on_chat_model_start() — langchain Function Reference

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

Function python Observability Tracers calls 2

Entity Profile

Observability→ Tracers→ on_chat_model_start() — langchain Function Reference

Dependency Diagram

graph TD
  68b325b2_a4ee_6bd3_7e65_01239a5c497c["on_chat_model_start()"]
  178590bb_85ff_b79e_979a_46e5c3c5389f["LangChainTracer"]
  68b325b2_a4ee_6bd3_7e65_01239a5c497c -->|defined in| 178590bb_85ff_b79e_979a_46e5c3c5389f
  1a52c867_8259_f52c_1ade_c23b7b18c690["_start_trace()"]
  68b325b2_a4ee_6bd3_7e65_01239a5c497c -->|calls| 1a52c867_8259_f52c_1ade_c23b7b18c690
  1f28ee91_49f8_e93f_e967_a9380e8e96a7["_on_chat_model_start()"]
  68b325b2_a4ee_6bd3_7e65_01239a5c497c -->|calls| 1f28ee91_49f8_e93f_e967_a9380e8e96a7
  style 68b325b2_a4ee_6bd3_7e65_01239a5c497c fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/tracers/langchain.py lines 152–196

    def on_chat_model_start(
        self,
        serialized: dict[str, Any],
        messages: list[list[BaseMessage]],
        *,
        run_id: UUID,
        tags: list[str] | None = None,
        parent_run_id: UUID | None = None,
        metadata: dict[str, Any] | None = None,
        name: str | None = None,
        **kwargs: Any,
    ) -> Run:
        """Start a trace for an LLM run.

        Args:
            serialized: The serialized model.
            messages: The messages.
            run_id: The run ID.
            tags: The tags.
            parent_run_id: The parent run ID.
            metadata: The metadata.
            name: The name.
            **kwargs: Additional keyword arguments.

        Returns:
            The run.
        """
        start_time = datetime.now(timezone.utc)
        if metadata:
            kwargs.update({"metadata": metadata})
        chat_model_run = Run(
            id=run_id,
            parent_run_id=parent_run_id,
            serialized=serialized,
            inputs={"messages": [[dumpd(msg) for msg in batch] for batch in messages]},
            extra=kwargs,
            events=[{"name": "start", "time": start_time}],
            start_time=start_time,
            run_type="llm",
            tags=tags,
            name=name,
        )
        self._start_trace(chat_model_run)
        self._on_chat_model_start(chat_model_run)
        return chat_model_run