langchain Architecture Docs
Home / Class/ CallbackManagerForLLMRun Class — langchain Architecture

CallbackManagerForLLMRun Class — langchain Architecture

Architecture documentation for the CallbackManagerForLLMRun class in manager.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  4a47bffe_726e_6355_d3b1_4c4ddbbd9cc8["CallbackManagerForLLMRun"]
  9ee9bc25_3f67_6972_bad7_11cbc05986ad["RunManager"]
  4a47bffe_726e_6355_d3b1_4c4ddbbd9cc8 -->|extends| 9ee9bc25_3f67_6972_bad7_11cbc05986ad
  ec453097_9dd7_3edc_a70f_a6b65b8f3e63["LLMManagerMixin"]
  4a47bffe_726e_6355_d3b1_4c4ddbbd9cc8 -->|extends| ec453097_9dd7_3edc_a70f_a6b65b8f3e63
  35cf5db6_bcb1_b854_6ebb_5e0368e51b58["manager.py"]
  4a47bffe_726e_6355_d3b1_4c4ddbbd9cc8 -->|defined in| 35cf5db6_bcb1_b854_6ebb_5e0368e51b58
  a390fcf8_5a1b_1fd6_01c0_9ee0dffae9b3["on_llm_new_token()"]
  4a47bffe_726e_6355_d3b1_4c4ddbbd9cc8 -->|method| a390fcf8_5a1b_1fd6_01c0_9ee0dffae9b3
  9460d0b1_4473_4b37_5ed1_65dcf90a8667["on_llm_end()"]
  4a47bffe_726e_6355_d3b1_4c4ddbbd9cc8 -->|method| 9460d0b1_4473_4b37_5ed1_65dcf90a8667
  5a30ab3c_c6bf_529b_8839_60cb2a22b4d4["on_llm_error()"]
  4a47bffe_726e_6355_d3b1_4c4ddbbd9cc8 -->|method| 5a30ab3c_c6bf_529b_8839_60cb2a22b4d4

Relationship Graph

Source Code

libs/core/langchain_core/callbacks/manager.py lines 672–750

class CallbackManagerForLLMRun(RunManager, LLMManagerMixin):
    """Callback manager for LLM run."""

    def on_llm_new_token(
        self,
        token: str,
        *,
        chunk: GenerationChunk | ChatGenerationChunk | None = None,
        **kwargs: Any,
    ) -> None:
        """Run when LLM generates a new token.

        Args:
            token: The new token.
            chunk: The chunk.
            **kwargs: Additional keyword arguments.

        """
        if not self.handlers:
            return
        handle_event(
            self.handlers,
            "on_llm_new_token",
            "ignore_llm",
            token=token,
            run_id=self.run_id,
            parent_run_id=self.parent_run_id,
            tags=self.tags,
            chunk=chunk,
            **kwargs,
        )

    def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
        """Run when LLM ends running.

        Args:
            response: The LLM result.
            **kwargs: Additional keyword arguments.

        """
        if not self.handlers:
            return
        handle_event(
            self.handlers,
            "on_llm_end",
            "ignore_llm",
            response,
            run_id=self.run_id,
            parent_run_id=self.parent_run_id,
            tags=self.tags,
            **kwargs,
        )

    def on_llm_error(
        self,
        error: BaseException,
        **kwargs: Any,
    ) -> None:
        """Run when LLM errors.

        Args:
            error: The error.
            **kwargs: Additional keyword arguments.

                - response (LLMResult): The response which was generated before
                    the error occurred.
        """
        if not self.handlers:
            return
        handle_event(
            self.handlers,
            "on_llm_error",
            "ignore_llm",
            error,
            run_id=self.run_id,
            parent_run_id=self.parent_run_id,
            tags=self.tags,
            **kwargs,
        )

Defined In

Extends

Source

Frequently Asked Questions

What is the CallbackManagerForLLMRun class?
CallbackManagerForLLMRun is a class in the langchain codebase, defined in libs/core/langchain_core/callbacks/manager.py.
Where is CallbackManagerForLLMRun defined?
CallbackManagerForLLMRun is defined in libs/core/langchain_core/callbacks/manager.py at line 672.
What does CallbackManagerForLLMRun extend?
CallbackManagerForLLMRun extends RunManager, LLMManagerMixin.

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free