pyrit.prompt_converter.TranslationConverter

pyrit.prompt_converter.TranslationConverter#

class TranslationConverter(*, converter_target: PromptChatTarget = REQUIRED_VALUE, language: str, prompt_template: SeedPrompt | None = None, max_retries: int = 3, max_wait_time_in_seconds: int = 60)[source]#

Bases: PromptConverter

Translates prompts into different languages using an LLM.

__init__(*, converter_target: PromptChatTarget = REQUIRED_VALUE, language: str, prompt_template: SeedPrompt | None = None, max_retries: int = 3, max_wait_time_in_seconds: int = 60)[source]#

Initialize the converter with the target chat support, language, and optional prompt template.

Parameters:

  • converter_target (PromptChatTarget) – The target chat support for the conversion which will translate. Can be omitted if a default has been configured via PyRIT initialization.

  • language (str) – The language for the conversion. E.g. Spanish, French, leetspeak, etc.

  • prompt_template (SeedPrompt, Optional) – The prompt template for the conversion.

  • max_retries (int) – Maximum number of retries for the conversion.

  • max_wait_time_in_seconds (int) – Maximum wait time in seconds between retries.

Raises:

  • ValueError – If converter_target is not provided and no default has been configured.

  • ValueError – If the language is not provided.

Methods

__init__(*[, converter_target, ...])

Initialize the converter with the target chat support, language, and optional prompt template.

convert_async(*, prompt[, input_type])

Convert the given prompt by translating it using the converter target.

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

SUPPORTED_INPUT_TYPES

Tuple of input modalities supported by this converter.

SUPPORTED_OUTPUT_TYPES

Tuple of output modalities supported by this converter.

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.
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 translating it using the converter target.

Parameters:

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

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

Returns:

The result containing the generated version of the prompt.

Return type:

ConverterResult

Raises:

ValueError – If the input type is not supported.

Contents