I’m using:
- rasa-core==0.12.0
- rasa-nlu==0.13.7
When running train_online.py
, I have an error after saying hi to the chatbot « ERROR:rasa_core.server:Can not access action 'None', as that name is not a registered action for this domain. Available actions are: … »
:
(venv) mike-mac-thinks:ChatbotRASA_Room-reservation mike$ python train_online.py
/Users/mike/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/h5py/init.py:34: FutureWarning: Conversion of the second argument of issubdtype from
float
tonp.floating
is deprecated. In future, it will be treated asnp.float64 == np.dtype(float).type
.from ._conv import register_converters as _register_converters
INFO:rasa_nlu.components:Added ‘nlp_spacy’ to component cache. Key ‘nlp_spacy-en’.
/Users/mike/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_nlu/extractors/entity_synonyms.py:85: UserWarning: Failed to load synonyms file from ‘./models/current/nlu/entity_synonyms.json’
“”.format(entity_synonyms_file))
/Users/mike/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/pykwalify/core.py:99: UnsafeLoaderWarning:
The default ‘Loader’ for ‘load(stream)’ without further arguments can be unsafe.
Use ‘load(stream, Loader=ruamel.yaml.Loader)’ explicitly if that is OK.
Alternatively include the following in your code:
import warnings
warnings.simplefilter(‘ignore’, ruamel.yaml.error.UnsafeLoaderWarning)
In most other cases you should consider using ‘safe_load(stream)’
data = yaml.load(stream)
Processed Story Blocks: 100%|████████████████████████████████████████████████| 22/22 [00:00<00:00, 1774.89it/s, # trackers=1]
Processed Story Blocks: 100%|█████████████████████████████████████████████████| 22/22 [00:00<00:00, 419.34it/s, # trackers=6]
Processed Story Blocks: 100%|█████████████████████████████████████████████████| 22/22 [00:00<00:00, 257.53it/s, # trackers=9]
Processed Story Blocks: 100%|████████████████████████████████████████████████| 22/22 [00:00<00:00, 206.66it/s, # trackers=10]
Processed actions: 44it [00:00, 24688.88it/s, # examples=44]
2019-02-01 16:07:31.547900: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
Layer (type) Output Shape Param #
=================================================================
masking (Masking) (None, 3, 22) 0
lstm (LSTM) (None, 32) 7040
dense (Dense) (None, 11) 363
activation (Activation) (None, 11) 0
=================================================================
Total params: 7,403
Trainable params: 7,403
Non-trainable params: 0
INFO:rasa_core.policies.keras_policy:Fitting model with 57 total samples and a validation split of 0.1
Epoch 1/3
57/57 [==============================] - 1s 15ms/step - loss: 2.2700 - acc: 0.3333
Epoch 2/3
57/57 [==============================] - 0s 1ms/step - loss: 2.0997 - acc: 0.5088
Epoch 3/3
57/57 [==============================] - 0s 2ms/step - loss: 1.9411 - acc: 0.5088
INFO:rasa_core.policies.keras_policy:Done fitting keras policy model
INFO:rasa_core.training.interactive:Rasa Core server is up and running on http://localhost:5005
Bot loaded. Visualisation at http://localhost:5005/visualization.html.
Type a message and press enter (press ‘Ctr-c’ to exit).
hi
Processed Story Blocks: 100%|████████████████████████████████████████████████| 22/22 [00:00<00:00, 2855.74it/s, # trackers=1]
? Next user input (Ctr-c to abort): hi
/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-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:
? Is the NLU classification for ‘hi’ with intent ‘greet’ correct? Yes
Chat History
Bot You
────────────────────────────────────────────
1 action_listen
────────────────────────────────────────────
2 hi
intent: greet 0.97
Current slots:
day: None, duration: None, hour_start: None, name_room: None
? The bot wants to run ‘utter_greet’, correct? No
Chat History
Bot You
────────────────────────────────────────────
1 action_listen
────────────────────────────────────────────
2 hi
intent: greet 0.97
Current slots:
day: None, duration: None, hour_start: None, name_room: None
? What is the next action of the bot? 1.00 utter_greet
Thanks! The bot will now run utter_greet.
ERROR:rasa_core.server:Can not access action ‘None’, as that name is not a registered action for this domain. Available actions are:
- action_listen - action_restart - action_default_fallback - action_deactivate_form - utter_greet - utter_goodbye - utter_ask_room - utter_ask_day - utter_ask_hour_start - utter_ask_duration - action_room
Traceback (most recent call last):
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/server.py”, line 220, in execute_action
confidence)
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/agent.py”, line 359, in execute_action
confidence)
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/processor.py”, line 150, in execute_action
action = self._get_action(action_name)
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/processor.py”, line 239, in _get_action
return self.domain.action_for_name(action_name, self.action_endpoint)
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/domain.py”, line 284, in action_for_name
self._raise_action_not_found_exception(action_name)
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/domain.py”, line 323, in _raise_action_not_found_exception
"".format(action_name, action_names))
NameError: Can not access action ‘None’, as that name is not a registered action for this domain. Available actions are:
- action_listen - action_restart - action_default_fallback - action_deactivate_form - utter_goodbye - utter_ask_room - utter_ask_day - utter_ask_hour_start - utter_ask_duration - action_room
ERROR:rasa_core.training.interactive:failed to execute action!
ERROR:rasa_core.training.interactive:An exception occurred while recording messages.
Traceback (most recent call last):
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/training/interactive.py”, line 1260, in record_messages
finetune, sender_ids, plot_file)
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/training/interactive.py”, line 841, in _predict_till_next_listen
finetune=finetune)
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/training/interactive.py”, line 980, in _validate_action
is_new_action=is_new_action)
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/training/interactive.py”, line 877, in _correct_wrong_action
is_new_action=is_new_action)
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/training/interactive.py”, line 174, in send_action
return _response_as_json(r)
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/rasa_core/training/interactive.py”, line 92, in _response_as_json
response.raise_for_status()
File “/Users/nathaliefouet/projets/ChatbotRASA_Room-reservation/venv/lib/python3.6/site-packages/requests/models.py”, line 940, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 500 Server Error: INTERNAL SERVER ERROR for url: http://localhost:5005/conversations/default/execute
I don’t have any None
actions. Is it linked to the fact that I have day: None, duration: None, hour_start: None, name_room: None
after asking hi ?
Do you have any ideas ?