All - Activity - niveK - Rasa Community Forum

Rasa model versioning in s3?

I’d recommend synchronizing your local models folder with S3 at the end of the training session and using the model from S3 as a build artifact. You can use the below commands to do so with the AWS CLI in a script as part of your CI/CD (I have it set up as a step in my GitHub Actions, for example) …

Trigger or activate a storie after another one

As @nik202 mentioned, you want to store that information in a slot. You can build the pattern whereby:

User: I need help with

Bot:

Bot: Did that help? Yes/No

User: No

Bot: Would you like to create a ticket? Yes (/create_ticket) / No (/deny…

Format response yml for custom response for different channels

There’s no rasa channel AFAIK, I believe rasa-x uses the rest channel based on this. Just keep in mind whether you’re using the REST or callback channel for anything user-facing.

How to get Entities in Docker compose?

I think you’re just missing the endpoints.yml specification in the command, so it would be:

version: '3.0'
services:
rasa:
  image: 'rasa/rasa:2.5.0-full'
  ports:
    - '5005:5005'
  volumes:
    - './:/app'
  command:
    - run
    - -m
    - models
    - --cors
    - "*"

or this (whatever your preference):

command: ["run", "-m", "models", "--cors", "*", "--debug"]

Any way to increase visibility on tracker db connection loss?

Bumping again, anyone from the Rasa team have any thoughts?

When are stories necessary?

Typically stories are good for branching paths – rules are good, but they’re not machine learning, really. It’s possible to use a form to handle conditional form logic, but stories are good for also capturing multi-turn interactions that branch into different areas. There’s a good example in the docs.

Any way to recreate BinarySingleStateFeaturizer performance with TEDPolicy?

Hi, I’m currently on Rasa 1.10.20, will be upgrading to 2.0 soon. Made the switch over to the TED policy and I’m noticing that the predictions are not really following the stories all that well. A lot of my utterances use very similar vocabulary, so my hunch is that could be causing the incorrect…

Guidelines to best deploy Rasa Stack to AWS?

I haven’t made any changes to my current deployment (still running on an instance managed through Elastic Beanstalk). For a Rasa X deployment using Docker Compose, I’d recommend checking out this installation guide. That being said, I’d recommend creating an EC2 instance and running the server quick install.

Issues regarding data validation script and with slots/entities and followups from custom actions

Actually, just changed this and I got the following error:

Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/home/runner/work/venus/venus/venus/data/validator.py", line 27, in main

Help with rasa context

The memoization policy would definitely help, but I don’t think it’s strictly necessary. All the memoization policy does is memorize your stories so it can predict intended behavior from stories much more clearly.

Rasa train gives "NameError: Cannot access action 'action_facility_search', as that name is not a registered action for this domain" error

You need to rename action_facility_search to facility_search in your actions section of your domain.yml, actions with prefix actions_ are Rasa default action overrides, which is why I think you are having issues.