pyrit.prompt_converter.MaliciousQuestionGeneratorConverter

pyrit.prompt_converter.MaliciousQuestionGeneratorConverter#

class MaliciousQuestionGeneratorConverter(*, converter_target: PromptChatTarget, prompt_template: SeedPrompt = None)[source]#

Bases: LLMGenericTextConverter

A PromptConverter that generates malicious questions using an LLM via an existing PromptTarget (like Azure OpenAI).

__init__(*, converter_target: PromptChatTarget, prompt_template: SeedPrompt = None)[source]#

Initializes the converter with a specific target and template.

Parameters:

  • converter_target (PromptChatTarget) – The endpoint that converts the prompt.

  • prompt_template (SeedPrompt) – The seed prompt template to use.

Methods

__init__(*, converter_target[, prompt_template])

Initializes the converter with a specific target and template.

convert_async(*, prompt[, input_type])

Convert a prompt based on the prompt template

convert_tokens_async(*, prompt[, ...])

Converts substrings within a prompt that are enclosed by specified start and end tokens.

get_identifier()

input_supported(input_type)

Checks if the input type is supported by the converter
async convert_async(*, prompt: str, input_type: Literal['text', 'image_path', 'audio_path', 'url', 'error'] = 'text') → ConverterResult[source]#

Convert a prompt based on the prompt template

Parameters:

  • prompt (str) – The prompt to convert.

  • input_type (PromptDataType, Optional) – The data type of the input prompt. Defaults to “text”.

Returns:

The result of the conversion, including the converted output text and output type.

Return type:

ConverterResult

Raises:

ValueError – If the input type is not supported.