aiq.agent.tool_calling_agent.register

Attributes

logger

Classes

ToolCallAgentWorkflowConfig

A Tool Calling Agent requires an LLM which supports tool calling. A tool Calling Agent utilizes the tool

Functions

tool_calling_agent_workflow(config, builder)

Module Contents

logger

class ToolCallAgentWorkflowConfig(/, **data: Any)

Bases: aiq.data_models.function.FunctionBaseConfig

A Tool Calling Agent requires an LLM which supports tool calling. A tool Calling Agent utilizes the tool input parameters to select the optimal tool. Supports handling tool errors.

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.

tool_names: list[aiq.data_models.component_ref.FunctionRef] = None

llm_name: aiq.data_models.component_ref.LLMRef = None

verbose: bool = None

handle_tool_errors: bool = None

description: str = None

max_iterations: int = None

async tool_calling_agent_workflow(

config: ToolCallAgentWorkflowConfig,

builder: aiq.builder.builder.Builder,

)