Continuing the discussion from How to change model runtime?:
If you are using Rasa as a server, you can change the model with the HTTP API..
However, if you wish to dynamically swap out a model as stated in the previous post (e.g. when processing a new message), you’d have to write some custom implementation for that, since Rasa only supports one NLU model per conversation. Could you state what problem you’d like this functionality to solve? Perhaps there is another solution
@MetcalfeTom is it possible, or which approach is better?
there are multiple clients and different stories and model for different client ID
there will be one rasa server running and based on client id, rasa server will load respective model and configuration and will answer accordingly
there will be different RAsa server running for every client, there will be one common node-server that will check the client id and call to respective server, get the response and return to the caller client.