Caleb M. Keller

you can communicate directly with Rasa by exposing it's port in docker, then communicating to localhost:5000, you'd have to get the model name by querying the agent.

There are some examples here for querying the Rasa API directly: https://github.com/samtecspg/rasa_nlu/blob/master/docs/http.rst

Can you provide information on the version of Articulate you're running, the command you're using to execute these tests?

@mordebip please see above.

you still haven't said what you're using to make the stress test calls, how many requests you consider to be a stress test, etc.

@alshell7 do Rasa and spaCy support arabic? That setting really only applies to spaCy and duckling. and If you're using the default pipelines it only has an impact if you're...

We are using version 0.14.4 of Rasa, that is the last version where they supported multiple models, which Articulate requires for now. the DIET classifier isn't an option here, as...

we do have the tensorflow pipeline, which to use a different language with that nothing is required, just type your sayings in the language you want. The drop down only...

This shows up in several places and looks not so hot. 

Not currently supported. There is probably a way to get there if you accept the answer in the form of numbers/letters. Articulate could recognize an answer like `A and C`...