Class Prompt (1.144.0)

Represents a prompt.

API documentation for dataset property.

API documentation for dataset_version property.

Returns the ID associated with the prompt resource.

Returns the ID associated with the prompt version resource.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Transforms a Prompt object into a list with a single genai_types.Content object.

This method replaces the variables in the prompt template with the values provided in prompt.prompt_data.variables. If no variables are provided, prompt.prompt_data.contents is returned as is. Only single-turn prompts are supported.

This can be used to call generate_content() in the Gen AI SDK.

Example usage:

my_prompt = types.Prompt( prompt_data=types.PromptData( model="gemini-2.0-flash-001", contents=[ genai_types.Content( parts=[ genai_types.Part(text="Hello {name}!"), ], ), ], variables=[ { "name": genai_types.Part(text="Alice"), }, ], ), )

from google import genai

genai_client = genai.Client(vertexai=True, project="my-project", location="us-central1") genai_client.models.generate_content( model=my_prompt.prompt_data.model, contents=my_prompt.assemble_contents(), )

This function is meant to behave like a BaseModel method to initialise private attributes.

It takes context as an argument since that's what pydantic-core passes when calling it.