Adding TED policy in config. Bot does not respond

When I add TED policy and train the core, after that while running the bot on the command line i didn’t get any response from the bot with the Error Logs:

2020-11-05 19:55:20 DEBUG    rasa.core.processor  - Received user message 'hi' with intent '{'id': -5976068340782558361, 'name': 'greetings.hello', 'confidence': 0.9986205101013184}' and entities '[]'
2020-11-05 19:55:20 DEBUG    rasa.core.processor  - Logged UserUtterance - tracker now has 4 events.
2020-11-05 19:55:20 DEBUG    rasa.core.policies.memoization  - Current tracker state [{'slots': {'form_mapping_counter': (1.0,)}}, {'user': {'intent': 'greetings.hello'}, 'slots': {'form_mapping_counter': (1.0,)}, 'prev_action': {'action_name': 'action_listen'}}]
2020-11-05 19:55:20 DEBUG    rasa.core.policies.memoization  - Launch DeLorean...
2020-11-05 19:55:20 DEBUG    rasa.core.policies.memoization  - Current tracker state [{'slots': {'form_mapping_counter': (1.0,)}}, {'user': {'intent': 'greetings.hello'}, 'slots': {'form_mapping_counter': (1.0,)}, 'prev_action': {'action_name': 'action_listen'}}]
2020-11-05 19:55:20 DEBUG    rasa.core.policies.memoization  - There is no memorised next action
2020-11-05 19:55:20 DEBUG    rasa.core.lock_store  - Deleted lock for conversation '6e38565c3a144a73b652be6c202c3d3b'.
2020-11-05 19:55:31 ERROR    asyncio  - Task exception was never retrieved
future: <Task finished coro=<configure_app.<locals>.run_cmdline_io() done, defined at /usr/local/lib/python3.6/dist-packages/rasa/core/run.py:132> exception=TimeoutError()>
Traceback (most recent call last):
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/run.py", line 138, in run_cmdline_io
    sender_id=conversation_id,
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 129, in throw
    return self.gen.throw(type, value, traceback)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/channels/console.py", line 182, in record_messages
    async for response in bot_responses:
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/channels/console.py", line 137, in send_message_receive_stream
    async for line in resp.content:
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 129, in throw
    return self.gen.throw(type, value, traceback)
  File "/usr/local/lib/python3.6/dist-packages/aiohttp/streams.py", line 39, in __anext__
    rv = await self.read_func()
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 129, in throw
    return self.gen.throw(type, value, traceback)
  File "/usr/local/lib/python3.6/dist-packages/aiohttp/streams.py", line 328, in readline
    await self._wait('readline')
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 129, in throw
    return self.gen.throw(type, value, traceback)
  File "/usr/local/lib/python3.6/dist-packages/aiohttp/streams.py", line 296, in _wait
    await waiter
  File "/usr/local/lib/python3.6/dist-packages/aiohttp/helpers.py", line 596, in __exit__
    raise asyncio.TimeoutError from None
concurrent.futures._base.TimeoutError
Transport closed @ ('127.0.0.1', 41170) and exception experienced during error handling
^CTraceback (most recent call last):
  File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/code/ai/scripts/tc_cmd.py", line 87, in <module>
    subprocess.Popen(command, shell=True).communicate()
  File "/usr/lib/python3.6/subprocess.py", line 855, in communicate
    self.wait()
  File "/usr/lib/python3.6/subprocess.py", line 1477, in wait
    (pid, sts) = self._try_wait(0)
  File "/usr/lib/python3.6/subprocess.py", line 1424, in _try_wait
    (pid, sts) = os.waitpid(self.pid, wait_flags)
KeyboardInterrupt
2020-11-05 19:55:54 ERROR    asyncio  - Task exception was never retrieved
future: <Task finished coro=<RestInput.on_message_wrapper() done, defined at /usr/local/lib/python3.6/dist-packages/rasa/core/channels/rest.py:33> exception=NotFittedError('Vocabulary not fitted or provided',) created at /usr/local/lib/python3.6/dist-packages/rasa/core/channels/rest.py:73>
source_traceback: Object created at (most recent call last):
  File "/usr/local/bin/rasa", line 8, in <module>
    sys.exit(main())
  File "/usr/local/lib/python3.6/dist-packages/rasa/__main__.py", line 116, in main
    cmdline_arguments.func(cmdline_arguments)
  File "/usr/local/lib/python3.6/dist-packages/rasa/cli/shell.py", line 123, in shell
    rasa.cli.run.run(args)
  File "/usr/local/lib/python3.6/dist-packages/rasa/cli/run.py", line 121, in run
    rasa.run(**vars(args))
  File "/usr/local/lib/python3.6/dist-packages/rasa/run.py", line 58, in run
    **kwargs,
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/run.py", line 226, in serve_application
    workers=number_of_workers,
  File "/usr/local/lib/python3.6/dist-packages/sanic/app.py", line 1167, in run
    serve(**server_settings)
  File "/usr/local/lib/python3.6/dist-packages/sanic/server.py", line 920, in serve
