Tiered HNSW - batch iterator [MOD-4323] #350
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Codecov Report
Additional details and impacted files@@ Coverage Diff @@
## feature_HNSW_tiered_index #350 +/- ##
============================================================
Coverage ? 96.77%
============================================================
Files ? 66
Lines ? 4527
Branches ? 0
============================================================
Hits ? 4381
Misses ? 146
Partials ? 0 Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. ☔ View full report in Codecov by Sentry. |
GuyAv46
changed the title
GuyAv46
force-pushed
the
guyav-tiered_hnsw_batch_iterator
branch
from
10e3342 to
fe17545
Compare
alonre24
reviewed
Apr 18, 2023
alonre24
approved these changes
Apr 20, 2023
GuyAv46
force-pushed
the
guyav-tiered_hnsw_batch_iterator
branch
from
d403961 to
264212c
Compare
DvirDukhan
reviewed
Apr 23, 2023
DvirDukhan
approved these changes
Apr 24, 2023
meiravgri
pushed a commit
that referenced
this pull request
May 8, 2023
* small modification to bf batch iterator * remove promise of perfect score in HNSW multi batch * implement batch iterator for tiered and some needed helpers * fix for merge results * make the iterator a nested class, fix and modify logic * added first unit test * some fixes and more tests * another test * first overlapping vector tests * fix a bug on reallocation * added an edge cases test * added comments * added `BY_SCORE_THEN_ID` order and sorter * make BF batch iterator use it in select-base search * modification to the BI to handle resize while alive, and use BY_SCORE_THEN_ID * added dynamic parallel test * move iterator from generic vec_sim_tiered to hnsw_tiered * leak fixes * fix clang build * minor test refactor * review fixes * decrease index size * move some array logic to arr_cpp.h * after rebase fixes * review fixes
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Describe the changes in the pull request
Implementation of the batch-iterator of the tiered HNSW.
This PR also includes the new
BY_SCORE_THEN_IDorder. in most cases, we already return the results this way (the standard priority queue and our updatable heap guarantee it). Still, in the BF batch iterator, it may not be the case (depending on the heuristic we choose).This may still be redundant, and we can consider making the
BY_SCOREorder implicitly handle ties by comparing the labels.Main objects this PR modified
BY_SCORE_THEN_IDorderMark if applicable