aiq.agent.react_agent.register

Attributes

logger

Classes

ReActAgentWorkflowConfig

Defines an AgentIQ function that uses a ReAct Agent performs reasoning inbetween tool calls, and utilizes the tool

Functions

react_agent_workflow(config, builder)

Module Contents

logger

class ReActAgentWorkflowConfig(/, **data: Any)

Bases: aiq.data_models.function.FunctionBaseConfig

Defines an AgentIQ function that uses a ReAct Agent performs reasoning inbetween tool calls, and utilizes the tool names and descriptions to select the optimal tool.

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

retry_parsing_errors: bool = None

max_retries: int = None

include_tool_input_schema_in_tool_description: bool = None

max_iterations: int = None

description: str = None

system_prompt: str | None = None

max_history: int = None

use_openai_api: bool = None

additional_instructions: str | None = None

async react_agent_workflow(

config: ReActAgentWorkflowConfig,

builder: aiq.builder.builder.Builder,

)