aplan() — langchain Function Reference

Architecture documentation for the aplan() function in base.py from the langchain codebase.

Function python AgentOrchestration ToolInterface

Entity Profile

AgentOrchestration→ ToolInterface→ aplan() — langchain Function Reference

Dependency Diagram

graph TD
  b6e57bb0_10c3_3ee9_0c58_8dc9d4b47668["aplan()"]
  b444f628_93a3_fafc_0827_7b9ca1eef67c["OpenAIFunctionsAgent"]
  b6e57bb0_10c3_3ee9_0c58_8dc9d4b47668 -->|defined in| b444f628_93a3_fafc_0827_7b9ca1eef67c
  style b6e57bb0_10c3_3ee9_0c58_8dc9d4b47668 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/openai_functions_agent/base.py lines 137–168

    async def aplan(
        self,
        intermediate_steps: list[tuple[AgentAction, str]],
        callbacks: Callbacks = None,
        **kwargs: Any,
    ) -> AgentAction | AgentFinish:
        """Async given input, decided what to do.

        Args:
            intermediate_steps: Steps the LLM has taken to date,
                along with observations.
            callbacks: Callbacks to use.
            **kwargs: User inputs.

        Returns:
            Action specifying what tool to use.
            If the agent is finished, returns an AgentFinish.
            If the agent is not finished, returns an AgentAction.
        """
        agent_scratchpad = format_to_openai_function_messages(intermediate_steps)
        selected_inputs = {
            k: kwargs[k] for k in self.prompt.input_variables if k != "agent_scratchpad"
        }
        full_inputs = dict(**selected_inputs, agent_scratchpad=agent_scratchpad)
        prompt = self.prompt.format_prompt(**full_inputs)
        messages = prompt.to_messages()
        predicted_message = await self.llm.ainvoke(
            messages,
            functions=self.functions,
            callbacks=callbacks,
        )
        return self.output_parser.parse_ai_message(predicted_message)