Open
Conversation
- reorganize settings and add options for new models - make sure the settings menu elements are understandable and do what they say - make sure the setting parameters are used correctly
Since gpt-4.1-nano is so cheap, we generate Chat titles automatically.
Aborting needs to be instant to save costs (especially with expensive models)
also fixes Chat Title Generation request setup
Owner
|
It looks good, only the |
Author
|
Right, didn't consider this - the model selection for automatic title generation (or whether to do it at all) therefore should be a preference in global settings somewhere. I'm also not yet super happy with the automatic chat title generation since the gpt-4.1-nano is super cheap but sometimes doesnt get the prompt/what it's supposed to do. I'll work with it a bit more and try to figure it out but if someone else has a great idea that would be very welcome, too :) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I added settings for the new OpenAI-Models and fixed a few annoying behaviours in the settings menu (especially regarding creation of new profiles).
I also removed unnecessary/non-functional elements from the settings, hid advanced settings and reordered them so the user can quickly adjust the important settings.
Furthermore the UI contains now more information and the "Suggest a chat name"-function uses the latest cheap model (now gpt-4.1-nano)