Skip to content

pydantic_ai.models.test

Utilities for testing apps built with PydanticAI.

TestModel dataclass

Bases: Model

A model specifically for testing purposes.

This will (by default) call all retrievers in the agent model, then return a tool response if possible, otherwise a plain response.

How useful this function will be is unknown, it may be useless, it may require significant changes to be useful.

Apart from __init__ derived by the dataclass decorator, all methods are private or match those of the base class.

call_retrievers class-attribute instance-attribute

call_retrievers: list[str] | Literal['all'] = 'all'

List of retrievers to call. If 'all', all retrievers will be called.

custom_result_text class-attribute instance-attribute

custom_result_text: str | None = None

If set, this text is return as teh final result.

custom_result_args class-attribute instance-attribute

custom_result_args: Any | None = None

If set, these args will be passed to the result tool.

seed class-attribute instance-attribute

seed: int = 0

Seed for generating random data.

TestAgentModel dataclass

Bases: AgentModel

Implementation of AgentModel for testing purposes.