keras-team/keras · error · ValueError

No endpoints have been set yet. Call add_endpoint().

Error message

No endpoints have been set yet. Call add_endpoint().

What it means

Error "No endpoints have been set yet. Call add_endpoint()." thrown in keras-team/keras.

Source

Thrown at keras/src/export/saved_model_export_archive.py:266

        Arguments:
            filepath: `str` or `pathlib.Path` object.
                Path where to save the artifact.
            options: `tf.saved_model.SaveOptions` object that specifies
                SavedModel saving options.
            verbose: whether to print all the variables of an
                exported SavedModel.

        **Note on TF-Serving**: all endpoints registered via `add_endpoint()`
        are made visible for TF-Serving in the SavedModel artifact. In addition,
        the first endpoint registered is made visible under the alias
        `"serving_default"` (unless an endpoint with the name
        `"serving_default"` was already registered manually),
        since TF-Serving requires this endpoint to be set.
        """
        from keras.src.utils import io_utils

        if not self._endpoint_names:
            raise ValueError(
                "No endpoints have been set yet. Call add_endpoint()."
            )
        self._filter_and_track_resources()

        signatures = {}
        for name in self._endpoint_names:
            signatures[name] = self._get_concrete_fn(name)
        # Add "serving_default" signature key for TFServing
        if "serving_default" not in self._endpoint_names:
            signatures["serving_default"] = self._get_concrete_fn(
                self._endpoint_names[0]
            )

        tf.saved_model.save(
            self._tf_trackable,
            filepath,
            options=options,
            signatures=signatures,

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/export/saved_model_export_archive.py:266 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/fad5e563226b2e10. Report an issue: GitHub.