AgentExecutor

The agent to run for creating a plan and determining actions to take at each step of the execution loop.

The valid tools the agent can call.

Whether to return the agent's trajectory of intermediate steps at the end in addition to the final output.

The maximum number of steps to take before ending the execution loop.

Setting to 'None' could lead to an infinite loop.

The maximum amount of wall clock time to spend in the execution loop.

The method to use for early stopping if the agent never returns AgentFinish. Either 'force' or 'generate'.

"force" returns a string saying that it stopped because it met a time or iteration limit.

"generate" calls the agent's LLM Chain one final time to generate a final answer based on the previous steps.

How to handle errors raised by the agent's output parser. Defaults to False, which raises the error. If true, the error will be sent back to the LLM as an observation. If a string, the string itself will be sent to the LLM as an observation. If a callable function, the function will be called with the exception as an argument, and the result of that function will be passed to the agent as an observation.

How to trim the intermediate steps before returning them. Defaults to -1, which means no trimming.

Return the input keys.

Return the singular output key.

Create from agent and tools.

Validate that tools are compatible with agent.

Convert runnable to agent if passed in.

Raise error - saving not supported for Agent Executors.

Save the underlying agent.

Enables iteration over steps taken to reach final output.

Lookup tool by name.

Enables streaming over steps taken to reach final output.

Async enables streaming over steps taken to reach final output.