    loop.run_forever()
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 126, in send
    return self.gen.send(value)
  File "/usr/local/lib/python3.6/dist-packages/spf/framework.py", line 554, in _handle_request
    stream_callback)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/sanic/app.py", line 1036, in handle_request
    await stream_callback(response)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/sanic/server.py", line 532, in stream_response
    self.request.version, keep_alive, self.keep_alive_timeout
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/sanic/response.py", line 98, in stream
    await self.streaming_fn(self)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/channels/rest.py", line 73, in stream
    on_new_message, text, q, sender_id, input_channel, metadata
Traceback (most recent call last):
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 126, in send
    return self.gen.send(value)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/channels/rest.py", line 47, in on_message_wrapper
    await on_new_message(message)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/channels/channel.py", line 84, in handler
    await app.agent.handle_message(*args, **kwargs)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/agent.py", line 526, in handle_message
    return await processor.handle_message(message)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/processor.py", line 98, in handle_message
    await self._predict_and_execute_next_action(message.output_channel, tracker)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/processor.py", line 563, in _predict_and_execute_next_action
    action, policy, confidence = self.predict_next_action(tracker)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/processor.py", line 285, in predict_next_action
    action_confidences, policy = self._get_next_action_probabilities(tracker)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/processor.py", line 829, in _get_next_action_probabilities
    tracker, self.domain, self.interpreter
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/ensemble.py", line 672, in probabilities_using_best_policy
    tracker, domain, interpreter
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/ensemble.py", line 562, in _best_policy_prediction
    for i, p in enumerate(self.policies)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/ensemble.py", line 562, in <dictcomp>
    for i, p in enumerate(self.policies)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/ensemble.py", line 593, in _get_prediction
    tracker, domain, interpreter
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/ted_policy.py", line 385, in predict_action_probabilities
    [tracker], domain, interpreter
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/tracker_featurizers.py", line 180, in create_state_features
    return self._featurize_states(trackers_as_states, interpreter)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/tracker_featurizers.py", line 73, in _featurize_states
    for tracker_states in trackers_as_states
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/tracker_featurizers.py", line 73, in <listcomp>
    for tracker_states in trackers_as_states
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/tracker_featurizers.py", line 71, in <listcomp>
    for state in tracker_states
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/single_state_featurizer.py", line 201, in encode_state
    self._extract_state_features(sub_state, interpreter, sparse=True)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/single_state_featurizer.py", line 169, in _extract_state_features
    parsed_message = interpreter.featurize_message(message)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/interpreter.py", line 158, in featurize_message
    result = self.interpreter.featurize_message(message)
  File "/usr/local/lib/python3.6/dist-packages/rasa/nlu/model.py", line 415, in featurize_message
    component.process(message, **self.context)
  File "/usr/local/lib/python3.6/dist-packages/rasa/nlu/featurizers/sparse_featurizer/count_vectors_featurizer.py", line 562, in process
    attribute, [message_tokens]
  File "/usr/local/lib/python3.6/dist-packages/rasa/nlu/featurizers/sparse_featurizer/count_vectors_featurizer.py", line 438, in _create_features
    seq_vec = self.vectorizers[attribute].transform(tokens)
  File "/usr/local/lib/python3.6/dist-packages/sklearn/feature_extraction/text.py", line 1267, in transform
    self._check_vocabulary()
  File "/usr/local/lib/python3.6/dist-packages/sklearn/feature_extraction/text.py", line 490, in _check_vocabulary
    raise NotFittedError("Vocabulary not fitted or provided")
sklearn.exceptions.NotFittedError: Vocabulary not fitted or provided
Makefile:50: recipe for target 'run-bot-shell' failed

