pyrit.score.SelfAskLikertScorer

pyrit.score.SelfAskLikertScorer#

class SelfAskLikertScorer(chat_target: PromptChatTarget, likert_scale_path: Path)[source]#

A class that represents a “self-ask” score for text scoring for a likert scale.

__init__(chat_target: PromptChatTarget, likert_scale_path: Path) → None[source]#

Methods

`__init__`(chat_target, likert_scale_path)
`get_identifier`()	Returns an identifier dictionary for the scorer.
`scale_value_float`(value, min_value, max_value)	Scales a value from 0 to 1 based on the given min and max values.
`score_async`(request_response, *[, task])	Scores the given request_response using "self-ask" for the chat target and adds score to memory.
`score_image_async`(image_path, *[, task])	Scores the given image using the chat target.
`score_prompts_batch_async`(*, request_responses)
`score_text_async`(text, *[, task])	Scores the given text based on the task using the chat target.
`validate`(request_response, *[, task])	Validates the request_response piece to score.

Attributes

scorer_type

async score_async(request_response: PromptRequestPiece, *, task: str | None = None) → list[Score][source]#

Scores the given request_response using “self-ask” for the chat target and adds score to memory.

Parameters:

request_response (PromptRequestPiece) – The prompt request piece containing the text to be scored.
task (str) – The task based on which the text should be scored (the original attacker model’s objective). Currently not supported for this scorer.

Returns:

The request_response scored.: The category is configured from the likert_scale. The score_value is a value from [0,1] that is scaled from the likert scale.

Return type:

list[Score]

validate(request_response: PromptRequestPiece, *, task: str | None = None)[source]#

Validates the request_response piece to score. Because some scorers may require specific PromptRequestPiece types or values.

Parameters:

request_response (PromptRequestPiece) – The request response to be validated.
task (str) – The task based on which the text should be scored (the original attacker model’s objective).