pyrit.prompt_converter.CharacterSpaceConverter#
- class CharacterSpaceConverter[source]#
Bases:
PromptConverterSpaces out the input prompt and removes specified punctuations.
For more information on the bypass strategy, refer to: https://www.robustintelligence.com/blog-posts/bypassing-metas-llama-classifier-a-simple-jailbreak
Methods
__init__()Initialize the prompt converter.
convert_async(*, prompt[, input_type])Convert the given prompt by removing punctuation and spacing out characters.
convert_tokens_async(*, prompt[, ...])Convert substrings within a prompt that are enclosed by specified start and end tokens.
get_identifier()Return an identifier dictionary for the converter.
input_supported(input_type)Check if the input type is supported by the converter.
output_supported(output_type)Check if the output type is supported by the converter.
Attributes
Tuple of input modalities supported by this converter.
Tuple of output modalities supported by this converter.
supported_input_typesReturns a list of supported input types for the converter.
supported_output_typesReturns a list of supported output types for the converter.
- SUPPORTED_INPUT_TYPES: tuple[Literal['text', 'image_path', 'audio_path', 'video_path', 'binary_path', 'url', 'reasoning', 'error', 'function_call', 'tool_call', 'function_call_output'], ...] = ('text',)#
Tuple of input modalities supported by this converter. Subclasses must override this.
- SUPPORTED_OUTPUT_TYPES: tuple[Literal['text', 'image_path', 'audio_path', 'video_path', 'binary_path', 'url', 'reasoning', 'error', 'function_call', 'tool_call', 'function_call_output'], ...] = ('text',)#
Tuple of output modalities supported by this converter. Subclasses must override this.
- async convert_async(*, prompt: str, input_type: Literal['text', 'image_path', 'audio_path', 'video_path', 'binary_path', 'url', 'reasoning', 'error', 'function_call', 'tool_call', 'function_call_output'] = 'text') ConverterResult[source]#
Convert the given prompt by removing punctuation and spacing out characters.
- Parameters:
prompt (str) – The input text prompt to be converted.
input_type (PromptDataType) – The type of input data.
- Returns:
The result containing the converted text.
- Return type:
- Raises:
ValueError – If the input type is not supported.