on_chat_model_start() — langchain Function Reference

Architecture documentation for the on_chat_model_start() function in manager.py from the langchain codebase.

Function python Observability CallbackManager calls 2 called by 1

Entity Profile

Observability→ CallbackManager→ on_chat_model_start() — langchain Function Reference

Dependency Diagram

graph TD
  fd9cf5b0_df49_0a9e_1f92_c0f24cb802a3["on_chat_model_start()"]
  90ea8982_7d84_5e8f_4b5a_533f89fc7211["AsyncCallbackManager"]
  fd9cf5b0_df49_0a9e_1f92_c0f24cb802a3 -->|defined in| 90ea8982_7d84_5e8f_4b5a_533f89fc7211
  a6207573_f43a_6004_ebfd_c9da6a0f2d8f["on_chat_model_start()"]
  a6207573_f43a_6004_ebfd_c9da6a0f2d8f -->|calls| fd9cf5b0_df49_0a9e_1f92_c0f24cb802a3
  a6207573_f43a_6004_ebfd_c9da6a0f2d8f["on_chat_model_start()"]
  fd9cf5b0_df49_0a9e_1f92_c0f24cb802a3 -->|calls| a6207573_f43a_6004_ebfd_c9da6a0f2d8f
  3a243d21_72d1_dca9_f7be_acbb482b9f86["ahandle_event()"]
  fd9cf5b0_df49_0a9e_1f92_c0f24cb802a3 -->|calls| 3a243d21_72d1_dca9_f7be_acbb482b9f86
  style fd9cf5b0_df49_0a9e_1f92_c0f24cb802a3 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/callbacks/manager.py lines 1873–1942

    async def on_chat_model_start(
        self,
        serialized: dict[str, Any],
        messages: list[list[BaseMessage]],
        run_id: UUID | None = None,
        **kwargs: Any,
    ) -> list[AsyncCallbackManagerForLLMRun]:
        """Async run when LLM starts running.

        Args:
            serialized: The serialized LLM.
            messages: The list of messages.
            run_id: The ID of the run.
            **kwargs: Additional keyword arguments.

        Returns:
            The list of async callback managers, one for each LLM run corresponding to
            each inner message list.
        """
        inline_tasks = []
        non_inline_tasks = []
        managers = []

        for message_list in messages:
            if run_id is not None:
                run_id_ = run_id
                run_id = None
            else:
                run_id_ = uuid7()

            for handler in self.handlers:
                task = ahandle_event(
                    [handler],
                    "on_chat_model_start",
                    "ignore_chat_model",
                    serialized,
                    [message_list],
                    run_id=run_id_,
                    parent_run_id=self.parent_run_id,
                    tags=self.tags,
                    metadata=self.metadata,
                    **kwargs,
                )
                if handler.run_inline:
                    inline_tasks.append(task)
                else:
                    non_inline_tasks.append(task)

            managers.append(
                AsyncCallbackManagerForLLMRun(
                    run_id=run_id_,
                    handlers=self.handlers,
                    inheritable_handlers=self.inheritable_handlers,
                    parent_run_id=self.parent_run_id,
                    tags=self.tags,
                    inheritable_tags=self.inheritable_tags,
                    metadata=self.metadata,
                    inheritable_metadata=self.inheritable_metadata,
                )
            )

        # Run inline tasks sequentially
        for task in inline_tasks:
            await task

        # Run non-inline tasks concurrently
        if non_inline_tasks:
            await asyncio.gather(*non_inline_tasks)

        return managers