model.predict not working for sequential retrieval tutorial. How to predict N next items?

Dear All,

I tried https://www.tensorflow.org/recommenders/examples/sequential_retrieval
with calling:
model.predict(cached_test) at the end.

https://colab.research.google.com/drive/1Goe4evEy-IchJ0MLv0emUA7UDZjEE6Ch?usp=sharing

Recieved following error. How to predict next N items using this sequential model?

NotImplementedError: Exception encountered when calling layer "model" (type Model).

Unimplemented `tf.keras.Model.call()`: if you intend to create a `Model` with the Functional API, please provide `inputs` and `outputs` arguments. Otherwise, subclass `Model` with an overridden `call()` method.

Call arguments received by layer "model" (type Model):
  • inputs={'context_movie_id': 'tf.Tensor(shape=(None, 10), dtype=string)', 'label_movie_id': 'tf.Tensor(shape=(None, 1), dtype=string)'}
  • training=False
  • mask=None

Reproduce the failure in the linked sequential retrieval tutorial and Colab notebook, starting with the model.predict(cached_test) call and the reported Model.call error. Determine whether the tutorial or its prediction instructions are incorrect; done means the example explains or demonstrates how to predict the next N items without the reported error.