Hi I have a form. When I post a query with right intent. Form gets activated and it asks for the slot value. All good here. But if I interrupt by posting the same question(the one that activated form), I get action_execution_rejected and post this TEDPolicy selects out of blue utter_iamabot
which is not at all related to the form
please help. I am stuck for a day now.
rules.yml
version: "3.1"
rules:
- rule: Say goodbye anytime the user says goodbye
steps:
- intent: goodbye
- action: utter_goodbye
- rule: Say 'I am a bot' anytime the user challenges
steps:
- intent: bot_challenge
- action: utter_iamabot
- rule: activate JD Parse form
steps:
- intent: parse_jd # intent that triggers form activation
- action: jd_parse_form # run the form
- active_loop: jd_parse_form # this form is active
- rule: submit form
condition:
- active_loop: jd_parse_form # this form must be active
steps:
- action: jd_parse_form # run the form
- active_loop: null # the form is no longer active because it has been filled
- action: inform_intent # action to take after the form is complete
nlu.yml
- intent: parse_jd
examples: |
- Parse JD
- Can you parse this JD [https://jobs.lever.co/findem/3a70e7d9-0a5c-4f73-a044-8f6a06455c50](url)
- Parse job Description [https://jobs.lever.co/findem/3a70e7d9-0a5c-4f73-a044-8f6a06455c50](url)
- job Description
stories.yml
- story: bot challenge
steps:
- intent: bot_challenge
- action: utter_iamabot
domain.yml
forms:
jd_parse_form:
required_slots:
- jd_url
utter_ask_jd_url:
- text: Please share the url for job description and I will build a search for you.
utter_iamabot:
- text: I am your AI power assistant to help you with your search.
Sequence
- Message to rasa: Can you parse this JD –>(activates form)
- Bot asking for slots: Please share the url for job description and I will build a search for you.
- Message to rasa: Can you parse this JD –>(Same as original trigger intent causes
action_execution_rejected
) - Bot utters
utter_iamabot
: I am your AI power assistant to help you with your search. (selected by TEDPolicy)