Posts

Showing posts with the label chatbot

How to set default action in Rasa

How to set default action in Rasa Using vanilla Rasa NLU will cause Rasa core to make use of the outputs of the highest probability of an intent or entity value. In other words, even if the probability of an intent is low, and yet it is the highest of all the options, it is still taken by Rasa core as the intent the user is conveying. How do I make it so that Rasa core performs a default action if the probability of the maximum probability intent provided by the NLU is below a certain threshold, say 5%? 1 Answer 1 This feature was added recently and is called Fallback Policy . See documentation here: https://core.rasa.com/patterns.html?highlight=fallback%20policy#fallback-default-actions By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of...

Can't get heroku procfile

Can't get heroku procfile I'm trying to build up a deep-learning-based facebook chatbot (using Python). I'm trying to deploy it on Heroku firstly, but as I'm using the command web: gunicorn echoserver:app the terminal says web: command not found . Howevere, I've installed gunicorn already. web: gunicorn echoserver:app web: command not found gunicorn 2 Answers 2 This is because you are typing web: , which is not a command line interface (CLI) command. web: If you've installed gunicorn , then the command (from the CLI) is gunicorn . Something like, for instance gunicorn gunicorn gunicorn echoserver:app I suppose it's also possible that you have a Windows machine. gunicorn does not work on Windows, so you would need to use something like waitress . With waitress , you would type web: on a Windows machine, so that it would be something like gunicorn waitress waitress...