test_global_cache_stream() — langchain Function Reference

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

Function python CoreAbstractions MessageSchema

Entity Profile

CoreAbstractions→ MessageSchema→ test_global_cache_stream() — langchain Function Reference

Dependency Diagram

graph TD
  aaeb0615_592f_db79_41a3_b903999f40be["test_global_cache_stream()"]
  51f634bf_713d_3f19_d694_5c6ef3e59c57["test_cache.py"]
  aaeb0615_592f_db79_41a3_b903999f40be -->|defined in| 51f634bf_713d_3f19_d694_5c6ef3e59c57
  style aaeb0615_592f_db79_41a3_b903999f40be fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/language_models/chat_models/test_cache.py lines 253–268

def test_global_cache_stream() -> None:
    """Test streaming."""
    global_cache = InMemoryCache()
    try:
        set_llm_cache(global_cache)
        messages = [
            AIMessage(content="hello world"),
            AIMessage(content="goodbye world"),
        ]
        model = GenericFakeChatModel(messages=iter(messages), cache=True)
        chunks = list(model.stream("some input"))
        assert len(chunks) == 3
        # Assert that streaming information gets cached
        assert global_cache._cache != {}
    finally:
        set_llm_cache(None)