I am using rasa-core v0.12.3. I have trained a simple bot using interactive learning and I have the trained model under the models directory. But I have to test it in command line using a Python script. I followed this code, but it didn’t work as expected.
But when I try to do it, it loads but after typing anything I get the following error:
Bot loaded. Type a message and press enter (use ‘/stop’ to exit):
hi
/usr/local/lib/python3.5/dist-packages/sklearn/preprocessing/label.py:151: DeprecationWarning: The truth value of an empty array is ambiguous. Returning False, but in future this will result in an error. Use array.size > 0 to check that an array is not empty.
if diff:
Exception in thread Thread-2:
Traceback (most recent call last):
File “/usr/lib/python3.5/threading.py”, line 914, in _bootstrap_inner
self.run()
File “/usr/lib/python3.5/threading.py”, line 862, in run
self._target(*self._args, **self._kwargs)
File “/usr/local/lib/python3.5/dist-packages/rasa_core/channels/channel.py”, line 321, in on_message_wrapper
on_new_message(message)
File “/usr/local/lib/python3.5/dist-packages/rasa_core/agent.py”, line 317, in handle_message
return processor.handle_message(message)
File “/usr/local/lib/python3.5/dist-packages/rasa_core/processor.py”, line 86, in handle_message
self._predict_and_execute_next_action(message, tracker)
File “/usr/local/lib/python3.5/dist-packages/rasa_core/processor.py”, line 305, in _predict_and_execute_next_action
action, policy, confidence = self.predict_next_action(tracker)
File “/usr/local/lib/python3.5/dist-packages/rasa_core/processor.py”, line 168, in predict_next_action
probabilities, policy = self._get_next_action_probabilities(tracker)
File “/usr/local/lib/python3.5/dist-packages/rasa_core/processor.py”, line 478, in _get_next_action_probabilities
tracker, self.domain)
File “/usr/local/lib/python3.5/dist-packages/rasa_core/policies/ensemble.py”, line 291, in probabilities_using_best_policy
if (result.index(max_confidence) ==
AttributeError: ‘NoneType’ object has no attribute ‘index’
I have created the following run.py script:
P.S. I get the same error even if I use RasaNLUInterpreter() instead of NaturalLanguageInterpreter.create()