test_model_data_to_profile_text_modalities() — langchain Function Reference

Architecture documentation for the test_model_data_to_profile_text_modalities() function in test_cli.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_model_data_to_profile_text_modalities() — langchain Function Reference

Dependency Diagram

graph TD
  4d0c46a5_112f_1925_4269_74ecf0b7e335["test_model_data_to_profile_text_modalities()"]
  8f48d3cf_da07_6b86_6f4f_33b7967df9e0["test_cli.py"]
  4d0c46a5_112f_1925_4269_74ecf0b7e335 -->|defined in| 8f48d3cf_da07_6b86_6f4f_33b7967df9e0
  style 4d0c46a5_112f_1925_4269_74ecf0b7e335 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/model-profiles/tests/unit_tests/test_cli.py lines 219–246

def test_model_data_to_profile_text_modalities() -> None:
    """Test that text input/output modalities are correctly mapped."""
    # Model with text in both input and output
    model_with_text = {
        "modalities": {"input": ["text", "image"], "output": ["text"]},
        "limit": {"context": 128000, "output": 4096},
    }
    profile = _model_data_to_profile(model_with_text)
    assert profile["text_inputs"] is True
    assert profile["text_outputs"] is True

    # Model without text input (e.g., Whisper-like audio model)
    audio_only_model = {
        "modalities": {"input": ["audio"], "output": ["text"]},
        "limit": {"context": 0, "output": 0},
    }
    profile = _model_data_to_profile(audio_only_model)
    assert profile["text_inputs"] is False
    assert profile["text_outputs"] is True

    # Model without text output (e.g., image generator)
    image_gen_model = {
        "modalities": {"input": ["text"], "output": ["image"]},
        "limit": {},
    }
    profile = _model_data_to_profile(image_gen_model)
    assert profile["text_inputs"] is True
    assert profile["text_outputs"] is False