All - Activity - vijmeister - Rasa Community Forum

vijmeister

I am a Data Scientist with work experience at IBM and BJs Wholesale. I have extensive domain knowledge of Biomedical Engineering, Manufacturing, Semiconductors, NLP, AI, Software Development, and Big Data.

Unable to train sara/rasa-demo bot in rasa x GCP Docker

Seems to still train for a comparable amount of time.

It is unable to train on a small repo.

Typically 1 hour.

No custom changes. Initially, I tried 0.38.x and then upgraded to 0.39.x. I’m wondering if the VM has to be configured in a particular way to use NGINX?

Including @mloubser

I have just set up rasa x in gcp vm (computer engine) via docker (not the manual install). The model spends some time trying to train and then fails. Here are a few excerpts from the log. @erohmensing, do you have any thoughts?

How to enable autoscaling using helm in gke

Sure, @mloubser. I did steps 1-8 here: Helm Chart Installation. I also did multidimensional scaling: Configuring multidimensional Pod autoscaling.

I have been stuck with running the rasa-demo (sara) in gke using vertical and horizontal scaling. Helm manages/overwrites this setting and I am unable how to fix this from looking at helm’s documentation. Has anyone been able to do this? Thanks!

Trouble migrating Rasa-demo (Sara) to gitlab

Hi, I am struggling to migrate the build_and_deploy.yml to a valid .gitlab_ci.yml file because it is rather complex and I am still learning the idiosyncrasies of gitlab vs github actions. I have been trying to manually convert the file into 2 editors (pycharm and the gitlab gui) but I cannot produce…

Concert bot in 2.1x : problem with intents

Sorry for the delay, @fkoerner. So many things happening in this world.

Package Version Location

Rasa Sara : problems with action server

I am trying to run Sara (GitHub - RasaHQ/rasa-demo: 🐯 Sara - the Rasa Demo Bot: An example of a contextual AI assistant built with the open source Rasa Stack) and I have problems chatting and utilizing the action server. No registered action found for name ‘action_greet_user’.

Successfully integrated Rasa Knowledge Base bot given in examples with neo4j knowledge graph

hey @noman, do you have a repo that you can share? I would really appreciate it.

Building an app on google cloud

Instead of using a ui to interact with the assistant, the user could use a shell.

Thanks, Ella. I was also wondering if I want to set up terminals for multiple users, would I need to use rasa core with a VM cluster instead of rasa x? If so, do you have a recommended type of container (Docker, Kubernetes, etc.)?

Hi everyone, I am currently trying to run a rasa app on GKE but my cluster is not sufficiently sized to handle the application. I was wondering if anyone knows of any recommended settings that I should try? Thanks!

I figured it out - my instance did not have the recommended configuration. This video helped me fix it: Installing Rasa X: Windows 10 (64 bit) and Google Cloud Platform - YouTube
Vijay

Ah, it works now! Thank you. However, it gets stuck on the Deploying Rasa Instance step - is there something else that needs to be done?

Thanks, Ella! I have tried the quick install command in my gcp shell and see the following error:

curl -s http://get-rasa-x.rasa.com/ | sudo bash

The connection to the server localhost:8080 was refused - did you specify the right host or port?

Hey everyone, I would like to build a Rasa app on GCP. Most of the examples that I have seen online use docker but I am wondering if there is a better way to do it with just a VM? Is there a very good example?

Is it possible to pass in a file and get an analysis (such as named entity recognition to make knowledge graphs)?

Can you please try again but this time run rasa train and not rasa train core?

As an aside, all of the domain/config/stories files in this example are named with default names, so you can get away without specifying them.