Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Switch to openai.ChatCompletion.create #4

Open
hophanms opened this issue Apr 8, 2023 · 1 comment
Open

Switch to openai.ChatCompletion.create #4

hophanms opened this issue Apr 8, 2023 · 1 comment

Comments

@hophanms
Copy link

hophanms commented Apr 8, 2023

Now with gpt-4-32k, would it make sense to switch to openai.ChatCompletion.create instead of openai.Completion.create API?

I know there is dependency on chatgpt-api but that library doesn't help on supporting multi-sessions in Teams chat anyways (e.g. I chat with the bot in Team channel vs. direct chat should be 2 separate prompt histories)

Thought?
@freistli
Copy link
Owner

If the model is gpt-4, we should use Chat Completion. Currently rootbot uses Completion for GPT3.5-turbo model and supports multiple sessions in Teams.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@freistli @hophanms