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

WIP: Feature Semantic Search #528

Merged
merged 14 commits into from
Nov 7, 2024
Merged

WIP: Feature Semantic Search #528

merged 14 commits into from
Nov 7, 2024

Conversation

travolin
Copy link
Collaborator

@travolin travolin commented Nov 5, 2024

  • Add vector embedding table to store document embeddings
  • Add model to calculate document embeddings
  • Add search query embedding distance check and update document boosts accordingly
  • Move embeddings into their own queue
  • Merge with new GUI updates

travolin added 14 commits November 4, 2024 17:21
- Add sqlite plugin and table for embeddings
- Add embedding model access via candle
- Add embedding model to state
- Add embeddings when documents are added and updated (and delete when deleted)
- Embed query strings and check distance against vector embedding store.
- Use query embedding distance calculate document boosts
- whisper rs conflicts with candle library
- will be transitioning to use candle instead of whisper
@travolin travolin marked this pull request as ready for review November 7, 2024 01:23
@travolin travolin merged commit ea787d1 into main Nov 7, 2024
2 checks passed
@travolin travolin deleted the feature/semantic_search branch November 7, 2024 01:27
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.

1 participant