pyrit.prompt_target.OpenAIImageTarget

pyrit.prompt_target.OpenAIImageTarget#

class OpenAIImageTarget(image_size: Literal['256x256', '512x512', '1024x1024', '1536x1024', '1024x1536'] = '1024x1024', quality: Literal['standard', 'hd', 'low', 'medium', 'high'] | None = None, style: Literal['natural', 'vivid'] | None = None, *args, **kwargs)[source]#

Bases: OpenAITarget

A target for image generation using OpenAI’s image models.

__init__(image_size: Literal['256x256', '512x512', '1024x1024', '1536x1024', '1024x1536'] = '1024x1024', quality: Literal['standard', 'hd', 'low', 'medium', 'high'] | None = None, style: Literal['natural', 'vivid'] | None = None, *args, **kwargs)[source]#

Initialize the image target with specified parameters.

Parameters:

  • model_name (str, Optional) – The name of the model.

  • endpoint (str, Optional) – The target URL for the OpenAI service.

  • api_key (str, Optional) – The API key for accessing the Azure OpenAI service. Defaults to the OPENAI_IMAGE_API_KEY environment variable.

  • headers (str, Optional) – Headers of the endpoint (JSON).

  • use_entra_auth (bool, Optional) – When set to True, user authentication is used instead of API Key. DefaultAzureCredential is taken for https://cognitiveservices.azure.com/.default . Please run az login locally to leverage user AuthN.

  • max_requests_per_minute (int, Optional) – Number of requests the target can handle per minute before hitting a rate limit. The number of requests sent to the target will be capped at the value provided.

  • image_size (Literal["256x256", "512x512", "1024x1024"], Optional) – The size of the generated images. Defaults to “1024x1024”.

  • quality (Literal["standard", "hd", "low", "medium", "high"], Optional) – The quality of the generated images. Different models support different quality settings. For DALL-E-3, there’s “standard” and “hd”. For newer models, there are “low”, “medium”, and “high”. Default is to not specify.

  • style (Literal["natural", "vivid"], Optional) – The style of the generated images. Default is to not specify.

  • *args – Additional positional arguments to be passed to AzureOpenAITarget.

  • **kwargs – Additional keyword arguments to be passed to AzureOpenAITarget.

  • httpx_client_kwargs (dict, Optional) – Additional kwargs to be passed to the httpx.AsyncClient() constructor. For example, to specify a 3 minutes timeout: httpx_client_kwargs={“timeout”: 180}

Methods

__init__([image_size, quality, style])

Initialize the image target with specified parameters.

dispose_db_engine()

Dispose database engine to release database connections and resources.

get_identifier()

is_json_response_supported()

Indicates that this target supports JSON response format.

is_response_format_json(message_piece)

Checks if the response format is JSON and ensures the target supports it.

send_prompt_async(**kwargs)

Sends a normalized prompt async to the prompt target.

set_model_name(*, model_name)

Set the model name for this target.

set_system_prompt(*, system_prompt, ...[, ...])

Sets the system prompt for the prompt target.

Attributes

ADDITIONAL_REQUEST_HEADERS

model_name_environment_variable

endpoint_environment_variable

api_key_environment_variable

supported_converters

api_key_environment_variable: str#
endpoint_environment_variable: str#
is_json_response_supported() → bool[source]#

Indicates that this target supports JSON response format.

model_name_environment_variable: str#
async send_prompt_async(**kwargs)#

Sends a normalized prompt async to the prompt target.

Returns:

A list of message responses. Most targets return a single message,

but some (like response target with tool calls) may return multiple messages.

Return type:

list[Message]

Contents