test_parse_without_language() — langchain Function Reference

Architecture documentation for the test_parse_without_language() function in test_chat.py from the langchain codebase.

Function python LangChainCore LanguageModelBase calls 1

Entity Profile

LangChainCore→ LanguageModelBase→ test_parse_without_language() — langchain Function Reference

Dependency Diagram

graph TD
  0b1de780_4b20_3a45_14f2_1305cb10c996["test_parse_without_language()"]
  f5bec192_7de8_cc94_e8e5_efb1fe183808["test_chat.py"]
  0b1de780_4b20_3a45_14f2_1305cb10c996 -->|defined in| f5bec192_7de8_cc94_e8e5_efb1fe183808
  944de1bd_501a_1d52_838f_49084107eecf["get_action_and_input()"]
  0b1de780_4b20_3a45_14f2_1305cb10c996 -->|calls| 944de1bd_501a_1d52_838f_49084107eecf
  style 0b1de780_4b20_3a45_14f2_1305cb10c996 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/tests/unit_tests/agents/test_chat.py lines 33–46

def test_parse_without_language() -> None:
    llm_output = """I can use the `foo` tool to achieve the goal.

    Action:
    ```
    {
      "action": "foo",
      "action_input": "bar"
    }
    ```
    """
    action, action_input = get_action_and_input(llm_output)
    assert action == "foo"
    assert action_input == "bar"