# Loads the Universal Sentence Encoder Multilingual module from TensorFlow Hub.
base_model_url = "https://tfhub.dev/google/universal-sentence-encoder-multilingual/3"
base_model = tf.keras.Sequential([
    hub.KerasLayer(base_model_url,
                   input_shape=[],
                   dtype=tf.string,
                   trainable=False)
])

# Defines a list of test sentences. These sentences represent various job titles.
test_text = ['Data Scientist', 'Data Analyst', 'Data Engineer',
             'Nurse Practitioner', 'Registered Nurse', 'Medical Assistant',
             'Social Media Manager', 'Marketing Strategist', 'Product Marketing Manager']

# Creates embeddings for the sentences in the test_text list. 
# The np.array() function is used to convert the result into a numpy array.
# The .tolist() function is used to convert the numpy array into a list, which might be easier to work with.
vectors = np.array(base_model.predict(test_text)).tolist()

# Calls the plot_similarity function to create a similarity plot.
plot_similarity(test_text, vectors, 90, "base model")

# Computes STS benchmark score for the base model
pearsonr = sts_benchmark(base_model)
print("STS Benachmark: " + str(pearsonr))