test_openai_client_caching() — langchain Function Reference

Architecture documentation for the test_openai_client_caching() function in test_base.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_openai_client_caching() — langchain Function Reference

Dependency Diagram

graph TD
  e0201335_c5a0_ac8d_759a_b875ca7815f8["test_openai_client_caching()"]
  48232d20_f8c1_b597_14fa_7dc407e9bfe5["test_base.py"]
  e0201335_c5a0_ac8d_759a_b875ca7815f8 -->|defined in| 48232d20_f8c1_b597_14fa_7dc407e9bfe5
  style e0201335_c5a0_ac8d_759a_b875ca7815f8 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/tests/unit_tests/chat_models/test_base.py lines 104–125

def test_openai_client_caching() -> None:
    """Test that the OpenAI client is cached."""
    llm1 = ChatOpenAI(model="gpt-4.1-mini")
    llm2 = ChatOpenAI(model="gpt-4.1-mini")
    assert llm1.root_client._client is llm2.root_client._client

    llm3 = ChatOpenAI(model="gpt-4.1-mini", base_url="foo")
    assert llm1.root_client._client is not llm3.root_client._client

    llm4 = ChatOpenAI(model="gpt-4.1-mini", timeout=None)
    assert llm1.root_client._client is llm4.root_client._client

    llm5 = ChatOpenAI(model="gpt-4.1-mini", timeout=3)
    assert llm1.root_client._client is not llm5.root_client._client

    llm6 = ChatOpenAI(
        model="gpt-4.1-mini", timeout=httpx.Timeout(timeout=60.0, connect=5.0)
    )
    assert llm1.root_client._client is not llm6.root_client._client

    llm7 = ChatOpenAI(model="gpt-4.1-mini", timeout=(5, 1))
    assert llm1.root_client._client is not llm7.root_client._client