I am working on a project. I have created a chatbot with rasa open source. However, I not able to use fallback policy properly. I have used out_of_scope but it doesn’t serve well. I would be grateful if the chatbot can return the unknown answer with a specific answer like "Sorry, couldn’t understand that! can you rephrase. There is not complete tutorial on that. I am wondering why nlu.yml is not touched there, Fallback and Human Handoff

Here the bot is predicting the user message with the wrong intent. You can use rasa shell nlu to check the confidence of the intent prediction. Based on that you can play with the threshold in config file to meet your needs. pipeline: - name: FallbackClassifier threshold: 0.7 # play with this

Hi, can you show your current implementation?

Can we have a video call on google meet to show the work? my email tashinus@gmail.com

Hi @tsheringtashi , you can post your code or link to GitHub here so others will be able to help as well.

Thanks, I have link embedded in Linkedin . I would like to know how to operate handoff and fallback policy.

Uncomment the pipeline components in the config file There are many stories that can be written as rules (to follow strict behavior)

I have uncommented the pipeline components in the config file. However, the problem remains. I wanted the bot to answer even if there is not intent in nlu.yml. below for instance: User: “who is the president of China?” Bot : “Sorry, I couldn’t understand. can you rephrase it?”

You can add a rule for the Fallback. Here you can find how to implement it.

I am sorry for not understanding Rasa properly. Do I have to use only rules from rules . rules: rule: Ask the user to rephrase whenever they send a message with low NLU confidence steps: intent: nlu_fallback action: utter_please_rephrase

Basically, Stories include multiple conversation paths and patterns (like receiving various info from users) and Rules follow strict behavior (like greeting or asking the user to rephrase)

Thank you, it is working but not meeting the expectation. Again explaining with the used case below: User: Who is the president of America? Bot: Bye What should I do?

Rasa fallback policy

Rasa Open Source

tsheringtashi (Tashi) October 27, 2022, 8:54am 13

thank you. How to deploy the application in docker?

Topic		Replies	Views
How can we perform fallback like in dialogflow if the user enter something the bot doesnt know? Rasa Open Source	14	688	November 21, 2020
Nlu_fallback not working in rasa2.1.2 in my sample application Tutorials, Resources & Videos	3	530	December 15, 2020
Rasa Fallback action failing for Faq Bot Rasa Open Source	2	1356	July 28, 2020
Fall back policy is not working Rasa Open Source	3	1442	August 7, 2023
Fallback problem - Rasa Rasa Open Source	6	316	May 2, 2024

Rasa fallback policy

Related topics