test_stop_sequence() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_stop_sequence() — langchain Function Reference

Dependency Diagram

graph TD
  5011ea30_0807_be85_a58d_8611d0aa41af["test_stop_sequence()"]
  971e928f_9c9b_ce7a_b93d_e762f2f5aa54["ChatModelIntegrationTests"]
  5011ea30_0807_be85_a58d_8611d0aa41af -->|defined in| 971e928f_9c9b_ce7a_b93d_e762f2f5aa54
  style 5011ea30_0807_be85_a58d_8611d0aa41af fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/standard-tests/langchain_tests/integration_tests/chat_models.py lines 1514–1550

    def test_stop_sequence(self, model: BaseChatModel) -> None:
        """Test that model does not fail when invoked with the `stop` parameter.

        The `stop` parameter is a standard parameter for stopping generation at a
        certain token.

        [More on standard parameters](https://python.langchain.com/docs/concepts/chat_models/#standard-parameters).

        This should pass for all integrations.

        ??? question "Troubleshooting"

            If this test fails, check that the function signature for `_generate`
            (as well as `_stream` and async variants) accepts the `stop` parameter:

            ```python
            def _generate(
                self,
                messages: List[BaseMessage],
                stop: list[str] | None = None,
                run_manager: CallbackManagerForLLMRun | None = None,
                **kwargs: Any,
            ) -> ChatResult:

            ```
        """
        result = model.invoke("hi", stop=["you"])
        assert isinstance(result, AIMessage)

        custom_model = self.chat_model_class(
            **{
                **self.chat_model_params,
                "stop": ["you"],
            }
        )
        result = custom_model.invoke("hi")
        assert isinstance(result, AIMessage)