Deploy Rasa Core separately

Hi All,

Is it possible to deploy Rasa Core separately like Rasa NLU?

I dont want to pass NLU model path to rasa core.

I want to pass my conversations to Rasa NLU, then pass result from NLU to Core API.

Rasa NLU and core are now merged into one repo

I want to use to only use RASA core for my usecase not RASA NLU. Is it possible?

Rasa NLU will be there, but you don’t need to use it

Rasa core accepts message in this form - {“message”: “hi”, “sender_id”: “1”}

But I want to send predicted intent from my NLU model to rasa core api directly. How can I achieve this?

I checked two APIs just now -

Add a message to a tracker - http://localhost:5005/conversations/{conversation_id}/messages

Predict the next action - http://localhost:5005/conversations/{conversation_id}/predict

I think these two API will help in achieving the functionality that I want.

Is conversation_id = sender_id ?

@r4sn4 yes, conversation_id == sender_id :slight_smile: Also you can always send intent format from your NLU to rasa core:

{“message”: "/intent{"entity": "some_value"}, “sender_id”: “1”}

Thanks @erohmensing :slight_smile: