Getting rasa command not found

pip show rasa displays rasa info…but i am still getting same error on training the model or even using rasa init

NLU detects random input with wrong intent that is none with zero confidence

The words you have mentioned above like "aoa, klh, umh” are termed as gibberish content, After 0.12 rasa returns intent as None for these cases as these are termed as out of scope messages. I have also seen these with tensorflow_embedding, you can either try a different intent classifier like miti...

NLU bot displaying null when entering alphanumeric word i.e SR85296341

The image shows a number of only id’s mentioned in my training data

...

yes i have provided enough amount of training data including just ID and ID + surrounding

Handoff to Human Agent

As i can say if i am getting you right, you can define another fallback action for generic fallback which will work according to the threshold you would have mentioned in your training script and you can mention that action name in your training script.

Forms - validation is getting skipped

Hey! I tried calling action_listen (in interactive learning) but after calling action_listen it asks for next user input. In that case, I will not be able to instruct the bot for activating the form.

...

Here is the debug trace when I am calling for software form to be activated (on using --debug flag)

Which Python version on AWS instance?

I read somewhere in issues that python 3.7 has right now no compatibility with tensorflow and also with rasa, so it's better to have version 3.6.

Fallback

No you don’t have to change it everytime… See it depends on your training data… The nlu threshold you have entered is too high 0.8 is very high… do one thing I’ll prefer changing your pipeline to tensorflow... why tensorflow? Because tensorflow works well for intent classification with higher confidence.