Model (autotransform.model.base)

The base class and associated classes for Model components.

class autotransform.model.base.Model

Bases: NamedComponent, Generic[TResultData]

The base for Model components. Used by AutoTransform to interact with AI models such as LLMs.

name

The name of the Component.

Type:

ClassVar[ModelName]

abstract get_result_for_item(item: FileItem) → Tuple[str, TResultData]

Gets a completion for a FileItem, usually used to find new file content.

Parameters:

item (FileItem) – The FileItem to get the result for.

Returns:

The result for the Item along with any information needed

for future completions with validation.

Return type:

Tuple[str, TResultData]

abstract get_result_with_validation(item: FileItem, result_data: TResultData, validation_failures: Sequence[ValidationResult]) → Tuple[str, TResultData]

Gets a new result based on ValidationResult issues.

Parameters:

• item (FileItem) – The FileItem to get the result for.

• result_data (TResultData) – The previously returned result data.

• validation_failures (Sequence[ValidationResult]) – The validation failures.

Returns:

The result for the failures along with any information needed

for future completions.

Return type:

Tuple[str, TResultData]

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

name: ClassVar[ModelName]

class autotransform.model.base.ModelName(value)

Bases: str, Enum

A simple enum for mapping.

OPEN_AI = 'open_ai'