WHY i am getting this issue

Rasa Open Source
1

{“event”: “user”, “timestamp”: 1613025055.9492116, “text”: “c”, “parse_data”: {“intent”: {“id”: 486301215759981951, “name”: “confirm_c”, “confidence”: 0.9993846416473389}, “entities”: [], “text”: “c”, “message_id”: “48bfcf33ff2341ad9e84863a99d3fa1d”, “metadata”: {}, “intent_ranking”: [{“id”: 486301215759981951, “name”: “confirm_c”, “confidence”: 0.9993846416473389}, {“id”: -2302161102145149566, “name”: “greet”, “confidence”: 0.0001463312073610723}

WHEN I GOT THE INTENT confirm_c WITH 99% confidence then why it is going to fallback my config - fallback

  • name: FallbackClassifier threshold: 0.8
2

Hi @yugalahir,

Could you post the contents of you config and domain files please?

3

Config.py

Configuration for Rasa NLU.

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

language: en

pipeline:

# No configuration for the NLU pipeline was provided. The following default pipeline was used to train your model.

# If you’d like to customize it, uncomment and adjust the pipeline.

# See Tuning Your NLU Model for more information.

  • name: WhitespaceTokenizer
  • name: RegexFeaturizer
  • name: LexicalSyntacticFeaturizer
  • name: CountVectorsFeaturizer
  • name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4
  • name: DIETClassifier epochs: 150
  • name: EntitySynonymMapper
  • name: ResponseSelector epochs: 150
  • name: FallbackClassifier threshold: 0.8

Configuration for Rasa Core.

https://rasa.com/docs/rasa/core/policies/

policies:

# No configuration for policies was provided. The following default policies were used to train your model.

# If you’d like to customize them, uncomment and adjust the policies.

# See Policies for more information.

- name: MemoizationPolicy

- name: TEDPolicy
  max_history: 5
  epochs: 100

- name: RulePolicy

DOMAIN.py version: “2.0”

intents:

  • greet
  • goodbye
  • affirm
  • bot_challenge
  • confirm_c
  • confirm_r
  • consent
  • loc_whats_app
  • date_picker
  • am_pm

actions:

  • action_consent_api
  • action_loc_whats_app
  • action_confirm_c
  • action_confirm_r

responses: utter_greet:

  • text: “Hello! Welcome to THE One virtual bot. How may I assist you today”

utter_cheer_up:

utter_did_that_help:

  • text: “Did that help you?”

utter_happy:

  • text: “Great, carry on!”

utter_goodbye:

  • text: “Bye”

utter_iamabot:

  • text: “I am a bot, powered by UCS.”

utter_default: - text: “Sorry I didn’t get that. Can you rephrase?”

session_config: session_expiration_time: 60 carry_over_slots_to_new_session: true

Custom actions are also there, and i need when intent classify with high confidence , it must pick that rather than fallback

Thank you

4

CONFIG.py pipeline:

  • name: WhitespaceTokenizer
  • name: RegexFeaturizer
  • name: LexicalSyntacticFeaturizer
  • name: CountVectorsFeaturizer
  • name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4
  • name: DIETClassifier epochs: 150
  • name: EntitySynonymMapper
  • name: ResponseSelector epochs: 150
  • name: FallbackClassifier threshold: 0.8

Configuration for Rasa Core.

policies:

- name: TEDPolicy
  max_history: 5
  epochs: 100
5

If you use a code block:

Like this

It will be much easier for me to read!

6

Ok, here what I am doing is making Number based chat for what app, I made a middleware API because I am using Vonage.

so any suggestion related to Number based chat (IVR)

Example like

press 1 for TV
press 2 for Mobile
press 3 for AC
press 4 for Exit



I also need the story or context name in my action.py

THANK YOU so much for your help :slight_smile: