Skip to content

Make hierarchical k-means over centroids cheaper #132316

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.

Sign up for GitHub

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

Merged
merged 1 commit into from
Aug 1, 2025
Merged

Make hierarchical k-means over centroids cheaper #132316

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions server/src/main/java/org/elasticsearch/index/codec/vectors/DefaultIVFVectorsWriter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -405,9 +405,9 @@ public int size() {
// this are small numbers so we run it wih all the centroids.
final KMeansResult kMeansResult = new HierarchicalKMeans(
fieldInfo.getVectorDimension(),
6,
floatVectorValues.size(),
floatVectorValues.size(),
HierarchicalKMeans.MAX_ITERATIONS_DEFAULT,
HierarchicalKMeans.SAMPLES_PER_CLUSTER_DEFAULT,
HierarchicalKMeans.MAXK,
-1 // disable SOAR assignments
).cluster(floatVectorValues, centroidsPerParentCluster);
final int[] centroidVectorCount = new int[kMeansResult.centroids().length];
Expand Down
8 changes: 4 additions & 4 deletions server/src/main/java/org/elasticsearch/index/codec/vectors/cluster/HierarchicalKMeans.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,10 +19,10 @@
*/
public class HierarchicalKMeans {

static final int MAXK = 128;
static final int MAX_ITERATIONS_DEFAULT = 6;
static final int SAMPLES_PER_CLUSTER_DEFAULT = 64;
static final float DEFAULT_SOAR_LAMBDA = 1.0f;
public static final int MAXK = 128;
public static final int MAX_ITERATIONS_DEFAULT = 6;
public static final int SAMPLES_PER_CLUSTER_DEFAULT = 64;
public static final float DEFAULT_SOAR_LAMBDA = 1.0f;

final int dimension;
final int maxIterations;
Expand Down