TransformersTextualQandA

Textual Q&A task

Subclass of Task.

Module: implementation.tasks

Default predictor

This task uses TransformersModel by default with this configuration:

TransformersPipeline(
    TransformersPipelineConfig(
        task="question-answering", 
        model="deepset/roberta-base-squad2"
    ),
    input_class=TransformersTextualQandAInput,
    output_class=TransformersTextualQandAOutput
)

See:

• TransformersPipeline

• TransformersPipelineConfig

• TransformersTextualQandAInput

• TransformersTextualQandAOutput

Methods and properties

Main methods and properties

---

__init__

Arguments:

• predictor (Predictor[Any, Any], optional): Predictor that will be used in task. If equals to None, default predictor will be used. Defaults to None.

• preprocess (Optional[Component], optional): Component executed before predictor. Defaults to None.

• postprocess (Optional[Component], optional): Component executed after predictor. Defaults to None.

• input_class (Type[Input], optional): Class for input validation. Defaults to TransformersTextualQandAInput.

• output_class (Type[Output], optional): Class for output validation. Defaults to TransformersTextualQandAOutput.

• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

---

---

QandAPostprocess

Check if answer score is higher than threshold. Subclass of Action. Type of Action[Dict[str, Any], Dict[str, Any]].

---

__init__

Arguments:

• threshold (float): Entities threshold score. Defaults to 0.

• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "answer" (Optional[str], optional);

  • "score" (float);

Returns:

• Dict[str, Any]: Expected keys:

  • "answer" (Optional[str], optional);

  • "score" (float);

---

---