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

Adjust how text is split depending on input type #1238

Merged
merged 1 commit into from
Apr 30, 2024

Conversation

timothycarambat
Copy link
Member

Pull Request Type

  • ✨ feat
  • πŸ› fix
  • ♻️ refactor
  • πŸ’„ style
  • πŸ”¨ chore
  • πŸ“ docs

Relevant Issues

resolves #1230

What is in this change?

Fixes issue where prompt would be split erroneously by the embedder during vector search resulting in worse semantic similarity.

Additional Information

Important

We need to also ensure the prompt given (or chunks of prompts) are not longer than the embedder model's max length or prompt search will crash

Developer Validations

  • I ran yarn lint from the root of the repo & committed changes
  • Relevant documentation has been updated
  • I have tested my code functionality
  • Docker build succeeds locally

@timothycarambat timothycarambat merged commit bf435b2 into master Apr 30, 2024
@timothycarambat timothycarambat deleted the 1230-text-input-embed-chunking-bug branch April 30, 2024 17:11
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.

[BUG]: User Query embeddings are being chunked per character when using LM Studio embedding models.
1 participant