Here is the Config File:

language: en
pipeline:
- name: WhitespaceTokenizer
- name: LexicalSyntacticFeaturizer
- name: CountVectorsFeaturizer
  token_pattern: (?u)\b\w+\b
- name: RegexEntityExtractor
  # text will be processed with case insensitive as default
  "case_sensitive": False
  # use lookup tables to extract entities
  "use_lookup_tables": True
  # use regexes to extract entities
  "use_regexes": True  
- name: DucklingHTTPExtractor
  url: http://duckling:7000
  dimensions:
  - sys_time
  - sys_day
  - sys_month
  - sys_year
  - phone-number
  - number
  - amount-of-money
  - distance
  - duration
  - volume
  - ordinal
  - temperature
  - email
  - url
  - time
  
- name: DIETClassifier
   epochs: 15
 - name: FallbackClassifier
   threshold: 0.6
   ambiguity_threshold: 0.1
 
 policies:
   - name: AugmentedMemoizationPolicy
   - name: TEDPolicy
     epochs: 100
   - name: RulePolicy
     core_fallback_threshold: 0.4
     core_fallback_action_name: "action_default_fallback"

@Tanja seen you providing solution to almost the similar problem on Git, if you please may help. Thanks

Can you provide more details: How did you train your bot? Did you use rasa train? How do your stories look like?

Trained NLU and Core separately. Core trained using command:

rasa train core --config ai/pre_built_bots/bot_name/config_nlu.yml --domain ai/pre_built_bots/bot_name/domain.yml --stories ai/pre_built_bots/bot_name/data/data_core

Giving the path to data using --stories , --data does not work for me

NLU training command:

rasa train nlu --config ai/pre_built_bots/bot_name/config_nlu.yml --nlu ai/pre_built_bots/bot_name/data/data_nlu/

Right now i have only single story which is:

version: β€œ2.0” stories:

  • story: inform - 1568286231.0008 steps:
    • intent: inform
    • action: utter_out_of_scope
    • action: action_restarted

Can you please try training them together, aka using rasa train, and then try again?

But it will not full fill my use case, i need to train them separately

what i do i train them separately and combine both the models. Link for the combined model is given https://drive.google.com/file/d/1dMc2qduIzRFKucmXiieerl1gUCJIQvFn/view?usp=sharing

After upgrading rasa to rasa==2.0.4 from rasa==2.0.0. I have trained both core and nlu using the single command that is:

rasa train --domain ai/pre_built_bots/bot_name/domain.yml --config ai/pre_built_bots/bot_name/config_nlu.yml --data ai/pre_built_bots/bot_name/data/ --out ai/pre_built_bots/bot_name/models/

My training data contains single story:

version: β€œ2.0” stories:

  • story: inform - 1568286231.0008 steps:
    • intent: inform
    • action: utter_inform

And these rules having no rule for inform:

version: "2.0"
rules:
- rule: respond to FAQs
  steps:
  - intent: faq
  - action: utter_faq
- rule: utter_greetings after greetings at conversation start
  conversation_start: true
  steps:
  - intent: greetings.hello
  - action: utter_greetings.hello
  - action: utter_welcome_message

# - rule: Rule to map `greetings.hello` intent to `action_utterances_handler` (automatic conversion)
#   steps:
#   - intent: greetings.hello
#   - action: action_utterances_handler

