Rasa chatbot training error

Rasa Open Source
1

Hi, I am working on some basic chatbot, while training my bot , I was facing some errors, I didn’t write any action code in actions file. , please help me how to fix it. this is my nlu.md.

intent:greet

  • Good afternoon.
  • Good morning
  • Guten Tag
  • HI
  • Hello
  • Hello?
  • Hey
  • Hey dude
  • Hi
  • Hi bot
  • ahoy
  • good evening
  • good morning
  • hEllo
  • hello
  • hello?
  • hey
  • hey there
  • hey yo
  • hey you
  • heyo
  • hi
  • hi there
  • hii
  • hiya
  • hiyy
  • hoi
  • hola
  • howdy
  • ola amigo
  • what’s good
  • yo
  • hai
  • HELLO
  • happy thanksgiving how are you
  • hello]
  • Hello!
  • Hell
  • Hi my name is Eric
  • oh uh hi
  • hallo
  • hallo?
  • Hello??
  • Hey there
  • hello!
  • Hello. /thanksgiving
  • Hello, and happy Thanksgiving.
  • Hello.
  • yo!
  • hello.
  • Good Morning!
  • Good Morning
  • ih
  • hi\
  • hi again
  • Heyo
  • okay hi
  • Hello robot!v
  • hi bot

intent:restart

  • restart
  • start again
  • start over please
  • let’s start over
  • lets start fresh
  • back to the beginning
  • let’s go back to the start
  • start over
  • can we start again please
  • start
  • Restart
  • get started
  • Let’s begin
  • Start
  • Let’s start again
  • Lets restart
  • That’s ok, can we start over?
  • Let’s start over

intent:thank

  • Great, thanks!
  • Thank you very much for your help.
  • Thank you, dear bot.
  • Thanks
  • Thanks!
  • That shall be it for today. Thank you for the conversation and the link that you have provided.
  • cheers thanks
  • cheers!
  • gracias
  • many thanks
  • ok thank you
  • ok, thanks
  • ta
  • tak
  • thank you
  • thanks
  • thanks I’ll read that
  • thanks for that
  • thanks!
  • thx
  • ok thanks
  • okay thanks for helping
  • thank you so much
  • thans
  • Thank you.
  • Thank you for instrction
  • yes really thank you for sharing this information
  • Thats great thank you
  • Thank you
  • Thank you!
  • awesome, thanks!
  • Thank you :slight_smile:
  • thank you for the info
  • Thank You
  • Thank you, you are a good bot!
  • thank you for your time
  • I will do that, thank you!
  • great thanks!
  • Thank you for the information.
  • Ok, thanks
  • Cool. Thanks.
  • cool, thanks
  • Perfect, thanks
  • Ok thanks
  • hank you
  • good bot
  • Okay thank you
  • Thank you so much
  • oh ok thanks any way
  • thanls
  • That’s great! Thanks for the link
  • oh thaks

intent:goodbye

  • Godspeed
  • Goodbye!
  • I guess we’re done?
  • bye
  • bye for now
  • bye then
  • bye-bye
  • end the conversation
  • good bye
  • good bye for now
  • goodbye
  • no. terminate.
  • please shut up
  • please stop
  • see ya
  • see you
  • see you around
  • see you later
  • shut up
  • sleep!
  • Discontinue my name. Thank you.
  • so long
  • stop
  • STOP
  • end chat
  • thank you, bye
  • goodbye have a nice day
  • ok bye
  • end
  • Leave
  • Good bye
  • Bye
  • Good bye.
  • bye!
  • ok, bye
  • ok goodbye then
  • Goodbye
  • Bye!!
  • Bye!
  • I said goodbye!
  • Well…goodbye.
  • allright then. thank you and goodbye
  • Thanks. I’m done.
  • See you later alligator
  • I live you hood nite
  • go awy
  • I need a donate but I’ll do it when I get a little bit more head of money you have a good day
  • Oh Okay Then I’ll be going
  • Unsubscribe
  • Later
  • Get your business off my phone
  • Hang up
  • OK goodbye

intent : payment_confirm

  • I have done my payment
  • It was paid on july
  • I did pay on time . I have proof on bank statement
  • paid insurance on [7-26-19] (date)
  • paid it on card
  • I already paid my due
  • I paid my due on 8-20-19

intent: faq/ask_channels

  • What channels of communication does rasa support?
  • what channels do you support?
  • what chat channels does rasa uses
  • channels supported by Rasa
  • which messaging channels does rasa support?

intent: faq/ask_languages

  • what language does rasa support?
  • which language do you support?
  • which languages supports rasa
  • can I use rasa also for another laguage?
  • languages supported

intent: faq/ask_rasax

  • I want information about rasa x
  • i want to learn more about Rasa X
  • what is rasa x?
  • Can you tell me about rasa x?
  • Tell me about rasa x
  • tell me what is rasa x

intent:bot_challenge

  • are you a bot?
  • are you a human?
  • am I talking to a bot?
  • am I talking to a human?
  • you are a bot right
  • aren’t you a bot

this is my stories.md file

   ## happy path
  • greet
    • utter_greet
    • utter_help

restart path

  • restart
    • utter_restart

thank

  • thank
    • utter_welcome

say goodbye

  • goodbye
    • utter_goodbye

payment path

  • payment_confirm
    • utter_payment_confirm

Some questions From FAQ

  • faq
    • respond_faq

bot challenge

  • bot_challenge
    • utter_iamabot

this is my domin.yml

session_config:

  session_expiration_time: 0

  carry_over_slots_to_new_session: true

intents:

