cuery.tool

Base classes for tools with well-defined input and output interfaces.

Tools are essentially wrappers of Tasks. But they use pydantic models to also define the input interface. The inputs are then used to customize a task’s prompt, response model and input context. They’re only really useful if a task’s prompt or response are configurable, e.g. a classification task with configurable number of classes.

Classes

Tool	Base class for all tools.

Module Contents

class cuery.tool.Tool(/, **data)

Bases: cuery.utils.Configurable, abc.ABC

Base class for all tools.

Subclasses need to implement prompt and response models; either statically as ClassVars, or dynamically as (executable) instance properties.

Parameters:

data (Any)

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

model: str = None

The LLM provider and model to use.

property response_model: cuery.response.ResponseClass

Abstractmethod:

Return type:

cuery.response.ResponseClass

Defines the response model for this tool (ClassVar or property).

property prompt: cuery.prompt.Prompt

Abstractmethod:

Return type:

cuery.prompt.Prompt

Defines the prompt for this tool (ClassVar or property).

property task: cuery.task.Task

Create a Task instance for this tool.

Return type:

cuery.task.Task

property context: cuery.context.AnyContext | None

Return type:

cuery.context.AnyContext | None

async __call__(**kwargs)

Return type:

cuery.response.Response | cuery.response.ResponseSet