- rule: Rule to map `complaints.unanswered_phone_call` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: complaints.unanswered_phone_call
  - action: action_utterances_handler
- rule: Rule to map `complaints.donation` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: complaints.donation
  - action: action_utterances_handler
- rule: Rule to map `contact.us` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: contact.us
  - action: action_utterances_handler
- rule: Rule to map `menu.main_message` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: menu.main_message
  - action: action_utterances_handler
- rule: Rule to map `daig.total_recipients` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: daig.total_recipients
  - action: action_utterances_handler
- rule: Rule to map `daig.terms_and_conditions` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: daig.terms_and_conditions
  - action: action_utterances_handler
- rule: Rule to map `daig.items` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: daig.items
  - action: action_utterances_handler
- rule: Rule to map `daig.donate` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: daig.donate
  - action: action_utterances_handler
- rule: Rule to map `daig.distribution_process` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: daig.distribution_process
  - action: action_utterances_handler
- rule: Rule to map `daig.cost` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: daig.cost
  - action: action_utterances_handler
- rule: Rule to map `volunteer.join` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: volunteer.join
  - action: action_utterances_handler
- rule: Rule to map `volunteer.distribution` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: volunteer.distribution
  - action: action_utterances_handler
- rule: Rule to map `out_of_scope` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: out_of_scope
  - action: action_utterances_handler
- rule: Rule to map `get_started` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: get_started
  - action: action_utterances_handler
- rule: Rule to map `attachment.received` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: attachment.received
  - action: action_utterances_handler
- rule: Rule to map `user.needs_advice` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: user.needs_advice
  - action: action_utterances_handler
- rule: Rule to map `user.hurry` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: user.hurry
  - action: action_utterances_handler
- rule: Rule to map `user.happy` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: user.happy
  - action: action_utterances_handler
- rule: Rule to map `user.good` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: user.good
  - action: action_utterances_handler
- rule: Rule to map `user.going_to_bed` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: user.going_to_bed
  - action: action_utterances_handler
- rule: Rule to map `user.confirm_later` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: user.confirm_later
  - action: action_utterances_handler
- rule: Rule to map `user.bored` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: user.bored
  - action: action_utterances_handler
- rule: Rule to map `greetings.whatsup` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.whatsup
  - action: action_utterances_handler
- rule: Rule to map `greetings.salam` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.salam
  - action: action_utterances_handler
- rule: Rule to map `greetings.nice_to_talk_to_you` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.nice_to_talk_to_you
  - action: action_utterances_handler
- rule: Rule to map `greetings.nice_to_see_you` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.nice_to_see_you
  - action: action_utterances_handler
- rule: Rule to map `greetings.mashaallah` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.mashaallah
  - action: action_utterances_handler
- rule: Rule to map `greetings.jazakallah` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.jazakallah
  - action: action_utterances_handler
- rule: Rule to map `greetings.goodmorning` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.goodmorning
  - action: action_utterances_handler
- rule: Rule to map `greetings.emoji` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.emoji
  - action: action_utterances_handler
- rule: Rule to map `greetings.bye` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.bye
  - action: action_utterances_handler
- rule: Rule to map `greetings.allah_hafiz` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.allah_hafiz
  - action: action_utterances_handler
- rule: Rule to map `geetings.inshaallah` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: geetings.inshaallah
  - action: action_utterances_handler
- rule: Rule to map `deny` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: deny
  - action: action_utterances_handler
- rule: Rule to map `appraisal.welcome` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: appraisal.welcome
  - action: action_utterances_handler
- rule: Rule to map `appraisal.thank_you` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: appraisal.thank_you
  - action: action_utterances_handler
- rule: Rule to map `appraisal.good` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: appraisal.good
  - action: action_utterances_handler
- rule: Rule to map `appraisal.bad` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: appraisal.bad
  - action: action_utterances_handler
- rule: Rule to map `agent.what_can_do` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: agent.what_can_do
  - action: action_utterances_handler
- rule: Rule to map `agent.happy` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: agent.happy
  - action: action_utterances_handler
- rule: Rule to map `agent.good` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: agent.good
  - action: action_utterances_handler
- rule: Rule to map `agent.chatbot` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: agent.chatbot
  - action: action_utterances_handler
- rule: Rule to map `agent.can_you_help` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: agent.can_you_help
  - action: action_utterances_handler
- rule: Rule to map `affirm` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: affirm
  - action: action_utterances_handler
- rule: Rule to map `lunch.process` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: lunch.process
  - action: action_utterances_handler
- rule: Rule to map `lunch.donors` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: lunch.donors
  - action: action_utterances_handler
- rule: Rule to map `lunch.donate` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: lunch.donate
  - action: action_utterances_handler
- rule: Rule to map `ration.terms_&_conditions` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: ration.terms_&_conditions
  - action: action_utterances_handler
- rule: Rule to map `ration.rizqbanks` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: ration.rizqbanks
  - action: action_utterances_handler
- rule: Rule to map `ration.process` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: ration.process
