Class AsyncPromptOptimizer (1.121.0)

AsyncPromptOptimizer(api_client_: google.genai._api_client.BaseApiClient)

Prompt Optimizer

Methods

optimize

optimize(
    method: str,
    config: typing.Union[
        vertexai._genai.types.PromptOptimizerVAPOConfig,
        vertexai._genai.types.PromptOptimizerVAPOConfigDict,
    ],
) -> vertexai._genai.types.CustomJob

Call async Vertex AI Prompt Optimizer (VAPO).

Note: The wait_for_completion parameter in the config will be ignored when using the AsyncClient, as it is not supported.

Example usage: client = vertexai.Client(project=PROJECT_NAME, location='us-central1') vapo_config = vertexai.types.PromptOptimizerVAPOConfig( config_path='gs://you-bucket-name/your-config.json', service_account=service_account, ) job = await client.aio.prompt_optimizer.optimize( method='vapo', config=vapo_config)

optimize_prompt

optimize_prompt(
    *, prompt: str, config: typing.Optional[vertexai._genai.types.OptimizeConfig] = None
) -> vertexai._genai.types.OptimizeResponse

Makes an async request to _optimize_prompt and returns an optimized prompt.

Example usage: client = vertexai.Client(project=PROJECT_NAME, location='us-central1') prompt = "Generate system instructions for analyzing medical articles" response = await client.aio.prompt_optimizer.optimize_prompt(prompt=prompt)