[GitHub] [kyuubi] bowenliang123 commented on pull request #4558: [CHAT] Make ChatGPT model ID configurable

["bowenliang123 (via GitHub)" <gi...@apache.org>]

bowenliang123 commented on PR #4558:
URL: https://github.com/apache/kyuubi/pull/4558#issuecomment-1475254218

   According to OpenAI's API reference(https://platform.openai.com/docs/api-reference/completions/create), many detailed settings of chat completion request, other than model id, like `max_tokens`, `topP`,  can be configured.
   Do you guys think we should expose them one by one in separate config in Kyuubi , or just expose a config in JSON style, that consumes dynamic settings for ChatGPT? @pan3793 @cxzl25 


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: notifications-unsubscribe@kyuubi.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@kyuubi.apache.org
For additional commands, e-mail: notifications-help@kyuubi.apache.org