ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all() how can i use them?

Question

i got this error while trying to predict the machine learning model for single batch

but i do not know how to use any() or all() in my code i think because of the size of array at least

i have to use one of them any() or all()

Code:

saved_weights = find_checkpoint_file('.')
print('please enter the value')
user_input1 = input()
if len(saved_weights) == 0:
    print("The network hasn't been trained! Program will exit...")
    sys.exit()
else:
    X_test = load_test_data(user_input1, X_word_to_ix, MAX_LEN)
    print(type(X_test))
    X_test = pad_sequences(X_test, maxlen=4, dtype='int32')
    print(type(X_test))
    model.load_weights(saved_weights)
    predictions = np.array(model.predict(X_test))
    print(type(predictions))
    sequences = []
    for prediction in predictions:
        sequence = ' '.join([y_ix_to_word[index] for index in prediction if index > 0])
        print(sequence)
        l = sequences.append(sequence)
    np.savetxt('test_result.txt', sequences, fmt='%s')

the line that i think though out the error:

sequence = ' '.join([y_ix_to_word[index] for index in prediction if index > 0])

error:

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

sequence = ' '.join([y_ix_to_word[index] for index in prediction if index > 0]) 

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

in the below image is the traceback of error traceback