Rasa form not working

I have set up a Rasa bot using Rasa 1.10.17. The bot works well except that the form action is not working. Form does not trigger at all each time I call the form. I have attached the relevant file links:

Github repo: GitHub - edmundrotimi/rasabot

Erorr Log: rasabot/errorlog.txt at master · edmundrotimi/rasabot · GitHub

Error Log:

2020-11-30 04:55:15 DEBUG rasa.core.lock_store - Issuing ticket for conversation ‘37ea4b66f7c741198fa39936b9c945ab’. 2020-11-30 04:55:15 DEBUG rasa.core.lock_store - Acquiring lock for conversation ‘37ea4b66f7c741198fa39936b9c945ab’. 2020-11-30 04:55:15 DEBUG rasa.core.lock_store - Acquired lock for conversation ‘37ea4b66f7c741198fa39936b9c945ab’. 2020-11-30 04:55:15 DEBUG rasa.core.tracker_store - Creating a new tracker for id ‘37ea4b66f7c741198fa39936b9c945ab’. 2020-11-30 04:55:15 DEBUG rasa.core.processor - Starting a new session for conversation ID ‘37ea4b66f7c741198fa39936b9c945ab’. 2020-11-30 04:55:15 DEBUG rasa.core.processor - Action ‘action_session_start’ ended with events ‘[<rasa.core.events.SessionStarted object at 0x0000017BF3E4E948>, <rasa.core.events.ActionExecuted object at 0x0000017BF51C6C08>]’. 2020-11-30 04:55:15 DEBUG rasa.core.processor - Current slot values: ADDRESS: None FEE: None FULLNAME: None KG: None KILOMETER: None PHONE: None PICKUP: None SERVICE: None requested_slot: None 2020-11-30 04:55:15 DEBUG rasa.nlu.classifiers.diet_classifier - There is no trained model for ‘ResponseSelector’: The component is either not trained or didn’t receive enough training data. 2020-11-30 04:55:15 DEBUG rasa.nlu.selectors.response_selector - Adding following selector key to message property: default 2020-11-30 04:55:15 DEBUG rasa.core.processor - Received user message ‘hi’ with intent ‘{‘name’: ‘greet’, ‘confidence’: 0.995304524898529}’ and entities ‘[]’ 2020-11-30 04:55:15 DEBUG rasa.core.processor - Logged UserUtterance - tracker now has 4 events. 2020-11-30 04:55:15 DEBUG rasa.core.policies.memoization - Current tracker state [None, None, None, {}, {‘intent_greet’: 1.0, ‘prev_action_listen’: 1.0}] 2020-11-30 04:55:15 DEBUG rasa.core.policies.memoization - There is a memorised next action ‘utter_menue’ 2020-11-30 04:55:15 DEBUG rasa.core.policies.form_policy - There is no active form 2020-11-30 04:55:15 DEBUG rasa.core.policies.ensemble - Predicted next action using policy_0_MemoizationPolicy 2020-11-30 04:55:15 DEBUG rasa.core.processor - Predicted next action ‘utter_menue’ with confidence 1.00. 2020-11-30 04:55:15 DEBUG rasa.core.processor - Action ‘utter_menue’ ended with events '[BotUttered('Welcome to Rhema Gas interactive service platform for all things gas. Get started with our interactive menue: ‘, {“elements”: null, “quick_replies”: null, “buttons”: [{“pyloads”: “cylinder_refill”, “title”: “Gas Cylinder Refill”}, {“pyloads”: “gas_repair”, “title”: “Repair and Metainance Services”}, {“pyloads”: “cylinder_painting”, “title”: “Cylinder Painting”}, {“pyloads”: “cylinder_purchase”, “title”: “Gas Cylinder Purchase”}, {“pyloads”: “gas_part”, “title”: “Buy Parts”}, {“pyloads”: “contact_us”, “title”: “Contact Us”}], “attachment”: null, “image”: null, “custom”: null}, {}, 1606708515.5276608)]’. 2020-11-30 04:55:15 DEBUG rasa.core.policies.memoization - Current tracker state [None, None, {}, {‘intent_greet’: 1.0, ‘prev_action_listen’: 1.0}, {‘prev_utter_menue’: 1.0, ‘intent_greet’: 1.0}] 2020-11-30 04:55:15 DEBUG rasa.core.policies.memoization - There is a memorised next action ‘action_listen’ 2020-11-30 04:55:15 DEBUG rasa.core.policies.mapping_policy - There is no mapped action for the predicted intent, ‘greet’. 2020-11-30 04:55:15 DEBUG rasa.core.policies.form_policy - There is no active form 2020-11-30 04:55:15 DEBUG rasa.core.policies.ensemble - Predicted next action using policy_0_MemoizationPolicy 2020-11-30 04:55:15 DEBUG rasa.core.processor - Predicted next action ‘action_listen’ with confidence 1.00. 2020-11-30 04:55:15 DEBUG rasa.core.processor - Action ‘action_listen’ ended with events ‘[]’. 2020-11-30 04:55:15 DEBUG rasa.core.lock_store - Deleted lock for conversation ‘37ea4b66f7c741198fa39936b9c945ab’. ? Welcome to Rhema Gas interactive service platform for all things gas. Get started with our interactive menue:
1: Gas Cylinder Refill - {“pyloads”: “cylinder_refill”}
