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.

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

[Feature Request] Add a marker that shows the part of the conversation that is being summarized #51

Open
kickahaota opened this issue May 26, 2023 · 1 comment

Comments

@kickahaota
Copy link

Once the conversation gets long enough to require summarization, it would be nice if there were a way to quickly tell what part of the start of the conversation is being summarized. For regular users, this could be a cue to mention important story elements every so often; for more sophisticated users, it could be a reminder to check the summary/memories/lore. A user can currently see this information by clicking the brain icon for the most recent AI response; but it could definitely be more elegant. A possibility: A "Summarization ends here" message displayed between the last summarized message and the first non-summarized one, displayed in the same way that the reminder message is displayed before the most recent the AI response.

@kickahaota
Copy link
Author

I've been looking at the code, and I see a clean way to implement the UI aspect of this. But the whole summary/lore/memory mechanism is still pretty much a black box to me.

If you're interested in implementing this feature, then perhaps you could add a placeholder function like this:

async function placeSummaryEndMarker(threadId, idxLastSummarizedMessage) {
    // todo
}

and call it when the summary is regenerated. Then I could give you some proposed code to place and move the marker in the UX.

If you're not interested, that's obviously more than fine too. 😀

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant