# Load the pre-trained word embedding model
embedding_layer = hub.load(base_model_url)

# Create a Keras layer from the loaded embedding model
shared_embedding_layer = hub.KerasLayer(embedding_layer, trainable=True)

# Define the inputs to the model
left_input = keras.Input(shape=(), dtype=tf.string)
right_input = keras.Input(shape=(), dtype=tf.string)

# Pass the inputs through the shared embedding layer
embedding_left_output = shared_embedding_layer(left_input)
embedding_right_output = shared_embedding_layer(right_input)

# Compute the cosine similarity between the embedding vectors
cosine_similarity = tf.keras.layers.Dot(axes=-1, normalize=True)(
    [embedding_left_output, embedding_right_output]
)

# Convert the cosine similarity to angular distance
pi = tf.constant(math.pi, dtype=tf.float32)
clip_cosine_similarities = tf.clip_by_value(
    cosine_similarity, -0.99999, 0.99999
)
acos_distance = 1.0 - (tf.acos(clip_cosine_similarities) / pi)

# Package the model
encoder = tf.keras.Model([left_input, right_input], acos_distance)

# Compile the model
encoder.compile(
    optimizer=tf.keras.optimizers.Adam(
        learning_rate=0.00001,
        beta_1=0.9,
        beta_2=0.9999,
        epsilon=0.0000001,
        amsgrad=False,
        clipnorm=1.0,
        name="Adam",
    ),
    loss=tf.keras.losses.MeanSquaredError(
        reduction=keras.losses.Reduction.AUTO, name="mean_squared_error"
    ),
    metrics=[
        tf.keras.metrics.MeanAbsoluteError(),
        tf.keras.metrics.MeanAbsolutePercentageError(),
    ],
)

# Print the model summary
encoder.summary()