test_openai_stop_valid() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_openai_stop_valid() — langchain Function Reference

Dependency Diagram

graph TD
  a4c8c53c_fb9a_63b4_9fc6_991a2ac4390b["test_openai_stop_valid()"]
  2edc9f83_2189_a9c8_70f5_10e2e98e8272["test_base.py"]
  a4c8c53c_fb9a_63b4_9fc6_991a2ac4390b -->|defined in| 2edc9f83_2189_a9c8_70f5_10e2e98e8272
  style a4c8c53c_fb9a_63b4_9fc6_991a2ac4390b fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/tests/integration_tests/llms/test_base.py lines 90–98

def test_openai_stop_valid() -> None:
    """Test openai stop logic on valid configuration."""
    query = "write an ordered list of five items"
    first_llm = OpenAI(stop="3", temperature=0)  # type: ignore[call-arg]
    first_output = first_llm.invoke(query)
    second_llm = OpenAI(temperature=0)
    second_output = second_llm.invoke(query, stop=["3"])
    # Because it stops on new lines, shouldn't return anything
    assert first_output == second_output