Prompt optimizer

Overview

The Prompt Optimizer module provides algorithms for automatically improving LLM prompts based on evaluation metrics. It uses Optuna for hyperparameter optimization.

Available algorithms

Algorithm	Description
GEPA	Genetic Evolution Prompt Algorithm — evolves prompts through selection and mutation
MIPROv2	Multi-Instance Prompt Optimization v2 — generates and evaluates prompt candidates

Usage

from gaussia.prompt_optimizer import PromptOptimizer

optimizer = PromptOptimizer(
    algorithm="gepa",
    n_trials=50,
)

best_prompt = optimizer.optimize(
    initial_prompt="You are a helpful assistant.",
    evaluation_fn=my_evaluation_function,
)

Requires the prompt-optimizer extra: pip install "gaussia[prompt-optimizer]".

Generators Explainability

Getting started

Core concepts

Metrics

Integrations

Advanced

Prompt optimizer

Overview

Available algorithms

Usage

​Overview

​Available algorithms

​Usage

Overview

Available algorithms

Usage