-
Notifications
You must be signed in to change notification settings - Fork 83
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
Fix scann range search #315
Fix scann range search #315
Conversation
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: chasingegg The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
@chasingegg 🔍 Important: PR Classification Needed! For efficient project management and a seamless review process, it's essential to classify your PR correctly. Here's how:
For any PR outside the kind/improvement category, ensure you link to the associated issue using the format: “issue: #”. Thanks for your efforts and contribution to the community!. |
/kind bug |
6eaef11
to
086f892
Compare
/run-e2e |
1 similar comment
/run-e2e |
086f892
to
48912ff
Compare
Signed-off-by: chasingegg <[email protected]>
48912ff
to
9c17716
Compare
/run-e2e |
/lgtm |
issue #171
Faiss is highly optimized for batch searching, and different queries will search the same ivf bucket by gathering different queries' nprobe list which could reorder the npobe sequence, this could cause bug since range search goes as a 'early termination' manner, it will go through all ivf buckets and early terminate when no results found in one bucket, we have to search buckets by its sorted distance to query. Also, knowhere will split nq to single query, no need to gather queries' nprobe list.
before this pr
range search recall for IVF_FLAT with same param:
after this pr