pyrit.prompt_converter.PromptConverter

class PromptConverter

Bases: ABC, Identifier

Base class for converters that transform prompts into a different representation or format.

__init__()

Initializes the prompt converter.

Methods

__init__()	Initializes the prompt converter.
convert_async(*, prompt[, input_type])	Converts the given prompt into the target format supported by the converter.
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.

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

Converts the given prompt into the target format supported by the converter.

Parameters:

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

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

Returns:

The result containing the converted output and its type.

Return type:

ConverterResult

async convert_tokens_async(*, prompt: str, input_type: Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'reasoning', 'error'] = 'text', start_token: str = '⟪', end_token: str = '⟫') → ConverterResult

Converts substrings within a prompt that are enclosed by specified start and end tokens. If there are no tokens present, the entire prompt is converted.

Parameters:

• prompt (str) – The input prompt containing text to be converted.

• input_type (str) – The type of input data. Defaults to “text”.

• start_token (str) – The token indicating the start of a substring to be converted. Defaults to “⟪” which is relatively distinct.

• end_token (str) – The token indicating the end of a substring to be converted. Defaults to “⟫” which is relatively distinct.

Returns:

The prompt with specified substrings converted.

Return type:

str

Raises:

ValueError – If the input is inconsistent.

get_identifier()

Returns an identifier dictionary for the converter.

Returns:

The identifier dictionary.

Return type:

dict

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

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

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

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

property supported_input_types: list[Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'reasoning', 'error']]

Returns a list of supported input types for the converter.

Returns:

A list of supported input types.

Return type:

list[PromptDataType]

property supported_output_types: list[Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'reasoning', 'error']]

Returns a list of supported output types for the converter.

Returns:

A list of supported output types.

Return type:

list[PromptDataType]