-
Notifications
You must be signed in to change notification settings - Fork 265
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
feat: detect the drift and retrain the index if hit threshold #3489
base: main
Are you sure you want to change the base?
Conversation
Signed-off-by: BubbleCal <bubble-cal@outlook.com>
@@ -45,9 +49,6 @@ pub struct IvfBuildParams { | |||
|
|||
pub shuffle_partition_concurrency: usize, | |||
|
|||
/// Use residual vectors to build sub-vector. | |||
pub use_residual: bool, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this is never used, so remove it
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #3489 +/- ##
==========================================
+ Coverage 78.66% 78.84% +0.18%
==========================================
Files 254 254
Lines 95025 95690 +665
Branches 95025 95690 +665
==========================================
+ Hits 74751 75447 +696
+ Misses 17250 17124 -126
- Partials 3024 3119 +95
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
…loss Signed-off-by: BubbleCal <bubble-cal@outlook.com>
Signed-off-by: BubbleCal <bubble-cal@outlook.com>
Signed-off-by: BubbleCal <bubble-cal@outlook.com>
Signed-off-by: BubbleCal <bubble-cal@outlook.com>
…loss Signed-off-by: BubbleCal <bubble-cal@outlook.com>
Today we provide 2 ways for users to maintain the vector index:
create_index
: create a new index on the entire datasetoptimize
: incrementally index on the unindexed rowsit's recommended that the users should call optimize for shorter indexing time, but the index might be not accurate as inserting more rows.
this PR introduces:
avg_loss
>original_avg_loss * THRESHOLD
after this, the users don't need to call
create_index
to create a new index to replace existing one,optimize
would detect the avg loss, and retrain the index in more efficient way