Add support for custom AgentExecutor

[rbbby]

In more advanced agents use cases, you often want to have greater control of the loop that controls how agents act.

The langchain AgentExecutor class has a method _take_next_step which is encouraged to be overridden in order to "(...) take control of how the agent makes and acts on choices." (https://github.com/hwchase17/langchain/blob/master/langchain/agents/agent.py#L748)

Trying to do so in conjunction with the newly added agent streaming support raises:
"Error! Chain type 'CustomAgentExecutor' is not currently supported by 'AsyncStreamingResponseCallback'."

To reproduce the error you can run examples/app/zero_shot_agent.py and replace the zero_shot_agent_dependency with a modified version of the function. This function creates a dummy custom subclass of AgentExecutor and initializes it manually rather than using the initialize_agent helper function as it currently does not support custom agent executors.

def zero_shot_agent_dependency() -> Callable[[], AgentExecutor]:
    @lru_cache(maxsize=1)
    def dependency() -> AgentExecutor:
        llm = ChatOpenAI(
            temperature=0,
            streaming=True,
        )
        tools = load_tools(["llm-math"], llm=llm)
        # Additional imports
        from langchain.agents import AgentExecutor
        from langchain.agents.loading import AGENT_TO_CLASS
        # Create dummy custom agent executor
        class CustomAgentExecutor(AgentExecutor):
            pass
        # Initialize agent without initialize_agent helper function
        agent = AgentType.ZERO_SHOT_REACT_DESCRIPTION
        agent_cls = AGENT_TO_CLASS[agent]
        agent_obj = agent_cls.from_llm_and_tools(llm, tools)
        agent = CustomAgentExecutor.from_agent_and_tools(
            agent=agent_obj,
            tools=tools,
            )
        return agent

    return dependency

Acceptance Criteria

• Running a subclass of AgentExecutor no longer raises an error

[ajndkr]

Hi! I need to update the error message here but you can already solve this by registering a custom callback handler. You can find the docs for it here: https://lanarky.readthedocs.io/en/latest/advanced/custom_callbacks.html

[rbbby]

@ajndkr thanks this works if I import register_streaming_callback instead of register_callback as shown in the docs as that raises an error.

Keeping the ticket open in the meantime but feel free to close it when you want.

[ajndkr]

you're right! i will update the docs.