test_global_cache_abatch() — langchain Function Reference

Architecture documentation for the test_global_cache_abatch() function in test_cache.py from the langchain codebase.

Function python CoreAbstractions MessageSchema

Entity Profile

CoreAbstractions→ MessageSchema→ test_global_cache_abatch() — langchain Function Reference

Dependency Diagram

graph TD
  ecaff70b_7abc_3a6d_6b7e_9f2b46f3685d["test_global_cache_abatch()"]
  51f634bf_713d_3f19_d694_5c6ef3e59c57["test_cache.py"]
  ecaff70b_7abc_3a6d_6b7e_9f2b46f3685d -->|defined in| 51f634bf_713d_3f19_d694_5c6ef3e59c57
  style ecaff70b_7abc_3a6d_6b7e_9f2b46f3685d fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/language_models/chat_models/test_cache.py lines 190–214

async def test_global_cache_abatch() -> None:
    global_cache = InMemoryCache()
    try:
        set_llm_cache(global_cache)
        chat_model = FakeListChatModel(
            cache=True, responses=["hello", "goodbye", "meow", "woof"]
        )
        results = await chat_model.abatch(["first prompt", "second prompt"])
        assert results[0].content == "hello"
        assert results[1].content == "goodbye"

        # Now try with the same prompt
        results = await chat_model.abatch(["first prompt", "first prompt"])
        assert results[0].content == "hello"
        assert results[1].content == "hello"

        global_cache = InMemoryCache()
        set_llm_cache(global_cache)
        assert global_cache._cache == {}
        results = await chat_model.abatch(["prompt", "prompt"])

        assert results[0].content == "meow"
        assert results[1].content == "meow"
    finally:
        set_llm_cache(None)