You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is your feature request related to a problem? Please describe.
I am not seeing a way to signal to the stream that I want to abort, for the cases of when a response is getting too long, or is wrong and I want to start over.
In the node package for the OpenAI API, they expose a controller object which allows you to abort the stream midway through.
Describe the solution you'd like
I would like that calling the chat method on a client instance would return a stream controller so that I can abort the stream if need be. Perhaps this is already possible with how you built it, but I did not have success attempting to use it. If this is already possible, would you please update the readme with instructions?
Is your feature request related to a problem? Please describe.
I am not seeing a way to signal to the stream that I want to abort, for the cases of when a response is getting too long, or is wrong and I want to start over.
In the node package for the OpenAI API, they expose a
controller
object which allows you to abort the stream midway through.Describe the solution you'd like
I would like that calling the
chat
method on a client instance would return a stream controller so that I can abort the stream if need be. Perhaps this is already possible with how you built it, but I did not have success attempting to use it. If this is already possible, would you please update the readme with instructions?Example usage:
Additional context
Node.js implementation:
Thank you for providing and maintaining this Gem 🙏
The text was updated successfully, but these errors were encountered: