Add index to embeddings
What does this MR do and why?
As per https://gitlab.com/gitlab-org/gitlab/-/issues/410581+, we are adding an index to the embeddings.
We changed the distance function to use cosine similarity (cosine
) per OpenAI docs.
We refactored the neighbor_for
scope, and got rid of select
query, since the nearest_neighbors
is already returning the nearest and not all the neighbors.
Screenshots or screen recordings
Screenshots are required for UI changes, and strongly recommended for all other merge requests.
Before | After |
---|---|
How to set up and validate locally
Numbered steps to set up and validate the change are strongly suggested.
MR acceptance checklist
This checklist encourages us to confirm any changes have been analyzed to reduce risks in quality, performance, reliability, security, and maintainability.
-
I have evaluated the MR acceptance checklist for this MR.
Edited by Bojan Marjanovic