  - action: action_utterances_handler
- rule: Rule to map `ration.items` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: ration.items
  - action: action_utterances_handler
- rule: Rule to map `ration.donate` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: ration.donate
  - action: action_utterances_handler
- rule: Rule to map `ration.cost` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: ration.cost
  - action: action_utterances_handler
- rule: Rule to map `job.apply` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: job.apply
  - action: action_utterances_handler
- rule: Rule to map `donation.zakat` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: donation.zakat
  - action: action_utterances_handler
- rule: Rule to map `donation.proof` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: donation.proof
  - action: action_utterances_handler
- rule: Rule to map `donation.different` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: donation.different
  - action: action_utterances_handler
- rule: Rule to map `donation.confirmation` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: donation.confirmation
  - action: action_utterances_handler
- rule: Rule to map `donation.change` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: donation.change
  - action: action_utterances_handler
- rule: Rule to map `donation.cash_collection` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: donation.cash_collection
  - action: action_utterances_handler
- rule: Rule to map `beneficiary.verification` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: beneficiary.verification
  - action: action_utterances_handler
- rule: Rule to map `beneficiary.status` intent to `beneficiary.status_form` (automatic conversion)
  steps:
  - intent: beneficiary.status
  - action: beneficiary.status_form
- rule: Rule to map `beneficiary.register` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: beneficiary.register
  - action: action_utterances_handler
- rule: Rule to map `beneficiary.reference` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: beneficiary.reference
  - action: action_utterances_handler
- rule: Rule to map `beneficiary.ration` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: beneficiary.ration
  - action: action_utterances_handler
# - rule: Rule to map `bachao.terms_and_conditions` intent to `action_utterances_handler` (automatic conversion)
#   steps:
#   - intent: bachao.terms_and_conditions
#   - action: action_utterances_handler
# - rule: Rule to map `bachao.process` intent to `action_utterances_handler` (automatic conversion)
#   steps:
#   - intent: bachao.process
#   - action: action_utterances_handler
# - rule: Rule to map `bachao.donate` intent to `action_utterances_handler` (automatic conversion)
#   steps:
#   - intent: bachao.donate
#   - action: action_utterances_handler
- rule: Rule to map `about.team` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: about.team
  - action: action_utterances_handler
- rule: Rule to map `about.social_media` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: about.social_media
  - action: action_utterances_handler
- rule: Rule to map `about.services` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: about.services
  - action: action_utterances_handler
- rule: Rule to map `about.rizq` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: about.rizq
  - action: action_utterances_handler
- rule: Rule to map `about.partners` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: about.partners
  - action: action_utterances_handler
- rule: Rule to map `about.operation` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: about.operation
  - action: action_utterances_handler
- rule: Rule to map `about.location` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: about.location
  - action: action_utterances_handler
- rule: Rule to map `about.founders` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: about.founders
  - action: action_utterances_handler
- rule: Rule to map `about.donating` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: about.donating
  - action: action_utterances_handler
- rule: Rule to map `about.contact` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: about.contact
  - action: action_utterances_handler
- rule: Rule to map `about.blog` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: about.blog
  - action: action_utterances_handler
- rule: Rule to map `form_deactivate` intent to `action_form_deactivate` (automatic conversion)
  steps:
  - intent: form_deactivate
  - action: action_form_deactivate
- rule: Rule to map `increment_form_mapping_counter` intent to `action_increment_form_mapping_counter` (automatic conversion)
  steps:
  - intent: increment_form_mapping_counter
  - action: action_increment_form_mapping_counter
- rule: Rule to map `None` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: None
  - action: action_utterances_handler
- rule: Rule to map `dialog.hold_on` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: dialog.hold_on
  - action: action_utterances_handler
- rule: Rule to map `agent.who_are_you` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: agent.who_are_you
  - action: action_utterances_handler
- rule: Rule to map `user.waits` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: user.waits
  - action: action_utterances_handler
- rule: Rule to map `user.back` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: user.back
  - action: action_utterances_handler
- rule: Rule to map `user.confused` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: user.confused
  - action: action_utterances_handler
- rule: Rule to map `user.busy` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: user.busy
  - action: action_utterances_handler
- rule: Rule to map `agent.bad` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: agent.bad
  - action: action_utterances_handler
- rule: Rule to map `emoji.angry` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: emoji.angry
  - action: action_utterances_handler
- rule: Rule to map `greetings.how_are_you` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.how_are_you
  - action: action_utterances_handler
- rule: Rule to map `greetings.nice_to_meet_you` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: greetings.nice_to_meet_you
  - action: action_utterances_handler
- rule: Rule to map `agent.sure` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: agent.sure
  - action: action_utterances_handler
- rule: Rule to map `dialog.wrong` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: dialog.wrong
  - action: action_utterances_handler
- rule: Rule to map `emoji.happy` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: emoji.happy
  - action: action_utterances_handler
- rule: Rule to map `emoji.sad` intent to `action_utterances_handler` (automatic conversion)
  steps:
  - intent: emoji.sad
  - action: action_utterances_handler
- rule: Rule to handle messages with low NLU confidence (automated conversion from 'TwoStageFallbackPolicy')
  steps:
  - intent: nlu_fallback
  - action: action_two_stage_fallback

