retail/recommendation-system/bqml-scann/embeddings_lookup/lookup_creator.py [57:73]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    self.vocabulary_file = tf.saved_model.Asset(VOCABULARY_FILE_NAME)
    initializer = tf.lookup.KeyValueTensorInitializer(
        keys=vocabulary, values=list(range(len(vocabulary))))
    self.token_to_id = tf.lookup.StaticHashTable(
        initializer, default_value=len(vocabulary))

  @tf.function(input_signature=[tf.TensorSpec([None], tf.string)])
  def __call__(self, inputs):
    tokens = tf.strings.split(inputs, sep=None).to_sparse()
    ids = self.token_to_id.lookup(tokens) 
    embeddings = tf.nn.embedding_lookup_sparse(
        params=self.embeddings, 
        sp_ids=ids, 
        sp_weights=None, 
        combiner="mean"
    )
    return embeddings
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



retail/recommendation-system/bqml-scann/tfx_pipeline/lookup_creator.py [68:84]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    self.vocabulary_file = tf.saved_model.Asset(VOCABULARY_FILE_NAME)
    initializer = tf.lookup.KeyValueTensorInitializer(
        keys=vocabulary, values=list(range(len(vocabulary))))
    self.token_to_id = tf.lookup.StaticHashTable(
        initializer, default_value=len(vocabulary))

  @tf.function(input_signature=[tf.TensorSpec([None], tf.string)])
  def __call__(self, inputs):
    tokens = tf.strings.split(inputs, sep=None).to_sparse()
    ids = self.token_to_id.lookup(tokens) 
    embeddings = tf.nn.embedding_lookup_sparse(
        params=self.embeddings, 
        sp_ids=ids, 
        sp_weights=None, 
        combiner="mean"
    )
    return embeddings
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -