Opik Agent Optimizer API Reference

1
FewShotBayesianOptimizer(
2
    model: str,
3
    project_name: Optional = 'Optimization',
4
    min_examples: int = 2,
5
    max_examples: int = 8,
6
    seed: int = 42,
7
    n_threads: int = 8,
8
    verbose: int = 1,
9
    model_kwargs: None
10
)

1
evaluate_prompt(
2
    prompt: ChatPrompt,
3
    dataset: Dataset,
4
    metric: Callable,
5
    dataset_item_ids: Optional = None,
6
    experiment_config: Optional = None,
7
    optimization_id: Optional = None,
8
    n_samples: Optional = None
9
)

1
get_history()

1
optimize_prompt(
2
    prompt: ChatPrompt,
3
    dataset: Dataset,
4
    metric: Callable,
5
    n_trials: int = 10,
6
    experiment_config: Optional = None,
7
    n_samples: Optional = None
8
)

1
update_optimization(
2
    optimization: None,
3
    status: str
4
)

1
MetaPromptOptimizer(
2
    model: str,
3
    reasoning_model: Optional = None,
4
    rounds: int = 3,
5
    num_prompts_per_round: int = 4,
6
    num_threads: int = 12,
7
    project_name: str = 'Optimization',
8
    verbose: int = 1,
9
    enable_context: bool = True,
10
    model_kwargs: None
11
)

1
evaluate_prompt(
2
    prompt: ChatPrompt,
3
    dataset: Dataset,
4
    metric: Callable,
5
    use_full_dataset: bool = True,
6
    experiment_config: Optional = None,
7
    n_samples: Optional = None,
8
    optimization_id: Optional = None,
9
    verbose: int = 1
10
)

1
get_history()

1
optimize_prompt(
2
    prompt: ChatPrompt,
3
    dataset: Dataset,
4
    metric: Callable,
5
    experiment_config: Optional = None,
6
    n_samples: Optional = None,
7
    auto_continue: bool = False,
8
    kwargs: None
9
)

1
update_optimization(
2
    optimization: None,
3
    status: str
4
)

1
EvolutionaryOptimizer(
2
    model: str,
3
    project_name: str = 'Optimization',
4
    population_size: int = 30,
5
    num_generations: int = 15,
6
    mutation_rate: float = 0.2,
7
    crossover_rate: float = 0.8,
8
    tournament_size: int = 4,
9
    num_threads: int = 12,
10
    elitism_size: int = 3,
11
    adaptive_mutation: bool = True,
12
    enable_moo: bool = True,
13
    enable_llm_crossover: bool = True,
14
    seed: Optional = 42,
15
    output_style_guidance: Optional = None,
16
    infer_output_style: bool = False,
17
    verbose: int = 1,
18
    model_kwargs: None
19
)

1
evaluate_prompt(
2
    prompt: ChatPrompt,
3
    dataset: Dataset,
4
    metric: Callable,
5
    n_samples: Optional = None,
6
    dataset_item_ids: Optional = None,
7
    experiment_config: Optional = None,
8
    optimization_id: Optional = None,
9
    verbose: int = 0
10
)

1
get_history()

1
get_llm_crossover_system_prompt()

1
optimize_prompt(
2
    prompt: ChatPrompt,
3
    dataset: Dataset,
4
    metric: Callable,
5
    experiment_config: Optional = None,
6
    n_samples: Optional = None,
7
    auto_continue: bool = False,
8
    kwargs: None
9
)

1
update_optimization(
2
    optimization: None,
3
    status: str
4
)

1
ChatPrompt(
2
    system: Optional = None,
3
    prompt: Optional = None,
4
    messages: Optional = None,
5
    tools: Optional = None
6
)

1
format(
2
    kwargs: Any
3
)

1
to_dict()

1
OptimizationResult(
2
    optimizer: <class 'str'> = 'Optimizer',
3
    prompt: List[Dict[Literal['role', 'content'], str]],
4
    score: <class 'float'>,
5
    metric_name: <class 'str'>,
6
    initial_prompt: Optional[List[Dict[Literal['role', 'content'], str]]] = None,
7
    initial_score: Optional[float] = None,
8
    details: Dict[str, Any] = PydanticUndefined,
9
    history: List[Dict[str, Any]] = [],
10
    llm_calls: Optional[int] = None,
11
    demonstrations: Optional[List[Dict[str, Any]]] = None,
12
    mipro_prompt: Optional[str] = None,
13
    tool_prompts: Optional[Dict[str, str]] = None
14
)