pyrit.prompt_converter.TemplateSegmentConverter#

class TemplateSegmentConverter(*, prompt_template: SeedPrompt | None = None)[source]#

Bases: PromptConverter

Uses a template to randomly split a prompt into segments defined by the template.

This converter is a generalized version of this: https://adversa.ai/blog/universal-llm-jailbreak-chatgpt-gpt-4-bard-bing-anthropic-and-beyond/

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

Initializes the converter with the specified target and prompt template.

Parameters:

prompt_template (SeedPrompt, Optional) – The prompt template for the conversion. Must have two or more parameters. If not provided, uses the default tom_and_jerry.yaml template.

Raises:

ValueError – If the template has fewer than two parameters or if any parameter is missing in the template.

Methods

__init__(*[, prompt_template])

Initializes the converter with the specified target and prompt template.

convert_async(*, prompt[, input_type])

Converts the given prompt by splitting it into random segments and using them to fill the template parameters.

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

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

get_identifier()

Returns an identifier dictionary for the converter.

input_supported(input_type)

Checks if the input type is supported by the converter.

output_supported(output_type)

Checks if the output type is supported by the converter.

Attributes

supported_input_types

Returns a list of supported input types for the converter.

supported_output_types

Returns a list of supported output types for the converter.

async convert_async(*, prompt: str, input_type: Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'reasoning', 'error'] = 'text') ConverterResult[source]#

Converts the given prompt by splitting it into random segments and using them to fill the template parameters. The prompt is split into N segments (where N is the number of template parameters) at random word boundaries. Each segment is then used to fill the corresponding template parameter.

Parameters:
  • prompt (str) – The prompt to be converted.

  • input_type (PromptDataType) – The type of input data.

Returns:

The result containing the template filled with prompt segments.

Return type:

ConverterResult

Raises:

ValueError – If the input type is not supported.

input_supported(input_type: Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'reasoning', 'error']) bool[source]#

Checks if the input type is supported by the converter.

Parameters:

input_type (PromptDataType) – The input type to check.

Returns:

True if the input type is supported, False otherwise.

Return type:

bool

output_supported(output_type: Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'reasoning', 'error']) bool[source]#

Checks if the output type is supported by the converter.

Parameters:

output_type (PromptDataType) – The output type to check.

Returns:

True if the output type is supported, False otherwise.

Return type:

bool