-
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
sparse: disable refinement by default #1033
Conversation
@sparknack 🔍 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!. |
a5d3373
to
74baa01
Compare
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #1033 +/- ##
=========================================
+ Coverage 0 73.15% +73.15%
=========================================
Files 0 82 +82
Lines 0 7479 +7479
=========================================
+ Hits 0 5471 +5471
- Misses 0 2008 +2008 |
lgtm, but should it affect existing users? |
Yes. For the current code in main branch, if refinement is used, it will lead to a significant degradation in performance, thus affecting the usability of all range of the drop_ratio_search. Although turning off refinement by default will cause a certain decline in the recall rate with the same drop_ratio_search, it can still ensure that it is basically usable. Users still can use small drop_ratio_search like 0.1. |
KNOWHERE_CONFIG_DECLARE_FIELD(refine_factor) | ||
.description("refine factor") | ||
.set_default(10) | ||
.set_default(1) | ||
.set_range(1, 10, true, true) | ||
.for_search() | ||
.for_range_search(); |
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.
remove for_range_search
KNOWHERE_CONFIG_DECLARE_FIELD(refine_factor) | ||
.description("refine factor") | ||
.set_default(10) | ||
.set_default(1) | ||
.set_range(1, 10, true, true) |
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.
no need to set a upper limit
issue: #1035 |
74baa01
to
2b9ee37
Compare
Because of the removal of forward index, the current refine searching is slower than before. To prevent performance degradation when using a non-zero value of drop_ratio_search, disable refinement by default. Signed-off-by: Shawn Wang <[email protected]>
2b9ee37
to
db09d51
Compare
/lgtm |
/approve |
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: sparknack, zhengbuqian 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 |
/kind improvement |
Because of the removal of forward index, the current refine searching is
slower than before. To prevent performance degradation when using a
non-zero value of drop_ratio_search, disable refinement by default.