RASA NLU Use Multiple models at the same time

Rasa Open Source
1

I have a use case only for NLU part, where I have to use several models at the same time. So, I’m using the below code. But the response time is very high around 4-6 sec. Is there any way where I can use several models at the same time and get the response very quickly (only NLU). I took a clone of git repo version 1.10.x

from rasa.nlu.model import Interpreter

def run_nlu(modelpath,predText):

interpreter = Interpreter.load(modelpath);print(interpreter.parse(predText))
2

Why do you have multiple models? It might be faster to include them all in one pipeline. But I guess that also depends on what kind of models you have. Can you share some more details?

3

Hi, In our use case, Let’s say we have each model for each client. How can we run multiple models at the same time?

What exactly is " include them all in one pipeline"?

4

So, you have one bot that should handle multiple tasks? If so, you can maybe have a look at Meta bots: why they're probably not the solution to your problems | Akela Drissner - YouTube.