Yet I am facing this error:

NLU model training completed.
Training Core model…
Processed story blocks: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1/1 [00:00<00:00, 622.30it/s, # trackers=1]
Processed story blocks: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1/1 [00:00<00:00, 932.27it/s, # trackers=1]
Processed story blocks: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1/1 [00:00<00:00, 409.92it/s, # trackers=2]
Processed story blocks: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1/1 [00:00<00:00, 306.92it/s, # trackers=3]
Processed rules: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 96/96 [00:00<00:00, 958.74it/s, # trackers=1]
Processed trackers: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1/1 [00:00<00:00, 2253.79it/s, # actions=3]
Processed actions: 3it [00:00, 5291.38it/s, # examples=3]
Processed trackers: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:00<00:00, 1284.53it/s, # actions=9]
Epochs: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 100/100 [00:08<00:00, 12.35it/s, t_loss=0.213, loss=0.001, acc=1.000]
2020-11-09 08:50:57 INFO     rasa.utils.tensorflow.models  - Finished training.
Processed trackers: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 96/96 [00:00<00:00, 2206.06it/s, # actions=195]
Processed actions: 195it [00:00, 11103.88it/s, # examples=194]
Processed trackers: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1/1 [00:00<00:00, 1706.39it/s, # actions=3]
Processed trackers: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 96/96 [00:00<00:00, 130.09it/s]
Processed trackers: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 97/97 [00:00<00:00, 128.58it/s]
InvalidRule: 
Contradicting rules or stories found :rotating_light:

<font color="#EF2929">- the prediction of the action &apos;utter_inform&apos; in story &apos;inform - 1568286231.0008&apos; is contradicting with rule(s) &apos;&apos; which predicted action &apos;action_listen&apos;.</font>
<font color="#EF2929">Please update your stories and rules so that they don&apos;t contradict each other.</font>
<font color="#EF2929">You can find more information about the usage of rules at https://rasa.com/docs/rasa/rules. </font>
</pre>

Also I wonder, command for training core and nlu combined runs fine with --data argument for nlu and core data, but when we have to train the core independently command does not run with --data argument instead it runs with --stories argument why? Even though document does not have any clue regarding --stories Command Line Interface

Regarding the command line interface: I guess that is due to some legacy code. Feel free to open an issue on GitHub for that. The documentation just shows the main rasa train command. You need to run rasa train nlu --help or rasa train core --help to see the corresponding arguments for those commands.

I think this is now resolved, see this thread.

@SamS Are you sure this issue is related to this issue Contradicting rules or stories found ? Here bot does not respond if i include TED policy in the config while in the referenced issue we were having invalid rules/stories issue.

@noman I don’t have a proof that it’s solved, but I’d recommend that you try the fix mentioned in the other thread and see if your bot still doesn’t respond when you include TED. Why I think that this issue could now be solved as well? Because some of the issues in the other thread were occurring only when some stories were present or when TED was enabled, but with the fixed version of the codebase those errors are now gone too. @noman please let me know if you’re still running into problems once you’ve tried the fixed version from this PR :slight_smile:

Hi @SamS i have tried the fix by first installing the commit using pip3 install git+https://github.com/RasaHQ/rasa@33b7560e378fc32216e7b4c52299de97805b06a0 and then trained the bot using TED and it didn’t reply me with bot data similar to this issue Contradicting rules or stories found. Error logs:

