# Dspy Gepa Optimizer

> Full GEPA API and optimization patterns

- Skill: `j33bs/dspy-gepa-optimizer` (Agent Skill)
- Install (CLI): `npx skillmds@latest add j33bs/dspy-gepa-optimizer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/j33bs/dspy-gepa-optimizer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Integrations & APIs
- Author: j33bs (https://skillmd.com/u/j33bs)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/j33bs/dspy-gepa-optimizer

---


# GEPA Optimizer

## 🎯 Trigger Conditions
Use when asked about GEPA (Generative Evaluation-Preserving Optimization), advanced DSPy optimization, or when standard optimizers are insufficient.

## 📚 Prerequisites
- `dspy` package installed
- Training data with gold labels
- Clear evaluation objectives

## 🛠️ GEPA API

### 1. Basic GEPA Usage
```python
from dspy import GEPA

# Create GEPA optimizer
gepa = GEPA(
    metric=your_metric,
    max_budget=100,
    temperature=0.7,
    seed=42
)

# Optimize program
optimized = gepa.optimize(
    program=your_program,
    trainset=train_data,
    max_rounds=10
)
```

### 2. GEPA Configuration
```python
gepa = GEPA(
    metric=your_metric,
    # Budget control
    max_budget=100,
    max_rounds=10,
    # Sampling control
    temperature=0.7,
    top_p=0.9,
    # Optimization strategy
    strategy="generate-and-rerank",
    # Caching
    use_cache=True,
    cache_path="./gepa_cache"
)
```

### 3. Custom GEPA Strategies
```python
from dspy.optimizers.gepa import GenerateAndRerank, EvolveAndSelect

# Generate and rerank
strategy = GenerateAndRerank(
    n_candidates=10,
    reranker=your_reranker
)

# Evolve and select
strategy = EvolveAndSelect(
    population_size=20,
    mutation_rate=0.3,
    crossover_rate=0.4
)

gepa = GEPA(metric=your_metric, strategy=strategy)
```

### 4. GEPA with Fine-Tuning
```python
from dspy import GEPA, BootstrapFinetune

# Combine GEPA with fine-tuning
gepa = GEPA(metric=your_metric)
finetune = BootstrapFinetune(
    metric=your_metric,
    model_path="your-model-path"
)

# Two-stage optimization
optimized = gepa.optimize(program, train_data)
final = finetune.optimize(optimized, train_data)
```

## ⚠️ Pitfalls
- **Compute cost**: GEPA can be expensive
- **Overfitting**: Monitor dev set performance
- **Cache management**: Clear stale cache regularly
- **Strategy selection**: Choose strategy based on data size

## 📖 References
- [GEPA Documentation](https://dspy-docs.vercel.app/docs/deep-dive/optimization/gepa)
- [GEPA GitHub](https://github.com/stanfordnlp/dspy/tree/main/dspy/optimizers/gepa)