def score_prompt_manually()

in pyrit/score/human_in_the_loop_scorer.py [0:0]

• 28 lines of code
• 5 McCabe index (conditional complexity)

    def score_prompt_manually(self, request_response: PromptRequestPiece, *, task: Optional[str] = None) -> list[Score]:
        """
        Manually score the prompt

        Args:
            request_response (PromptRequestPiece): The prompt request piece to score.
            task (str): The task based on which the text should be scored (the original attacker model's objective).

        Returns:
            list of scores
        """
        self.validate(request_response, task=task)

        score_value = ""
        score_category = ""
        while not score_value or not score_category:
            if not score_category:
                score_category = self._get_user_input("Please enter score category (e.g., 'hate' or 'violence').")

            if not score_value:
                message = f"""This prompt has not been scored yet, please manually score the prompt.
                The prompt is: {request_response.converted_value}\n
                Please enter a score value
                (e.g., 'True' for true_false or a value between '0.0' and '1.0 for float_scale): """

                score_value = self._get_user_input(message)
        score_type = self._get_score_type(score_value)
        score_value_description = self._get_user_input(
            "Enter score value description (optional, press 'Enter' to skip): "
        )
        score_rationale = self._get_user_input("Enter score rationale (optional, press 'Enter' to skip): ")
        score_metadata = self._get_user_input("Enter score metadata (optional, press 'Enter' to skip): ")

        score = Score(
            score_value=score_value,
            score_value_description=score_value_description,
            score_type=score_type,  # type: ignore
            score_category=score_category,
            score_rationale=score_rationale,
            score_metadata=score_metadata,
            scorer_class_identifier=self.get_identifier(),
            prompt_request_response_id=request_response.id,
            task=task,
        )

        return [score]