pyrit.score.HumanInTheLoopScorerGradio

pyrit.score.HumanInTheLoopScorerGradio#

class HumanInTheLoopScorerGradio(*, open_browser=False, validator: ~pyrit.score.scorer_prompt_validator.ScorerPromptValidator | None = None, score_aggregator: ~typing.Callable[[~typing.Iterable[~pyrit.models.score.Score]], ~pyrit.score.score_aggregator_result.ScoreAggregatorResult] = <function _create_aggregator.<locals>.aggregator>)[source]#

Bases: TrueFalseScorer

Create scores from manual human input using Gradio and adds them to the database.

In the future this will not be a TrueFalseScorer. However, it is all that is supported currently.

__init__(*, open_browser=False, validator: ~pyrit.score.scorer_prompt_validator.ScorerPromptValidator | None = None, score_aggregator: ~typing.Callable[[~typing.Iterable[~pyrit.models.score.Score]], ~pyrit.score.score_aggregator_result.ScoreAggregatorResult] = <function _create_aggregator.<locals>.aggregator>) → None[source]#

Initialize the HumanInTheLoopScorerGradio.

Parameters:

  • open_browser (bool) – If True, the scorer will open the Gradio interface in a browser instead of opening it in PyWebview. Defaults to False.

  • validator (Optional[ScorerPromptValidator]) – Custom validator. Defaults to None.

  • score_aggregator (TrueFalseAggregatorFunc) – Aggregator for combining scores. Defaults to TrueFalseScoreAggregator.OR.

Methods

__init__(*[, open_browser, validator, ...])

Initialize the HumanInTheLoopScorerGradio.

get_identifier()

Get an identifier dictionary for the scorer.

get_scorer_metrics(dataset_name[, metrics_type])

Get evaluation statistics for the scorer using the dataset_name of the human labeled dataset.

retrieve_score(request_prompt, *[, objective])

Retrieve a score from the human evaluator through the RPC server.

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(message, *[, objective, ...])

Score the message, add the results to the database, and return a list of Score objects.

score_image_async(image_path, *[, objective])

Score the given image using the chat target.

score_image_batch_async(*, image_paths[, ...])

Score a batch of images asynchronously.

score_prompts_batch_async(*, messages[, ...])

Score multiple prompts in batches using the provided objectives.

score_response_async(*, response[, ...])

Score a response using an objective scorer and optional auxiliary scorers.

score_response_multiple_scorers_async(*, ...)

Score a response using multiple scorers in parallel.

score_text_async(text, *[, objective])

Scores the given text based on the task using the chat target.

validate_return_scores(scores)

Validate the scores returned by the scorer.

Attributes

scorer_type

retrieve_score(request_prompt: MessagePiece, *, objective: str | None = None) → list[Score][source]#

Retrieve a score from the human evaluator through the RPC server.

Parameters:

  • request_prompt (MessagePiece) – The message piece to be scored.

  • objective (Optional[str]) – The objective to evaluate against. Defaults to None.

Returns:

A list containing a single Score object from the human evaluator.

Return type:

list[Score]

Contents