Skip to content

Improve PQ training error message #706

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

Open
ashkrisk wants to merge 1 commit into
base: main
Choose a base branch
from
+16 −0
Open

Improve PQ training error message #706

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
3 changes: 3 additions & 0 deletions jvector-base/src/main/java/io/github/jbellis/jvector/quantization/ProductQuantization.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,9 @@ public static ProductQuantization compute(RandomAccessVectorValues ravv,
{
checkClusterCount(clusterCount);

if (ravv.size() < clusterCount) {
throw new IllegalArgumentException("Cannot train PQ with %d clusters on %d points, supply more training vectors or lower cluster count.");
}
var subvectorSizesAndOffsets = getSubvectorSizesAndOffsets(ravv.dimension(), M);
var vectors = extractTrainingVectors(ravv, parallelExecutor);

Expand Down
13 changes: 13 additions & 0 deletions ...r-tests/src/test/java/io/github/jbellis/jvector/quantization/TestProductQuantization.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -433,4 +433,17 @@ public void testPQCodebookSums() {
}
}
}

@Test
public void testErrorOnInsufficientVectors() {
int dim = 384;
var pqM = 48;

var ravv100 = new ListRandomAccessVectorValues(createRandomVectors(100, dim), dim);
var ravv200 = new ListRandomAccessVectorValues(createRandomVectors(200, dim), dim);
ProductQuantization.compute(ravv100, pqM, 50, false); // should not throw
assertThrows(IllegalArgumentException.class, () -> ProductQuantization.compute(ravv100, pqM, 150, false));
ProductQuantization.compute(ravv200, pqM, 150, false); // should not throw
assertThrows(IllegalArgumentException.class, () -> ProductQuantization.compute(ravv200, pqM, 256, false));
}
}
Loading