How do I save a TensorFlow mulit-task recommendation model?

Question

So I followed this tutorial and the model trains just fine (https://www.tensorflow.org/recommenders/examples/multitask?hl=en).
My question is how do i save the trained model so that it can be used for serving? The individual ranking and retrieval model are saved in very different ways:

• To save the retrieval model you encapsulate it into a BruteForce Layer and create an index that contains the possible candidates https://www.tensorflow.org/recommenders/examples/basic_retrieval#making_predictions
• To save the ranking model you simply call tf.saved_model.save( ) https://www.tensorflow.org/recommenders/examples/basic_ranking#exporting_for_serving

So how do I combine these two steps?