Communication between Rasa Server and Rasa-X

Hi

I have my Rasa server and Action Server running independently on different server (through CI-CD pipeline).

Now I want to deploy Rasa x (and not Rasa server) separately.

I have following questions:

  1. How is communication between Rasa and Rasa-X will happen?

  2. Why is communication between Rasa and Rasa-X is important?

Correct my understanding:

The communication between Rasa and Rasa-X is important because then we can visualize actual conversations coming to our bot (Rasa Server) and correct it (required action and intent) in Rasa-X.

Hence communication between rasa and rasa-x is important. Is my understanding correct?

3. Does this communication happen through Message broker like Rabbit MQ?

If I configure then is that all I need to have communication between Rasa Sever and Rasa-X?

4. What if I don’t care about communication happening between Rasa and Rasa-X.

Instead I will manually upload pre-trained model in rasa-x and then see the performance.

I don’t want to manually upload a model in Rasa-X every-time when I train it. Can we automate this step? I am sure there must be some API do achieve this?

Can you please reply these questions and may be additional points which I might have missed?

  • the communication between Rasa X and Rasa server is about the messages that are directed to your bot. The aim is Rasa X is for you to continually improve your bot by fetching new training data from conversations that is happening between your deployed rasa bot and the users. this lets you fetch new data you would curate to retrain a better model which then is deployed back for more inference

you have the REST API of Rasa X to upload trained model https://rasa.com/docs/rasa-x/pages/http-api