菜单
Use for GEPA reflective optimization, ReAct agent optimization, feedback metrics, LLM reflection, and execution trajectories.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use for DSPy adapter selection, JSONAdapter, XMLAdapter, ChatAdapter, native function calling, structured outputs, and multimodal inputs like dspy.Image or dspy.Audio.
Use for composing DSPy modules with Ensemble, MultiChainComparison, ensemble voting, sequential pipelines, and multi-program workflows.
Use for BetterTogether, prompt plus weight optimization, fine-tuning sequences, and strategy chains like p -> w -> p.
Use for BootstrapFewShot, bootstrapped demonstrations, teacher-model demos, and low-data DSPy prompt optimization.
Use for creating custom DSPy modules, extending dspy.Module, reusable components, stateful modules, serialization, and module testing.
Use for debugging DSPy programs, inspect_history, tracing LLM calls, custom callbacks, observability, monitoring, and cost tracking.
| name | dspy-gepa-reflective |
| version | 1.0.0 |
| dspy-compatibility | 3.2.1 |
| tags | ["optimizer","agent"] |
| requires-extras | [] |
| description | Use for GEPA reflective optimization, ReAct agent optimization, feedback metrics, LLM reflection, and execution trajectories. |
| allowed-tools | ["Read","Write","Glob","Grep"] |
Optimize complex agentic systems using LLM reflection on full execution traces with Pareto-based evolutionary search.
| Input | Type | Description |
|---|---|---|
program | dspy.Module | Agent or complex program |
trainset | list[dspy.Example] | Training examples |
metric | callable | Accepts five arguments and returns dspy.Prediction(score=..., feedback=...) |
reflection_lm | dspy.LM | Strong LM for reflection (GPT-4) |
auto | str | "light", "medium", "heavy" |
| Output | Type | Description |
|---|---|---|
compiled_program | dspy.Module | Reflectively optimized program |
GEPA requires metrics that return textual feedback:
def gepa_metric(example, pred, trace=None, pred_name=None, pred_trace=None):
"""Return score and actionable feedback for GEPA reflection."""
is_correct = example.answer.lower() in pred.answer.lower()
if is_correct:
feedback = "Correct. The answer accurately addresses the question."
else:
feedback = f"Incorrect. Expected '{example.answer}' but got '{pred.answer}'. The model may have misunderstood the question or retrieved irrelevant information."
return dspy.Prediction(score=float(is_correct), feedback=feedback)
import dspy
def search(query: str) -> list[str]:
"""Search knowledge base for relevant information."""
rm = dspy.ColBERTv2(url='http://20.102.90.50:2017/wiki17_abstracts')
results = rm(query, k=3)
return results if isinstance(results, list) else [results]
def calculate(expression: str) -> float:
"""Safely evaluate mathematical expressions."""
with dspy.PythonInterpreter() as interp:
return interp(expression)
agent = dspy.ReAct("question -> answer", tools=[search, calculate])
dspy.configure(lm=dspy.LM("openai/gpt-4o-mini"))
optimizer = dspy.GEPA(
metric=gepa_metric,
reflection_lm=dspy.LM("openai/gpt-4o"), # Strong model for reflection
auto="medium"
)
compiled_agent = optimizer.compile(agent, trainset=trainset)
import dspy
from dspy.evaluate import Evaluate
import logging
logger = logging.getLogger(__name__)
class ResearchAgent(dspy.Module):
def __init__(self):
self.react = dspy.ReAct(
"question -> answer",
tools=[self.search, self.summarize]
)
def search(self, query: str) -> list[str]:
"""Search for relevant documents."""
rm = dspy.ColBERTv2(url='http://20.102.90.50:2017/wiki17_abstracts')
results = rm(query, k=5)
return results if isinstance(results, list) else [results]
def summarize(self, text: str) -> str:
"""Summarize long text into key points."""
summarizer = dspy.Predict("text -> summary")
return summarizer(text=text).summary
def forward(self, question):
return self.react(question=question)
def detailed_feedback_metric(example, pred, trace=None, pred_name=None, pred_trace=None):
"""Rich feedback for GEPA reflection."""
expected = example.answer.lower().strip()
actual = pred.answer.lower().strip() if pred.answer else ""
# Exact match
if expected == actual:
return dspy.Prediction(score=1.0, feedback="Perfect match. Answer is correct and concise.")
# Partial match
if expected in actual or actual in expected:
return dspy.Prediction(score=0.7, feedback=f"Partial match. Expected '{example.answer}', got '{pred.answer}'. Answer contains correct info but may be verbose or incomplete.")
# Check for key terms
expected_terms = set(expected.split())
actual_terms = set(actual.split())
overlap = len(expected_terms & actual_terms) / max(len(expected_terms), 1)
if overlap > 0.5:
return dspy.Prediction(score=0.5, feedback=f"Some overlap. Expected '{example.answer}', got '{pred.answer}'. Key terms present but answer structure differs.")
return dspy.Prediction(score=0.0, feedback=f"Incorrect. Expected '{example.answer}', got '{pred.answer}'. The agent may need better search queries or reasoning.")
def optimize_research_agent(trainset, devset):
"""Full GEPA optimization pipeline."""
dspy.configure(lm=dspy.LM("openai/gpt-4o-mini"))
agent = ResearchAgent()
# Convert metric for evaluation (just score)
def eval_metric(example, pred, trace=None):
return detailed_feedback_metric(example, pred, trace).score
evaluator = Evaluate(devset=devset, num_threads=8, metric=eval_metric)
baseline = evaluator(agent)
logger.info(f"Baseline: {baseline:.2%}")
# GEPA optimization
optimizer = dspy.GEPA(
metric=detailed_feedback_metric,
reflection_lm=dspy.LM("openai/gpt-4o"),
auto="medium"
)
compiled = optimizer.compile(agent, trainset=trainset)
optimized = evaluator(compiled)
logger.info(f"Optimized: {optimized:.2%}")
compiled.save("research_agent_gepa.json")
return compiled
GEPA metrics must accept (gold, pred, trace, pred_name, pred_trace). Return dspy.Prediction(score=..., feedback=...) when textual feedback is available. Do not pass enable_tool_optimization; it is not a DSPy 3.2.1 GEPA constructor argument.