All - Activity - depicus - Rasa Community Forum

Rasa X not showing responses

Yes looks like Rasa-X on Linux has been broken for a while. Even if you rasa init and take the trained model from that you still get the … reply. If I check the logs with sudo docker-compose logs -t rasa-x there are a lot of 404 errors which is probably the issue. Hopefully they will fix soon but 0.…

AttributeError: Can't get attribute 'FeatureArray' on <module 'rasa.utils.tensorflow.model_data'>

Just tried with a clean install of 0.35 and still doesn’t work - version 2 seems to be VERY buggy.

I’m using the official Docker files so tied to whatever version of Python the script says sadly but thanks for the tip.

No Rasa-x does nothing but the model seems to be missing the intents and stories despite training perfectly without errors or warnings at the command line. The intent carddetails was found in the domain but is missing in the training data.

I have the same issue 2021-01-09 12:58:22 ERROR rasa.core.agent - Failed to update model. The previous model will stay loaded instead.

Private Docker Image from DockerHub in Rasa-X k3s quick install

Thanks, we moved to just using Docker as it’s faster for us to provision but hopefully one day I’ll get time to revisit and try again.

Rasa Open Source 2.0 is out now!

Yes old format because I didn’t know about the new one and it’s not front and centre on the upgrade info. Trained ok on the laptop so I’ll put into test next week when I have more time.

Ok managed to train on the laptop but uploading the model to the server and if you ask a question it never replies !!! Going to be a long day today.

Still trying to work out but using RASA X it now won’t train so having to build a RASA version on my laptop so I can see what the error is, so far half way through and no errors so far. Docker logs show a lot of 404 errors to http://rasa-x:5002/api/projects/default/models/tags/production?token=K1voL…

Would have been nice to get a heads up about the changes on the update page as I’ve just upgraded and now everything gone to shit.

Rasa connection (with Docker) with socketio for my own website

Just a hint on how I just resolved it. For me I logged into my docker server and then cd /etc/rasa and then edit the credentials.yml file and add:

socketio:
  user_message_evt: user_uttered
  bot_message_evt: bot_uttered
  session_persistence: true

This was Aug 2020 so YMMV.

I have a private docker image on Dockerhub which I can docker pull after using docker login but if I use the Rasa-X quick install with the k3s when I call sudo kubectl get pods --namespace=rasa I get an ErrImagePull on the rasa-app and if I query with sudo kubectl describe pod rasa-app-86694b5bff-…

It’s actually kubectl get pods --namespace=rasa and I have the same issue which is an ErrImagePull and to get the logs (not that you need them) kubectl logs rasa-app-6f55dd6695-lvcnf --namespace=rasa. Just remember the app name will be different.

Make sure you are running your docker run command in the directory where your credentials.yml and models are located.

I’ve used the one stop install script to install Rasa and Rasa X using Multipass on my Mac. So far so good, I had a previous model with some training and managed to get it on Github and into Rasa X and I’ve had somebody else try it from the links but I’m struggling to make it production ready.