langchain-ai/langchain · error · TypeError

Model must be a Pydantic model.

Error message

Model must be a Pydantic model.

What it means

Error "Model must be a Pydantic model." thrown in langchain-ai/langchain.

Source

Thrown at libs/core/langchain_core/utils/function_calling.py:190

            If not provided, the description of the schema will be used.
        rm_titles: Whether to remove titles from the schema.

    Raises:
        TypeError: If the model is not a Pydantic model.
        TypeError: If the model contains types that cannot be converted to JSON schema.

    Returns:
        The function description.
    """
    try:
        if hasattr(model, "model_json_schema"):
            schema = model.model_json_schema()  # Pydantic 2
        elif hasattr(model, "schema"):
            schema = model.schema()  # Pydantic 1
        else:
            msg = "Model must be a Pydantic model."
            raise TypeError(msg)
    except PydanticInvalidForJsonSchema as e:
        model_name = getattr(model, "__name__", str(model))
        msg = (
            f"Failed to generate JSON schema for '{model_name}': {e}\n\n"
            "Tool argument schemas must be JSON-serializable. If your schema includes "
            "custom Python classes, consider:\n"
            "  1. Converting them to Pydantic models with JSON-compatible fields\n"
            "  2. Using primitive types (str, int, float, bool, list, dict) instead\n"
            "  3. Passing the data as serialized JSON strings\n\n"
        )
        raise PydanticInvalidForJsonSchema(msg) from e
    return _convert_json_schema_to_openai_function(
        schema, name=name, description=description, rm_titles=rm_titles
    )


def _get_python_function_name(function: Callable[..., Any]) -> str:
    """Get the name of a Python function."""

View on GitHub (pinned to e32fa9a52e)

Solutions

1. Pass a subclass of pydantic.BaseModel (v1 or v2) instead of a dict, dataclass, or TypedDict.
2. If you have a plain function, use convert_to_openai_function or the @tool decorator, which builds the schema for you.
3. If you have a JSON schema dict, pass it directly to convert_to_openai_tool instead of convert_to_openai_function.

Example fix

from pydantic import BaseModel
class MySchema(BaseModel):
    query: str
tool = convert_to_openai_function(MySchema)

When it happens

Trigger: Raised when convert_to_openai_function/tool is given a class that is not a Pydantic BaseModel subclass (e.g. a plain class or TypedDict) where a Pydantic model was required.

Common situations: See trigger scenarios.

AI-assisted analysis of langchain-ai/langchain@e32fa9a52e (2026-08-14). Data as JSON: /api/errors/6665c6930c84f34f. Report an issue: GitHub.