Skip to content

Instantly share code, notes, and snippets.

@wolfram77

wolfram77/notes-introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency.md

Last active December 23, 2024 04:31
Show Gist options
  • Save wolfram77/829b255770757357f024e6c35637496f to your computer and use it in GitHub Desktop.
Save wolfram77/829b255770757357f024e6c35637496f to your computer and use it in GitHub Desktop.
Download ZIP
Introducing DRIFT Search: Combining global and local search methods to improve quality and efficiency : NOTES
Raw
notes-introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency.md

It seems DRIFT search uses vector similarity search with top-k communities in the top-most hierarchy, and then drills down to the lower hierarchy levels. They seem to use follow-up questions for this purpose. The answers are ranked based on relavance to the query. Need to check the paper for more details.

Display the source blob
Display the rendered blob
Raw
notes-introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency.pdf
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment