search

aws-solutions / qnabot-on-aws

AWS QnABot is a multi-channel, multi-language conversational interface (chatbot) that responds to your customer's questions, answers, and feedback. The solution allows you to deploy a fully functional chatbot across multiple channels including chat, voice, SMS and Amazon Alexa.
https://aws.amazon.com/solutions/implementations/aws-qnabot
Apache License 2.0
401 stars 253 forks source link

Seamless switching in between specialty bots #695

Closed ARUNIMA1314 closed 5 months ago

ARUNIMA1314 commented 9 months ago

Currently, in order to switch from one specialty bot to another, first we need to type in a phrase like exit, quit or bye, and then, type in a triggering phrase to start routing to another bot. This is a little inconvenient since users most likely wouldnt chat with a chatbot and type exit and then ask queries for another category. I tried to achieve seamless switching by adding a exit_routing intent in my specialty lex v1 bots and adding a fulfillment lambda in that intent, so that whenever the user enters an utterance matching with that intent, the routing is stopped and also that utterance would work as a triggering phrase to start routing to another bot. I'm able to stop the routing in the current bot but routing to the other bot is not working. How can I do this?

dougtoppin commented 9 months ago

@ARUNIMA1314 We will discuss and get back to you on this.

fhoueto-amz commented 8 months ago

We will analyze this for prioritization and keep you updated.

abhirpat commented 5 months ago

Hi @ARUNIMA1314, this issue should be addressed with the latest release v6.0.0 from changes in #726. To provide you with additional details of this mechcanism, if you notice on line 475, the dialog state of Fulfilled or Close will exit and provide welcomeBackMessage message. I'd recommend to try this functionality in 6.0.0 and let us know if you still have any questions or concerns. For now, I will archive this issue.

Please refer to CHANGELOG for additional details about this release. Thank You!