keras vs bag of words

Question

snippet for tokenizer for text

tk = keras.preprocessing.text.Tokenizer(nb_words=500, filters=keras.preprocessing.text.base_filter(), lower=True, split=" ")
tk.fit_on_texts(x)
x = tk.texts_to_sequences(x)

what is the use of a bag of words when we can assign a unique id to each word using the above code ? Please help me understand the importance of bow vs the above process