langchain-ai/langchain · error · ValueError

Unsupported function {function} Functions must be passed i

Error message

Unsupported function

{function}

Functions must be passed in as Dict, pydantic.BaseModel, or Callable. If they're a dict they must either be in OpenAI function format or valid JSON schema with top-level 'title' key.

What it means

Error "Unsupported function {function} Functions must be passed in as Dict, pydantic.BaseModel, or Callable. If they're a dict they must either be in OpenAI function format or valid JSON schema with top-level 'title' key." thrown in langchain-ai/langchain.

Source

Thrown at libs/core/langchain_core/utils/function_calling.py:468

            "dict[str, Any]", _convert_python_function_to_openai_function(function)
        )
    else:
        if isinstance(function, dict) and (
            "type" in function or "properties" in function
        ):
            msg = (
                f"Unsupported function\n\n{function}\n\nTo use a JSON schema as a "
                "function, it must have a top-level 'title' key to be used as the "
                "function name."
            )
            raise ValueError(msg)
        msg = (
            f"Unsupported function\n\n{function}\n\nFunctions must be passed in"
            " as Dict, pydantic.BaseModel, or Callable. If they're a dict they must"
            " either be in OpenAI function format or valid JSON schema with top-level"
            " 'title' key."
        )
        raise ValueError(msg)

    if strict is not None:
        if "strict" in oai_function and oai_function["strict"] != strict:
            msg = (
                f"Tool/function already has a 'strict' key with value "
                f"{oai_function['strict']} which is different from the explicit "
                f"`strict` arg received {strict=}."
            )
            raise ValueError(msg)
        oai_function["strict"] = strict
        if strict:
            # All fields must be `required`
            parameters = oai_function.get("parameters")
            if isinstance(parameters, dict):
                fields = parameters.get("properties")
                if isinstance(fields, dict) and fields:
                    parameters = dict(parameters)
                    parameters["required"] = list(fields.keys())

View on GitHub (pinned to e32fa9a52e)

Solutions

1. Pass the function as a dict in OpenAI function format, a pydantic.BaseModel subclass, or a Python callable.
2. If passing a dict, ensure it is either OpenAI function format or a valid JSON schema with a top-level 'title' key.

Example fix

convert_to_openai_function(MyModel)  # or a callable, or {'name':..., 'parameters': {...}}

When it happens

Trigger: Raised when convert_to_openai_function receives an unsupported object: not a dict in OpenAI function format, not a valid JSON schema with 'title', not a pydantic.BaseModel, and not a callable.

Common situations: See trigger scenarios.

AI-assisted analysis of langchain-ai/langchain@e32fa9a52e (2026-08-14). Data as JSON: /api/errors/782aeeaf8ddf1aec. Report an issue: GitHub.