2020-11-13 12:02:50 DEBUG    rasa.core.lock_store  - Deleted lock for conversation 'bc85d7feac7a4dd9b095e98b7fe01756'.
2020-11-13 12:03:01 ERROR    asyncio  - Task exception was never retrieved
future: <Task finished coro=<configure_app.<locals>.run_cmdline_io() done, defined at /usr/local/lib/python3.6/dist-packages/rasa/core/run.py:133> exception=TimeoutError()>
Traceback (most recent call last):
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/run.py", line 139, in run_cmdline_io
    sender_id=conversation_id,
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 129, in throw
    return self.gen.throw(type, value, traceback)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/channels/console.py", line 182, in record_messages
    async for response in bot_responses:
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/channels/console.py", line 137, in send_message_receive_stream
    async for line in resp.content:
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 129, in throw
    return self.gen.throw(type, value, traceback)
  File "/usr/local/lib/python3.6/dist-packages/aiohttp/streams.py", line 39, in __anext__
    rv = await self.read_func()
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 129, in throw
    return self.gen.throw(type, value, traceback)
  File "/usr/local/lib/python3.6/dist-packages/aiohttp/streams.py", line 328, in readline
    await self._wait('readline')
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 129, in throw
    return self.gen.throw(type, value, traceback)
  File "/usr/local/lib/python3.6/dist-packages/aiohttp/streams.py", line 296, in _wait
    await waiter
  File "/usr/local/lib/python3.6/dist-packages/aiohttp/helpers.py", line 596, in __exit__
    raise asyncio.TimeoutError from None
concurrent.futures._base.TimeoutError
Transport closed @ ('127.0.0.1', 46142) and exception experienced during error handling
future: <Task finished coro=<RestInput.on_message_wrapper() done, defined at /usr/local/lib/python3.6/dist-packages/rasa/core/channels/rest.py:33> exception=NotFittedError('Vocabulary not fitted or provided',) created at /usr/local/lib/python3.6/dist-packages/rasa/core/channels/rest.py:73>
source_traceback: Object created at (most recent call last):
  File "/usr/local/bin/rasa", line 8, in <module>
    sys.exit(main())
  File "/usr/local/lib/python3.6/dist-packages/rasa/__main__.py", line 116, in main
    cmdline_arguments.func(cmdline_arguments)
  File "/usr/local/lib/python3.6/dist-packages/rasa/cli/shell.py", line 123, in shell
    rasa.cli.run.run(args)
  File "/usr/local/lib/python3.6/dist-packages/rasa/cli/run.py", line 121, in run
    rasa.run(**vars(args))
  File "/usr/local/lib/python3.6/dist-packages/rasa/run.py", line 58, in run
    **kwargs,
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/run.py", line 227, in serve_application
    workers=number_of_workers,
  File "/usr/local/lib/python3.6/dist-packages/sanic/app.py", line 1167, in run
    serve(**server_settings)
  File "/usr/local/lib/python3.6/dist-packages/sanic/server.py", line 920, in serve
    loop.run_forever()
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 126, in send
    return self.gen.send(value)
  File "/usr/local/lib/python3.6/dist-packages/spf/framework.py", line 554, in _handle_request
    stream_callback)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/sanic/app.py", line 1036, in handle_request
    await stream_callback(response)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/sanic/server.py", line 532, in stream_response
    self.request.version, keep_alive, self.keep_alive_timeout
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/sanic/response.py", line 98, in stream
    await self.streaming_fn(self)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/channels/rest.py", line 73, in stream
    on_new_message, text, q, sender_id, input_channel, metadata
Traceback (most recent call last):
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 126, in send
    return self.gen.send(value)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/channels/rest.py", line 47, in on_message_wrapper
    await on_new_message(message)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/channels/channel.py", line 85, in handler
    await app.agent.handle_message(*args, **kwargs)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/agent.py", line 522, in handle_message
    return await processor.handle_message(message)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/processor.py", line 98, in handle_message
    await self._predict_and_execute_next_action(message.output_channel, tracker)
  File "/usr/lib/python3.6/asyncio/coroutines.py", line 110, in __next__
    return self.gen.send(None)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/processor.py", line 563, in _predict_and_execute_next_action
    action, policy, confidence = self.predict_next_action(tracker)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/processor.py", line 285, in predict_next_action
    action_confidences, policy = self._get_next_action_probabilities(tracker)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/processor.py", line 829, in _get_next_action_probabilities
    tracker, self.domain, self.interpreter
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/ensemble.py", line 672, in probabilities_using_best_policy
    tracker, domain, interpreter
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/ensemble.py", line 562, in _best_policy_prediction
    for i, p in enumerate(self.policies)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/ensemble.py", line 562, in <dictcomp>
    for i, p in enumerate(self.policies)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/ensemble.py", line 593, in _get_prediction
    tracker, domain, interpreter
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/ted_policy.py", line 385, in predict_action_probabilities
    [tracker], domain, interpreter
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/tracker_featurizers.py", line 180, in create_state_features
    return self._featurize_states(trackers_as_states, interpreter)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/tracker_featurizers.py", line 73, in _featurize_states
    for tracker_states in trackers_as_states
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/tracker_featurizers.py", line 73, in <listcomp>
    for tracker_states in trackers_as_states
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/tracker_featurizers.py", line 71, in <listcomp>
    for state in tracker_states
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/single_state_featurizer.py", line 201, in encode_state
    self._extract_state_features(sub_state, interpreter, sparse=True)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/featurizers/single_state_featurizer.py", line 169, in _extract_state_features
    parsed_message = interpreter.featurize_message(message)
  File "/usr/local/lib/python3.6/dist-packages/rasa/core/interpreter.py", line 158, in featurize_message
    result = self.interpreter.featurize_message(message)
  File "/usr/local/lib/python3.6/dist-packages/rasa/nlu/model.py", line 415, in featurize_message
    component.process(message, **self.context)
  File "/usr/local/lib/python3.6/dist-packages/rasa/nlu/featurizers/sparse_featurizer/count_vectors_featurizer.py", line 562, in process
    attribute, [message_tokens]
  File "/usr/local/lib/python3.6/dist-packages/rasa/nlu/featurizers/sparse_featurizer/count_vectors_featurizer.py", line 438, in _create_features
    seq_vec = self.vectorizers[attribute].transform(tokens)
  File "/usr/local/lib/python3.6/dist-packages/sklearn/feature_extraction/text.py", line 1267, in transform
    self._check_vocabulary()
  File "/usr/local/lib/python3.6/dist-packages/sklearn/feature_extraction/text.py", line 490, in _check_vocabulary
    raise NotFittedError("Vocabulary not fitted or provided")
sklearn.exceptions.NotFittedError: Vocabulary not fitted or provided

