Hello everyone,
I am a self taught Rasa programmer who needs some help.
Currently, I am attempting to implement my Rasa (3.6.20) chatbot into an EC2 AWS instance by following this tutorial: Create your chatbot using Rasa and deploy it on AWS | by Vishnu Sivan | Coinmonks | Medium.
After completing said tutorial, I have run into an issue that everyone else seems to have run into based off of the comments, but no one seems to have solved. The issue is that the bot does not respond to my inputs.
After lots of hours of testing and debugging, I’ve narrowed the problem down to one thing that is most likely causing the issue, my DIETClassifier.
When run locally, the bot works perfectly fine, same with when run on a live server through rasa run.
When I train it and run it on my server, however, and run it with rasa shell --debug, I get an error when trying to parse the input:
rasa.nlu.classifiers.diet_classifier - There is no trained model for ‘DIETClassifier’: The component is either not trained or didn’t receive enough training data.
This is where I’m stuck, I’ve tried just about everything I feel like and don’t understand why I am getting this error only when running the bot through my EC2 instance.
Please feel free to ask me for any clarifying details if that will help you with diagnosing this problem.
Any help is greatly appreciated, thanks.