When I upload a model to Rasa X (using Helm chart deployment on GKE) with the latest version of Rasa X (0.33) and Rasa 2.0.2, talking to the bot does not work as it should:
The input is set equal to the intent (i.e. if I say hello the intent = hello but if I say bananas the intent = bananas (see picture below).
The bot keeps loading (…) (see picture below as well)
EDIT: I do have the opportunity to adjust the correct intent (then all of my intents are listed) (see image below)
EDIT 2: Also when I test it locally, the input gets mapped to one of the intents available in my NLU.
I could not find anything about this on the forum, so if you can guide me to the solution to this would be really nice!
Thanks in advance
November 20, 2020, 1:44pm
To be clear, you mean that the model works as expected locally?
If you’re seeing this behavior in Rasa X server mode but not running the model locally or in Rasa X local mode, it sounds suspiciously like a bug we’ve pinned down when using rasa open source >= 2.0.3. Are you sure that you are running 2.0.2?
If so, can you provide the logs of the rasa-production container? For some reason it seems that your NLU model is not getting loaded correctly, so a RegexInterpreter is being used in its place.
I am using Rasa 2.0.2 (see the picture below):
It might have to do with the fact that my component folder is not mounted correctly as when I open the production container I receive the error:
ModuleNotFoundError: No module named 'components
I also opened a question for this here:
How to mount components folder when deploying through Helm charts?
Do you believe that it has to do with this (if so can you help me fix it)? If not, what can then be the problem?
Thanks for your reply!
November 20, 2020, 2:14pm
Ah yes that almost certainly is the issue! I’ll follow up with you on that thread!
Would please take a look on my thread?
I think it’s the same original problem from Fabrice but I just followed the steps
quick-install, nothing else, then at the first test on a simple bot … Rasa X doesn’t work properly!!
I really appreciate your time!!!