_generate() — langchain Function Reference

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

Function python LangChainCore Runnables

Entity Profile

LangChainCore→ Runnables→ _generate() — langchain Function Reference

Dependency Diagram

graph TD
  eaca9bb5_780b_83f3_2553_127322cb796b["_generate()"]
  1d1c5ebb_b952_3bf6_00c1_6dcb5a40551f["FakeChatOpenAI"]
  eaca9bb5_780b_83f3_2553_127322cb796b -->|defined in| 1d1c5ebb_b952_3bf6_00c1_6dcb5a40551f
  style eaca9bb5_780b_83f3_2553_127322cb796b fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/tests/unit_tests/runnables/test_openai_functions.py lines 20–41

    def _generate(
        self,
        messages: list[BaseMessage],
        stop: list[str] | None = None,
        run_manager: CallbackManagerForLLMRun | None = None,
        **kwargs: Any,
    ) -> ChatResult:
        return ChatResult(
            generations=[
                ChatGeneration(
                    message=AIMessage(
                        content="",
                        additional_kwargs={
                            "function_call": {
                                "name": "accept",
                                "arguments": '{\n  "draft": "turtles"\n}',
                            },
                        },
                    ),
                ),
            ],
        )