AgentExecutorIterator#

class langchain.agents.agent_iterator.AgentExecutorIterator(

agent_executor: AgentExecutor,

inputs: Any,

callbacks: Callbacks = None,

*,

tags: list[str] | None = None,

metadata: dict[str, Any] | None = None,

run_name: str | None = None,

run_id: UUID | None = None,

include_run_info: bool = False,

yield_actions: bool = False,

)[source]#

Iterator for AgentExecutor.

Initialize the AgentExecutorIterator with the given AgentExecutor, inputs, and optional callbacks.

Parameters:

• agent_executor (AgentExecutor) – The AgentExecutor to iterate over.

• inputs (Any) – The inputs to the AgentExecutor.

• callbacks (Callbacks, optional) – The callbacks to use during iteration. Defaults to None.

• tags (Optional[list[str]], optional) – The tags to use during iteration. Defaults to None.

• metadata (Optional[Dict[str, Any]], optional) – The metadata to use during iteration. Defaults to None.

• run_name (Optional[str], optional) – The name of the run. Defaults to None.

• run_id (Optional[UUID], optional) – The ID of the run. Defaults to None.

• include_run_info (bool, optional) – Whether to include run info in the output. Defaults to False.

• yield_actions (bool, optional) – Whether to yield actions as they are generated. Defaults to False.

Attributes

agent_executor	The AgentExecutor to iterate over.
color_mapping	A mapping of tool names to colors.
inputs	The inputs to the AgentExecutor.
name_to_tool_map	A mapping of tool names to tools.

Methods

__init__(agent_executor, inputs[, ...])	Initialize the AgentExecutorIterator with the given AgentExecutor, inputs, and optional callbacks.
make_final_outputs(outputs, run_manager)	Make final outputs for the iterator.
reset()	Reset the iterator to its initial state, clearing intermediate steps, iterations, and time elapsed.
update_iterations()	Increment the number of iterations and update the time elapsed.

__init__(

agent_executor: AgentExecutor,

inputs: Any,

callbacks: Callbacks = None,

*,

tags: list[str] | None = None,

metadata: dict[str, Any] | None = None,

run_name: str | None = None,

run_id: UUID | None = None,

include_run_info: bool = False,

yield_actions: bool = False,

)[source]#

Initialize the AgentExecutorIterator with the given AgentExecutor, inputs, and optional callbacks.

Parameters:

• agent_executor (AgentExecutor) – The AgentExecutor to iterate over.

• inputs (Any) – The inputs to the AgentExecutor.

• callbacks (Callbacks, optional) – The callbacks to use during iteration. Defaults to None.

• tags (Optional[list[str]], optional) – The tags to use during iteration. Defaults to None.

• metadata (Optional[Dict[str, Any]], optional) – The metadata to use during iteration. Defaults to None.

• run_name (Optional[str], optional) – The name of the run. Defaults to None.

• run_id (Optional[UUID], optional) – The ID of the run. Defaults to None.

• include_run_info (bool, optional) – Whether to include run info in the output. Defaults to False.

• yield_actions (bool, optional) – Whether to yield actions as they are generated. Defaults to False.

make_final_outputs(

outputs: dict[str, Any],

run_manager: CallbackManagerForChainRun | AsyncCallbackManagerForChainRun,

) → AddableDict[source]#

Make final outputs for the iterator.

Parameters:

• outputs (dict[str, Any]) – The outputs from the agent executor.

• run_manager (CallbackManagerForChainRun | AsyncCallbackManagerForChainRun) – The run manager to use for callbacks.

Return type:

AddableDict

reset() → None[source]#

Reset the iterator to its initial state, clearing intermediate steps, iterations, and time elapsed.

Return type:

None

update_iterations() → None[source]#

Increment the number of iterations and update the time elapsed.

Return type:

None