eustin

query_embeddings = np.row_stack([query_1_embeddings, query_2_embeddings_avg])

eustin

print(query_embeddings.shape)

eustin

docs_sequences = []
for docs_list in [bing_search_results, google_search_results]:
    docs_sequences.append(tokeniser.texts_to_sequences(docs_list))

docs_embeddings = []
for docs_set in docs_sequences:
    this_docs_set = []
    for doc in docs_set:
        this_doc_embeddings = np.array([embeddings[idx] for idx in doc])
        this_docs_set.append(this_doc_embeddings)

eustin

for embeddings in docs_embeddings[0]:
    print()
    print(embeddings)

eustin

for embeddings in docs_embeddings[1]:
    print()
    print(embeddings)

eustin

docs_averaged_embeddings = []
for docs_set in docs_embeddings:
    this_docs_set = []
    for doc in docs_set:
        this_docs_set.append(tf.reduce_mean(doc, axis=0, keepdims=True))
    concatenated_docs_set = tf.concat(this_docs_set, axis=0).numpy()
    docs_averaged_embeddings.append(concatenated_docs_set)
    
docs_averaged_embeddings = np.array(docs_averaged_embeddings)

eustin

print(docs_averaged_embeddings.shape)

eustin

NUM_DOCS_PER_QUERY = 5

expanded_queries = tf.gather(query_embeddings, [0 for x in range(NUM_DOCS_PER_QUERY)], axis=1).numpy()

print(expanded_queries)

eustin

expanded_batch = np.concatenate([expanded_queries, docs_averaged_embeddings], axis=-1)

print(expanded_batch)

eustin

dense_1 = tf.keras.layers.Dense(units=3, activation='relu')
dense_1_out = dense_1(expanded_batch)

print(dense_1_out)