nat.agent.responses_api_agent.register

Attributes

logger

Classes

ResponsesAPIAgentWorkflowConfig

Defines an NeMo Agent Toolkit function that uses a Responses API

Functions

responses_api_agent_workflow(config, builder)

Module Contents

logger

class ResponsesAPIAgentWorkflowConfig(/, **data: Any)

Bases: nat.data_models.function.FunctionBaseConfig

Defines an NeMo Agent Toolkit function that uses a Responses API 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.

llm_name: nat.data_models.component_ref.LLMRef = None

verbose: bool = None

nat_tools: list[nat.data_models.component_ref.FunctionRef] = None

mcp_tools: list[nat.data_models.openai_mcp.OpenAIMCPSchemaTool] = None

builtin_tools: list[dict[str, Any]] = None

max_iterations: int = None

description: str = None

parallel_tool_calls: bool = None

handle_tool_errors: bool = None

async responses_api_agent_workflow(

config: ResponsesAPIAgentWorkflowConfig,

builder: nat.builder.builder.Builder,

)