- greet

- restart

- goodbye

- thank

- faq

- payment_confirm

- affirm

- bot_challenge

entities:

- payment_confirm

slots:

  budget:

    type: unfeaturized

  business_email:

    type: unfeaturized

  company:

    type: unfeaturized

  job_function:

    type: unfeaturized

  person_name:

    type: unfeaturized

  use_case:

    type: unfeaturized

responses:

  utter_greet:

  - text: "Hey! How can I help you"

  utter_restart:

    - text: "ok! we restart."

  utter_goodbye:

  - text: Goodbye then!

  utter_welcome:

  - text: your welcome!

  utter_payment_confirm :

  - text: please could you provide the payment proof

  utter_iamabot :

  - text : I am a bot, powered by Rasa.

actions:

- utter_greet

- utter_goodbye

- utter_welcome

- utter_payment_confirm

- respond_faq

- utter_iamabot

this my response file

## ask channels

* faq/ask_channels

  - We have a comprehensive list of [supported connectors](https://rasa.com/docs/core/connectors/), but if

    you don't see the one you're looking for, you can always create a custom connector by following

    (https://rasa.com/docs/rasa/user-guide/connectors/custom-connectors/).

## ask languages

* faq/ask_languages

  - You can use Rasa to build assistants in any language you want!

## ask rasa x

* faq/ask_rasax

 - Rasa X is a tool to learn from real conversations and improve your assistant. Read more (https://rasa.com/docs/rasa-x/)

this my config.yml file:

Configuration for Rasa NLU.

https://rasa.com/docs/rasa/nlu/components/

language: "en"

pipeline:

  - name: ConveRTTokenizer

  - name: ConveRTFeaturizer

  - name: RegexFeaturizer

  - name: LexicalSyntacticFeaturizer

  - name: CountVectorsFeaturizer

  - name: CountVectorsFeaturizer

    analyzer: "char_wb"

    min_ngram: 1

    max_ngram: 4

  - name: DIETClassifier

    epochs: 100

  - name: EntitySynonymMapper

  - name: ResponseSelector

    epochs: 100

policies:

  - name: MemoizationPolicy

  - name: KerasPolicy

  - name: MappingPolicy

  - name: FormPolicy

Error:

Traceback (most recent call last):
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "C:\Users\suris\anaconda3\envs\installingrasa\Scripts\rasa.exe\__main__.py", line 7, in <module>
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\__main__.py", line 92, in main
    cmdline_arguments.func(cmdline_arguments)
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\cli\train.py", line 76, in train
    additional_arguments=extract_additional_arguments(args),
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\train.py", line 50, in train
    additional_arguments=additional_arguments,
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\asyncio\base_events.py", line 583, in run_until_complete
    return future.result()
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\train.py", line 101, in train_async
    additional_arguments,
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\train.py", line 144, in _train_async_internal
    file_importer.get_stories(), file_importer.get_nlu_data()
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\importers\importer.py", line 269, in get_nlu_data
    nlu_data = await asyncio.gather(*nlu_data)
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\importers\rasa.py", line 61, in get_nlu_data
    return utils.training_data_from_paths(self._nlu_files, language)
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\importers\utils.py", line 9, in training_data_from_paths
    training_datas = [loading.load_data(nlu_file, language) for nlu_file in paths]
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\importers\utils.py", line 9, in <listcomp>
    training_datas = [loading.load_data(nlu_file, language) for nlu_file in paths]
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\nlu\training_data\loading.py", line 67, in load_data
    data_sets = [_load(f, language) for f in files]
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\nlu\training_data\loading.py", line 67, in <listcomp>
    data_sets = [_load(f, language) for f in files]
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\nlu\training_data\loading.py", line 138, in _load
    return reader.read(filename, language=language, fformat=fformat)
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\nlu\training_data\formats\readerwriter.py", line 15, in read
    return self.reads(rasa.utils.io.read_file(filename), **kwargs)
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\nlu\training_data\formats\markdown.py", line 100, in reads
    self._set_current_section(header[0], header[1])
  File "c:\users\suris\anaconda3\envs\installingrasa\lib\site-packages\rasa\nlu\training_data\formats\markdown.py", line 315, in _set_current_section
    "".format(section, "', '".join(available_sections))
ValueError: Found markdown section 'intent ' which is not in the allowed sections 'intent', 'synonym', 'regex', 'lookup'.
2

This seems to be an issue of formatting. First of all you should define your responses in the domain.yml in the responses section and refer to them in the stories file instead of directly writing the answers in the stories. You would get an error from that if the process wouldnt fail before.

The error you’re getting now seems to be from the nlu.md file. I see that you’re inconsistent with the spaces between the intent keyword and the intent name (intent: faq..., intent : payment..., intent:goodbye). Also I’m not sure if you can use slashes ("/") in the intent names.

You might want to try those things and see what makes a difference.

3

Thank you for your reply vale_boca, I some doubts regarding the dates format , how to write a dates in intents