-
Notifications
You must be signed in to change notification settings - Fork 607
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
Add local kmeans actor scan #8756
Conversation
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
aaf632b
to
ae2247d
Compare
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
e2e6649
to
7225fcc
Compare
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
⚪ ⚪
⚪
🟢
*please be aware that the difference is based on comparing your commit and the last completed build from the post-commit, check comparation |
⚪
🟢
*please be aware that the difference is based on comparing your commit and the last completed build from the post-commit, check comparation |
It run kmeans for datashard with embeddings.
This scan contains 3 phases:
Important note, that this code doesn't contains slow-path (that can store some intermediate results to LocalDB).
Because in general slow-path will be run only if this code fails and at the same time, datashards are small enough to don't think about this in first implementation of vector index (another words granularity of work that needed to be re-done in case datashard restart <= datashard size)