-
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
The final candidate of the version that uses Faiss 1.7.4 #181
The final candidate of the version that uses Faiss 1.7.4 #181
Conversation
@alexanderguzhva 🔍 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!. |
/lgtm Thanks Alex! |
/approve Plz resolve the conflicts and link an issue with this PR. Thanks~ |
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: alexanderguzhva, liliu-z 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 |
Signed-off-by: Alexandr Guzhva <[email protected]>
c535a73
to
38c4a17
Compare
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.
/lgtm
Finalized version of #90
Based on Faiss 1.7.4 (based on commit c8d6f7bb2b09b8928570222131353f75acb4007b from Sep 6 2023, but with all the most recent merged commits).
Issue #186
The following changes were made to Knowhere besides refactoring:
BitsetView
filtering is replaced withfaiss::IDSelector
filtering.search()
/range_search()
are used withfaiss::SearchParameters
objects as a function parameter.faiss::elkan_L2_sse()
call is used by default as before, but IVF-indices in Knowhere (ivf.cc
) introduce a new flag “use_elkan” (false by default), which allows to significantly speed up the training/kind enhancement