autointent.OptimizationConfig

class autointent.OptimizationConfig(/, **data)

Bases: pydantic.BaseModel

Configuration for the optimization process.

One can use it to customize optimization beyond choosing different preset. Instantiate it and pass to autointent.Pipeline.from_optimization_config().

Parameters:

data (Any)

data_config: autointent.configs.DataConfig

search_space: list[dict[str, Any]]

See tutorial on search space customization.

logging_config: autointent.configs.LoggingConfig

See tutorial on logging configuration.

embedder_config: autointent.configs.EmbedderConfig

cross_encoder_config: autointent.configs.CrossEncoderConfig

sampler: autointent.custom_types.SamplerType = 'brute'

See tutorial on optuna and presets.

seed: pydantic.PositiveInt = 42