- Notifications
You must be signed in to change notification settings - Fork1k
feat: support for customizing “tool_choice” in OpenAI#785
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.
By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.
Already on GitHub?Sign in to your account
Uh oh!
There was an error while loading.Please reload this page.
Conversation
The ModelSettings class uses a TypedDict as its underlying type, providingflexibility to add options beyond the predefined attributes.Before generating chat completions, the code now checks if tool_choice is setin ModelSettings and applies it accordingly.Fixes:pydantic#224Signed-off-by: Sébastien Han <seb@redhat.com>
I think we'll want to customize this on |
@sydney-runkle Thanks for looking into this. Are you referring to exposing a setting like ModelSettings? I’m curious about how frequently users would need to adjust this flag. Thanks! |
Yes, we'll want to expose a setting and document it. Specifically, we'll probably want to add this to |
I no longer have the time to continue working on this, so I’ll be closing it. |
webcoderz commentedJan 31, 2025
thanks@leseb this seems to work.. |
webcoderz commentedJan 31, 2025
@sydney-runkle see:#825 i added tool_choice to ModelSettings as requested. |
Uh oh!
There was an error while loading.Please reload this page.
1016c92 feat: support for customizing “tool_choice” in OpenAI
commit1016c92
Author: Sébastien Hanseb@redhat.com
Date: Mon Jan 27 16:52:45 2025 +0100
Fixes:#224