on_llm_start() — langchain Function Reference

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

Function python Observability TelemetryUtilities

Entity Profile

Observability→ TelemetryUtilities→ on_llm_start() — langchain Function Reference

Dependency Diagram

graph TD
  eaa769c1_d32a_ef50_fa66_f5810a38668d["on_llm_start()"]
  6b65bf57_0fa9_b411_5886_294d6dbe5842["StreamingStdOutCallbackHandler"]
  eaa769c1_d32a_ef50_fa66_f5810a38668d -->|defined in| 6b65bf57_0fa9_b411_5886_294d6dbe5842
  style eaa769c1_d32a_ef50_fa66_f5810a38668d fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/callbacks/streaming_stdout.py lines 24–33

    def on_llm_start(
        self, serialized: dict[str, Any], prompts: list[str], **kwargs: Any
    ) -> None:
        """Run when LLM starts running.

        Args:
            serialized: The serialized LLM.
            prompts: The prompts to run.
            **kwargs: Additional keyword arguments.
        """