DSPy BetterTogether

Goal

Sequence prompt and weight optimizers, evaluate intermediate programs, and return the best candidate.

Prerequisites

• Use DSPy 3.2.1 or later in the stable 3.2.x series.
• Assign an LM directly to every predictor with student.set_lm(lm).
• Keep a validation set, or allow BetterTogether to hold out part of the trainset.
• Confirm the LM provider supports fine-tuning before including BootstrapFinetune.

Basic Pattern

import dspy

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

student = dspy.ChainOfThought("question -> answer")
student.set_lm(lm)

def metric(example, pred, trace=None):
    return float(example.answer.lower() == pred.answer.lower())

optimizer = dspy.BetterTogether(
    metric=metric,
    p=dspy.GEPA(
        metric=lambda gold, pred, trace=None, pred_name=None, pred_trace=None:
            dspy.Prediction(score=metric(gold, pred), feedback="Check answer correctness."),
        reflection_lm=dspy.LM("openai/gpt-4o"),
        auto="light",
    ),
    w=dspy.BootstrapFinetune(metric=metric),
)

compiled = optimizer.compile(
    student,
    trainset=trainset,
    valset=valset,
    strategy="p -> w -> p",
)

Strategy Choices

Optimizer names come from constructor keyword arguments. For example, mipro=... and gepa=... make "mipro -> gepa" valid.

Per-Optimizer Compile Arguments

Pass optimizer-specific arguments through optimizercompileargs:

compiled = optimizer.compile(
    student,
    trainset=trainset,
    valset=valset,
    strategy="p -> w",
    optimizer_compile_args={
        "p": {"max_metric_calls": 150},
    },
)

Do not pass student inside optimizercompileargs; BetterTogether manages the current program.

Inspect Results

The returned program exposes:

• candidate_programs: evaluated candidates with score and strategy
• flagcompilationerror_occurred: whether a step failed before completion

Related Skills

• Pick optimizers: [dspy-optimizer-selection](../dspy-optimizer-selection/SKILL.md)
• Fine-tune weights: [dspy-finetune-bootstrap](../dspy-finetune-bootstrap/SKILL.md)
• Reflect with GEPA: [dspy-gepa-reflective](../dspy-gepa-reflective/SKILL.md)

Official Documentation

• BetterTogether API: https://dspy.ai/api/optimizers/BetterTogether/
• Optimizer guide: https://dspy.ai/learn/optimization/optimizers/