aiq.agent.reasoning_agent.reasoning_agent

Attributes

logger

Classes

ReasoningFunctionConfig

Defines an AgentIQ function that performs reasoning on the input data.

Functions

build_reasoning_function(config, builder)

Build a ReasoningFunction from the provided config.

Module Contents

logger

class ReasoningFunctionConfig(/, **data: Any)

Bases: aiq.data_models.function.FunctionBaseConfig

Defines an AgentIQ function that performs reasoning on the input data. Output is passed to the next function in the workflow.

Designed to be used with an InterceptingFunction.

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.

llm_name: aiq.data_models.component_ref.LLMRef = None

augmented_fn: aiq.data_models.component_ref.FunctionRef = None

verbose: bool = None

reasoning_prompt_template: str = None

instruction_prompt_template: str = None

async build_reasoning_function(

config: ReasoningFunctionConfig,

builder: aiq.builder.builder.Builder,

)

Build a ReasoningFunction from the provided config.

Args:

config (ReasoningFunctionConfig): The config for the ReasoningFunction. builder (Builder): The Builder instance to use for building the function.

Returns:

ReasoningFunction: The built ReasoningFunction.