test_ainvoke() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_ainvoke() — langchain Function Reference

Dependency Diagram

graph TD
  18292dbd_beee_e64a_4da9_4ad7746e2219["test_ainvoke()"]
  971e928f_9c9b_ce7a_b93d_e762f2f5aa54["ChatModelIntegrationTests"]
  18292dbd_beee_e64a_4da9_4ad7746e2219 -->|defined in| 971e928f_9c9b_ce7a_b93d_e762f2f5aa54
  style 18292dbd_beee_e64a_4da9_4ad7746e2219 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/standard-tests/langchain_tests/integration_tests/chat_models.py lines 770–798

    async def test_ainvoke(self, model: BaseChatModel) -> None:
        """Test to verify that `await model.ainvoke(simple_message)` works.

        This should pass for all integrations. Passing this test does not indicate
        a "natively async" implementation, but rather that the model can be used
        in an async context.

        ??? question "Troubleshooting"

            First, debug
            `langchain_tests.integration_tests.chat_models.ChatModelIntegrationTests.test_invoke`.
            because `ainvoke` has a default implementation that calls `invoke` in an
            async context.

            If that test passes but not this one, you should make sure your `_agenerate`
            method does not raise any exceptions, and that it returns a valid
            `langchain_core.outputs.chat_result.ChatResult` like so:

            ```python
            return ChatResult(
                generations=[ChatGeneration(message=AIMessage(content="Output text"))]
            )
            ```
        """
        result = await model.ainvoke("Hello")
        assert result is not None
        assert isinstance(result, AIMessage)
        assert isinstance(result.text, str)
        assert len(result.content) > 0