admin/milvus
1
0
Fork 0
mirror of https://gitee.com/milvus-io/milvus.git synced 2026-02-02 01:06:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: [2.6] BM25 with boost return result not ordered (#44759)

Browse Source 
relate: https://github.com/milvus-io/milvus/issues/44758
pr: https://github.com/milvus-io/milvus/pull/44744
Wrong code which should be (result.seg_offsets_[i] >= 0 &&
result.seg_offsets_[j] < 0), but was (result.seg_offsets_[j] >= 0 &&
result.seg_offsets_[j] < 0) now.
But because all placeholder which was offset -1, will fill with worst
distance value.
For IP, L2 or COSIN, it will be +inf or -inf. So sort distance was
enough.
But when use BM25, it will be NAN. Will case sort out of ordered.

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
This commit is contained in:
aoiasd 2025-10-13 11:57:57 +08:00 committed by GitHub
parent 781df9d0b3
commit 6ff30e8f9e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
internal/core/src/exec/operator/Utils.h
View File

@ -118,15 +118,17 @@ sort_search_result(milvus::SearchResult& result, bool large_is_better) {
if (large_is_better) {
std::sort(idx.begin(), idx.end(), [&](size_t i, size_t j) {
return result.distances_[i] > result.distances_[j] ||
(result.seg_offsets_[j] >= 0 &&
result.seg_offsets_[j] < 0);
if (result.seg_offsets_[j] < 0 || result.seg_offsets_[i] < 0) {
return result.seg_offsets_[i] >= 0;
}
return result.distances_[i] > result.distances_[j];
});
} else {
std::sort(idx.begin(), idx.end(), [&](size_t i, size_t j) {
return result.distances_[i] < result.distances_[j] ||
(result.seg_offsets_[j] >= 0 &&
result.seg_offsets_[j] < 0);
if (result.seg_offsets_[j] < 0 || result.seg_offsets_[i] < 0) {
return result.seg_offsets_[i] >= 0;
}
return result.distances_[i] < result.distances_[j];
});
}
for (auto i : idx) {