test_caching() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_caching() — langchain Function Reference

Dependency Diagram

graph TD
  af91bab6_0b7a_58a5_e81a_0398ef603357["test_caching()"]
  aecd824f_70b2_ac20_4966_65af1dc88831["test_base.py"]
  af91bab6_0b7a_58a5_e81a_0398ef603357 -->|defined in| aecd824f_70b2_ac20_4966_65af1dc88831
  style af91bab6_0b7a_58a5_e81a_0398ef603357 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/tests/unit_tests/llms/test_base.py lines 21–45

def test_caching() -> None:
    """Test caching behavior."""
    set_llm_cache(InMemoryCache())
    llm = FakeLLM()
    params = llm.dict()
    params["stop"] = None
    llm_string = str(sorted([(k, v) for k, v in params.items()]))
    cache = get_llm_cache()
    assert cache is not None
    cache.update("foo", llm_string, [Generation(text="fizz")])
    output = llm.generate(["foo", "bar", "foo"])
    expected_cache_output = [Generation(text="foo")]
    cache_output = cache.lookup("bar", llm_string)
    assert cache_output == expected_cache_output
    set_llm_cache(None)
    expected_generations = [
        [Generation(text="fizz")],
        [Generation(text="foo")],
        [Generation(text="fizz")],
    ]
    expected_output = LLMResult(
        generations=expected_generations,
        llm_output=None,
    )
    assert output == expected_output