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.

Sign up for GitHub

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

Jump to bottom

feat: add semantic chunking to eval script; add wrapper for minilm #11

Merged
merged 4 commits into from
Sep 23, 2024
Merged

feat: add semantic chunking to eval script; add wrapper for minilm #11

merged 4 commits into from
Sep 23, 2024

Conversation

guenthermi
Copy link
Member

@guenthermi guenthermi commented Sep 23, 2024 •
edited
Loading

  • Adds the embedding model arguments to make it possible to execute semantic chunking
  • Adds SentenceTransformers wrapper to execute MiniLM
  • The current semantic chunking implementation omits the punctuation signs in the chunking. This PR changes it to include them
  • Makes the semantic chunking test more comprehensive

violenil
violenil reviewed Sep 23, 2024
View reviewed changes
Copy link
Member

@violenil violenil left a comment

Choose a reason for hiding this comment

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

Looks good! Maybe we can add a test for semantic chunking with a different embedding model as well?

violenil
violenil approved these changes Sep 23, 2024
View reviewed changes
Copy link
Member

@violenil violenil left a comment

Choose a reason for hiding this comment

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

🚀

@guenthermi guenthermi merged commit 70f81cb into main Sep 23, 2024
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@violenil violenil violenil approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@guenthermi @violenil