Hmmm, right. @noman was this after training NLU and Core separately, or together? If you train separately, then I’m not sure if I can be of any further help, but you could still share how exactly you combine NLU and Core into a single model :slight_smile:

If you train NLU and Core together and want me to try to reproduce the error, I might also need the NLU data (I’ve got the domain, config, rules and stories already, unless you’ve changed anything in the meantime).

@SamS yes it was after training NLU and Core separately.

I train them separately and combine them using this code:

import os
import sys
import tarfile


def combine_core_model(path):
    model_path_to_unzip = '{}/models/core.tar.gz'.format(path)
    tar = tarfile.open(model_path_to_unzip, mode="r:gz")
    tar.extractall('{}/models'.format(path))

    with tarfile.open('{}/models/core-nlu-combined.tar.gz'.format(path), mode='w:gz') as tar:
        tar.add('{}/models/core'.format(path), arcname='core')
        if os.path.isdir('{}/models/nlu'.format(path)):
            tar.add('{}/models/nlu'.format(path), arcname='nlu')

Its working fine with rasa==1.x

@noman thanks, and sorry for the delay. Perhaps we should take a step back and look at what the error message is saying. Can you check that inside your model archive there is an actual vocabulary saved for your CountVectorsFeaturizer? Here’s how to do it:

  1. unpack the tar archive of your model
  2. navigate to nlu/
  3. find the pickled featurizer vocabulary file (mine was named component_3_CountVectorsFeaturizer.pkl)
  4. load and inspect the contents in Python:
    import rasa.utils.io as io_utils
    vocab = io_utils.json_unpickle(<vocab file>)
    

If the contents look alright (e.g. {'text': {'how': 974, 'are': 117, 'you': 2302, 'something': 1879, ...), then we need to dig deeper.

1 Like

Hi, its fine @SamS , I have tried and my contents are:

there is a problem in 2.x with combining models that were trained separately right now. If nlu exists, rasa core will use its components to featurize intent and action labels. So when you call rasa train core there is no nlu model, and it creates one-hot features for labels, however, when you combine the models during prediction time, nlu interpreter will exist, and rasa core featurization will be different.

We’re working on the solution to make sure that core featurizer persist the information how they were trained and behave appropriately during prediction

2 Likes

created a fix: core featurizers should use regex interpreter if core was trained separately by Ghostvv Β· Pull Request #7316 Β· RasaHQ/rasa Β· GitHub

1 Like

Thanks @Ghostvv . I will try the fix and let you know :slight_smile: