Skip to content

More fixes #29

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

Open
wants to merge 40 commits into
base: main
Choose a base branch
from
Open

More fixes #29

wants to merge 40 commits into from

Conversation

mscottx88
Copy link
Contributor

Closes #28

Copy link
Contributor

@ryan-roemer ryan-roemer left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is looking pretty good! Just minor suggestions mostly.

Big thing is the binary search vs. linear progression for character splitting. Maybe I'm missing something? Let's chat if there's an optimization and whether to do it here or in follow on work

@mscottx88
Copy link
Contributor Author

mscottx88 commented Jul 16, 2025 via email

@mscottx88
Copy link
Contributor Author

I further analyzed the binary search when it comes to calculating where the overlap should begin. The performance is pretty dramatic.

image

@mscottx88 mscottx88 requested a review from ryan-roemer July 16, 2025 17:32
@simoneb
Copy link
Member

simoneb commented Jul 21, 2025

As discussed with @mscottx88, we're still waiting for a round of reviews on this and a bit of discussion.

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

Successfully merging this pull request may close these issues.

Finalize llm-chunk
3 participants