liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-06-06 05:51:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

Skip duplicate center check for bit [skip ci]

Browse Source
This commit is contained in:
Andrew Kane
2024-04-16 17:20:48 -07:00
parent 04af15c9d6
commit 4e2b76e627
3 changed files with 20 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
src/ivfkmeans.c
View File

@@ -707,21 +707,22 @@ CheckCenters(Relation index, VectorArray centers, IvfflatType type)
elog(ERROR, "Unsupported type");
}
/* Ensure no duplicate centers */
/* Fine to sort in-place */
if (type == IVFFLAT_TYPE_VECTOR)
qsort(centers->items, centers->length, centers->itemsize, CompareVectors);
else if (type == IVFFLAT_TYPE_HALFVEC)
qsort(centers->items, centers->length, centers->itemsize, CompareHalfVectors);
else if (type == IVFFLAT_TYPE_BIT)
qsort(centers->items, centers->length, centers->itemsize, CompareBitVectors);
else
elog(ERROR, "Unsupported type");
for (int i = 1; i < centers->length; i++)
if (type != IVFFLAT_TYPE_BIT)
{
if (datumIsEqual(PointerGetDatum(VectorArrayGet(centers, i)), PointerGetDatum(VectorArrayGet(centers, i - 1)), false, -1))
elog(ERROR, "Duplicate centers detected. Please report a bug.");
/* Ensure no duplicate centers */
/* Fine to sort in-place */
if (type == IVFFLAT_TYPE_VECTOR)
qsort(centers->items, centers->length, centers->itemsize, CompareVectors);
else if (type == IVFFLAT_TYPE_HALFVEC)
qsort(centers->items, centers->length, centers->itemsize, CompareHalfVectors);
else
elog(ERROR, "Unsupported type");
for (int i = 1; i < centers->length; i++)
{
if (datumIsEqual(PointerGetDatum(VectorArrayGet(centers, i)), PointerGetDatum(VectorArrayGet(centers, i - 1)), false, -1))
elog(ERROR, "Duplicate centers detected. Please report a bug.");
}
}
/* Ensure no zero vectors for cosine distance */

4
test/expected/ivfflat_bit_hamming.out
View File

@@ -29,4 +29,8 @@ DETAIL: This will cause low recall.
HINT: Drop the index until the table has more data.
CREATE INDEX ON t USING ivfflat ((val::bit(64001)) bit_hamming_ops) WITH (lists = 1);
ERROR: column cannot have more than 64000 dimensions for ivfflat index
CREATE INDEX ON t USING ivfflat ((val::bit(2)) bit_hamming_ops) WITH (lists = 5);
NOTICE: ivfflat index created with little data
DETAIL: This will cause low recall.
HINT: Drop the index until the table has more data.
DROP TABLE t;

1
test/sql/ivfflat_bit_hamming.sql
View File

@@ -16,4 +16,5 @@ CREATE TABLE t (val varbit(3));
CREATE INDEX ON t USING ivfflat (val bit_hamming_ops) WITH (lists = 1);
CREATE INDEX ON t USING ivfflat ((val::bit(3)) bit_hamming_ops) WITH (lists = 1);
CREATE INDEX ON t USING ivfflat ((val::bit(64001)) bit_hamming_ops) WITH (lists = 1);
CREATE INDEX ON t USING ivfflat ((val::bit(2)) bit_hamming_ops) WITH (lists = 5);
DROP TABLE t;