Class Prompt (1.129.0)

Version latest

• 1.122.0 (latest)
• 1.121.0
• 1.120.0
• 1.119.0
• 1.118.0
• 1.117.0
• 1.95.1
• 1.94.0
• 1.93.1
• 1.92.0
• 1.91.0
• 1.90.0
• 1.89.0
• 1.88.0
• 1.87.0
• 1.86.0
• 1.85.0
• 1.84.0
• 1.83.0
• 1.82.0
• 1.81.0
• 1.80.0
• 1.79.0
• 1.78.0
• 1.77.0
• 1.76.0
• 1.75.0
• 1.74.0
• 1.73.0
• 1.72.0
• 1.71.1
• 1.70.0
• 1.69.0
• 1.68.0
• 1.67.1
• 1.66.0
• 1.65.0
• 1.63.0
• 1.62.0
• 1.60.0
• 1.59.0

Prompt()

Represents a prompt.

Properties

dataset

API documentation for dataset property.

dataset_version

API documentation for dataset_version property.

prompt_id

Returns the ID associated with the prompt resource.

version_id

Returns the ID associated with the prompt version resource.

Methods

Prompt

Prompt()

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.

assemble_contents

assemble_contents() -> list[google.genai.types.Content]

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(), )

model_post_init

model_post_init(context: Any, /) -> None

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.