latent.agents.eval.classifier

Classifier[T] -- semantic alias for classification tasks (FR-1.5).

Classes

Classifier

Classifier(name: str, model: str, output_type: type[T], prompt_template: str | None = None, system_prompt: str | None = None, few_shot: Sequence[Message] | None = None, temperature: float = 0.0, max_tokens: int = 4096, is_eligible: Callable[[dict], bool] | None = None, row_mapper: Callable[[dict], dict] | None = None, column_prefix: str | None = None, kwargs: Any = {})

LLM agent specialized for classifying data rows.

Identical to Judge — exists as a semantic alias for classification tasks where the output model typically has a 'prediction' field.

The one behavioural difference: a plain-label prediction carries no rubric to generate, so an output model with no score annotations is expected here and gets the bare template. The same model would raise for a Judge, where a missing rubric means the scores measure nothing.