dspy.Module):
    def __init__(self):
        self.generate = dspy.ChainOfThought("question -> answer")

    def forward(self, question):
        return self.generate(question=question)

# Metric returns a numeric score
def qa_metric(example, pred, trace=None):
    correct = example.answer.lower() in pred.answer.lower()
    return 1.0 if correct else 0.0

# SIMBA optimizer
optimizer = dspy.SIMBA(
    metric=qa_metric,
    max_steps=10,  # Optimization iterations
    bsize=5  # Mini-batch size
)

program = QAPipeline()
compiled = optimizer.compile(program, trainset=trainset)
compiled.save("qa_simba.json")

import dspy

def detailed_metric(example, pred, trace=None):
    """Return a graded numeric score."""
    expected = example.answer.lower()
    actual = pred.answer.lower()

    if expected == actual:
        return 1.0
    elif expected in actual:
        return 0.7
    else:
        overlap = len(set(expected.split()) & set(actual.split()))
        if overlap > 0:
            return 0.3
        return 0.0

optimizer = dspy.SIMBA(
    metric=detailed_metric,
    max_steps=20,  # Optimization iterations
    bsize=8  # Mini-batch size
)

compiled = optimizer.compile(program, trainset=trainset)

import dspy
from dspy.evaluate import Evaluate
import logging

logger = logging.getLogger(__name__)

# Define tools as functions
def search(query: str) -> str:
    """Search knowledge base for relevant information."""
    retriever = dspy.ColBERTv2(url='http://20.102.90.50:2017/wiki17_abstracts')
    results = retriever(query, k=3)
    return "\n".join([r['text'] for r in results])

def calculate(expr: str) -> str:
    """Evaluate Python expressions safely."""
    try:
        with dspy.PythonInterpreter() as interp:
            return str(interp.execute(expr))
    except Exception as e:
        return f"Error: {e}"

class ResearchAgent(dspy.Module):
    def __init__(self):
        self.agent = dspy.ReAct(
            "question -> answer",
            tools=[search, calculate]
        )

    def forward(self, question):
        return self.agent(question=question)

def agent_metric(example, pred, trace=None):
    """Numeric metric for agent optimization."""
    expected = example.answer.lower().strip()
    actual = pred.answer.lower().strip() if pred.answer else ""

    # Exact match
    if expected == actual:
        return 1.0

    # Partial match
    if expected in actual:
        return 0.7

    # Check key terms
    expected_terms = set(expected.split())
    actual_terms = set(actual.split())
    overlap = len(expected_terms & actual_terms)

    if overlap >= len(expected_terms) * 0.5:
        return 0.5

    return 0.0

def optimize_agent(trainset, devset):
    """Full SIMBA optimization pipeline."""
    dspy.configure(lm=dspy.LM("openai/gpt-4o-mini"))

    agent = ResearchAgent()

    # Baseline evaluation
    evaluator = dspy.Evaluate(devset=devset, metric=agent_metric, num_threads=4)
    baseline = evaluator(agent)
    logger.info(f"Baseline: {baseline:.2%}")

    # SIMBA optimization
    optimizer = dspy.SIMBA(
        metric=agent_metric,
        max_steps=25,  # Optimization iterations
        bsize=6  # Mini-batch size
    )

    compiled = optimizer.compile(agent, trainset=trainset)

    # Evaluate optimized
    optimized = evaluator(compiled)
    logger.info(f"SIMBA optimized: {optimized:.2%}")

    compiled.save("research_agent_simba.json")
    return compiled

optimizer = dspy.SIMBA(
    metric=metric_fn,
    max_steps=20,                          # Optimization iterations
    bsize=32,                              # Mini-batch size (default: 32)
    num_candidates=6,                      # Candidates per iteration (default: 6)
    max_demos=4,                           # Max demos per predictor (default: 4)
    temperature_for_sampling=0.2,          # Sampling temperature (default: 0.2)
    temperature_for_candidates=0.2         # Candidate selection temperature (default: 0.2)
)