Steaming in Assistant API

Hey!

Does anyone know when output streaming will be available for the Assistant API - mentioned here Assistant API Limitations - will be implemented?

Assistant API is great and solves lots of different problems, but w/o streaming it’s kind of unusable production-wise (especially with RAG + function calls).

I know this topic was mentioned couple of times here, but no response. Maybe there as some OpenAI people here reading :slight_smile:
I’m more than happy to help with it if needed :slight_smile:

1 Like

This is the main thread on the subject: Any updates on Assistant API Streaming? - #17 by Dojima

I would stick to discussion there as it can help sustain the thread as a “top” suggested feature (though I’m sure they are already aware it’s a big request).

At the moment, no word has been received but I’m hopeful they are “actively working to add” streaming as their documentation suggests.