2020-11-30 04:55:21 DEBUG rasa.core.lock_store - Issuing ticket for conversation ‘37ea4b66f7c741198fa39936b9c945ab’. 2020-11-30 04:55:21 DEBUG rasa.core.lock_store - Acquiring lock for conversation ‘37ea4b66f7c741198fa39936b9c945ab’. 2020-11-30 04:55:21 DEBUG rasa.core.lock_store - Acquired lock for conversation ‘37ea4b66f7c741198fa39936b9c945ab’. 2020-11-30 04:55:21 DEBUG rasa.core.tracker_store - Recreating tracker for id ‘37ea4b66f7c741198fa39936b9c945ab’ 2020-11-30 04:55:21 DEBUG rasa.nlu.classifiers.diet_classifier - There is no trained model for ‘ResponseSelector’: The component is either not trained or didn’t receive enough training data. 2020-11-30 04:55:21 DEBUG rasa.nlu.selectors.response_selector - Adding following selector key to message property: default 2020-11-30 04:55:21 DEBUG rasa.core.processor - Received user message ‘1: Gas Cylinder Refill - {“pyloads”: “cylinder_refill”’ with intent ‘{‘name’: ‘maintenance_cooker_ignation’, ‘confidence’: 0.234479159116745}’ and entities ‘[]’ 2020-11-30 04:55:21 DEBUG rasa.core.processor - Logged UserUtterance - tracker now has 8 events. 2020-11-30 04:55:21 DEBUG rasa.core.policies.memoization - Current tracker state [None, {}, {‘intent_greet’: 1.0, ‘prev_action_listen’: 1.0}, {‘prev_utter_menue’: 1.0, ‘intent_greet’: 1.0}, {‘intent_maintenance_cooker_ignation’: 1.0, ‘prev_action_listen’: 1.0}] 2020-11-30 04:55:21 DEBUG rasa.core.policies.memoization - There is no memorised next action 2020-11-30 04:55:21 DEBUG rasa.core.policies.form_policy - There is no active form 2020-11-30 04:55:21 DEBUG rasa.core.policies.ensemble - Predicted next action using policy_1_TEDPolicy 2020-11-30 04:55:21 DEBUG rasa.core.processor - Predicted next action ‘utter_menue’ with confidence 0.37. 2020-11-30 04:55:21 DEBUG rasa.core.processor - Action ‘utter_menue’ ended with events '[BotUttered('Welcome to Rhema Gas interactive service platform for all things gas. Get started with our interactive menue: ‘, {“elements”: null, “quick_replies”: null, “buttons”: [{“pyloads”: “cylinder_refill”, “title”: “Gas Cylinder Refill”}, {“pyloads”: “gas_repair”, “title”: “Repair and Metainance Services”}, {“pyloads”: “cylinder_painting”, “title”: “Cylinder Painting”}, {“pyloads”: “cylinder_purchase”, “title”: “Gas Cylinder Purchase”}, {“pyloads”: “gas_part”, “title”: “Buy Parts”}, {“pyloads”: “contact_us”, “title”: “Contact Us”}], “attachment”: null, “image”: null, “custom”: null}, {}, 1606708521.2993839)]’. 2020-11-30 04:55:21 DEBUG rasa.core.policies.memoization - Current tracker state [{}, {‘intent_greet’: 1.0, ‘prev_action_listen’: 1.0}, {‘prev_utter_menue’: 1.0, ‘intent_greet’: 1.0}, {‘intent_maintenance_cooker_ignation’: 1.0, ‘prev_action_listen’: 1.0}, {‘intent_maintenance_cooker_ignation’: 1.0, ‘prev_utter_menue’: 1.0}] 2020-11-30 04:55:21 DEBUG rasa.core.policies.memoization - There is no memorised next action 2020-11-30 04:55:21 DEBUG rasa.core.policies.mapping_policy - There is no mapped action for the predicted intent, ‘maintenance_cooker_ignation’. 2020-11-30 04:55:21 DEBUG rasa.core.policies.form_policy - There is no active form 2020-11-30 04:55:21 DEBUG rasa.core.policies.ensemble - Predicted next action using policy_1_TEDPolicy 2020-11-30 04:55:21 DEBUG rasa.core.processor - Predicted next action ‘action_listen’ with confidence 0.98. 2020-11-30 04:55:21 DEBUG rasa.core.processor - Action ‘action_listen’ ended with events ‘[]’. 2020-11-30 04:55:21 DEBUG rasa.core.lock_store - Deleted lock for conversation ‘37ea4b66f7c741198fa39936b9c945ab’.

Any help will be appreciated as I can’t seem to figure out what I am doing wrong. Thanks

Hi @rt_ty,

It looks like your form is triggered with the following intent/entity payload:

cylinder_refill{"SERVICE": "Gas Cylinder Refill"}

But your button from your menu is returning:

1: Gas Cylinder Refill - {“pyloads”: “cylinder_refill”}

You should set your buttons in menu similar to the following:


utter_menue:
    - buttons:
      - payload: /cylinder_refill{"SERVICE": "Gas Cylinder Refill"}
        title: Gas Cylinder Refill

The / preceding the intent and entities tells Rasa to bypass NLU and send the intent and entities directly to the dialog manager. This is a typical design pattern.

Thanks @kearnsw for the reply, will try it now.