Skip to content

dspy.load

dspy.load(path)

Load saved DSPy model.

This method is used to load a saved DSPy model with save_program=True, i.e., the model is saved with cloudpickle.

Parameters:

Name Type Description Default
path str

Path to the saved model.

 required

Returns:

Type Description

The loaded model, a dspy.Module instance.
Source code in dspy/utils/saving.py 
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
def load(path):
    """Load saved DSPy model.

    This method is used to load a saved DSPy model with `save_program=True`, i.e., the model is saved with cloudpickle.

    Args:
        path (str): Path to the saved model.

    Returns:
        The loaded model, a `dspy.Module` instance.
    """
    path = Path(path)
    if not path.exists():
        raise FileNotFoundError(f"The path '{path}' does not exist.")

    with open(path / "metadata.json", "r") as f:
        metadata = ujson.load(f)

    dependency_versions = get_dependency_versions()
    saved_dependency_versions = metadata["dependency_versions"]
    for key, saved_version in saved_dependency_versions.items():
        if dependency_versions[key] != saved_version:
            logger.warning(
                f"There is a mismatch of {key} version between saved model and current environment. You saved with "
                f"`{key}=={saved_version}`, but now you have `{key}=={dependency_versions[key]}`. This might cause "
                "errors or performance downgrade on the loaded model, please consider loading the model in the same "
                "environment as the saving environment."
            )

    with open(path / "program.pkl", "rb") as f:
        return cloudpickle.load(f)