liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-06 20:50:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

Include vectors with zero norm in indexes for cosine distance

Browse Source
This commit is contained in:
Andrew Kane
2023-11-18 13:40:22 -08:00
parent 5b12ae8225
commit 63982fef41
8 changed files with 14 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/hnsw.h
View File

@@ -316,7 +316,7 @@ typedef struct HnswVacuumState
int HnswGetM(Relation index);
int HnswGetEfConstruction(Relation index);
FmgrInfo *HnswOptionalProcInfo(Relation index, uint16 procnum);
bool HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
void HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
void HnswCommitBuffer(Buffer buf, GenericXLogState *state);
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
void HnswInitPage(Buffer buf, Page page);

5
src/hnswbuild.c
View File

@@ -307,10 +307,7 @@ InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState *
/* Normalize if needed */
if (buildstate->normprocinfo != NULL)
{
if (!HnswNormValue(buildstate->normprocinfo, collation, &value, buildstate->normvec))
return false;
}
HnswNormValue(buildstate->normprocinfo, collation, &value, buildstate->normvec);
/* Copy value to element so accessible outside of memory context */
oldCtx = MemoryContextSwitchTo(outerCtx);

5
src/hnswinsert.c
View File

@@ -500,10 +500,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
/* Normalize if needed */
normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
if (normprocinfo != NULL)
{
if (!HnswNormValue(normprocinfo, collation, &value, NULL))
return false;
}
HnswNormValue(normprocinfo, collation, &value, NULL);
/*
* Get a shared lock. This allows vacuum to ensure no in-flight inserts

6
src/hnswutils.c
View File

@@ -55,7 +55,7 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
* The caller needs to free the pointer stored in value
* if it's different than the original value
*/
bool
void
HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result)
{
double norm = DatumGetFloat8(FunctionCall1Coll(procinfo, collation, *value));
@@ -71,11 +71,7 @@ HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result)
result->x[i] = v->x[i] / norm;
*value = PointerGetDatum(result);
return true;
}
return false;
}
/*

5
src/ivfbuild.c
View File

@@ -177,10 +177,7 @@ AddTupleToSort(Relation index, ItemPointer tid, Datum *values, IvfflatBuildState
/* Normalize if needed */
if (buildstate->normprocinfo != NULL)
{
if (!IvfflatNormValue(buildstate->normprocinfo, buildstate->collation, &value, buildstate->normvec))
return;
}
IvfflatNormValue(buildstate->normprocinfo, buildstate->collation, &value, buildstate->normvec);
/* Find the list that minimizes the distance */
for (int i = 0; i < centers->length; i++)

5
src/ivfinsert.c
View File

@@ -83,10 +83,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
/* Normalize if needed */
normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_NORM_PROC);
if (normprocinfo != NULL)
{
if (!IvfflatNormValue(normprocinfo, index->rd_indcollation[0], &value, NULL))
return;
}
IvfflatNormValue(normprocinfo, index->rd_indcollation[0], &value, NULL);
/* Find the insert page - sets the page and list info */
FindInsertPage(index, values, &insertPage, &listInfo);

7
test/expected/hnsw_cosine.out
View File

@@ -9,18 +9,19 @@ SELECT * FROM t ORDER BY val <=> '[3,3,3]';
[1,1,1]
[1,2,3]
[1,2,4]
(3 rows)
[0,0,0]
(4 rows)
SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> '[0,0,0]') t2;
count
-------
3
4
(1 row)
SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2;
count
-------
3
4
(1 row)
DROP TABLE t;

7
test/expected/ivfflat_cosine.out
View File

@@ -9,18 +9,19 @@ SELECT * FROM t ORDER BY val <=> '[3,3,3]';
[1,1,1]
[1,2,3]
[1,2,4]
(3 rows)
[0,0,0]
(4 rows)
SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> '[0,0,0]') t2;
count
-------
3
4
(1 row)
SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2;
count
-------
3
4
(1 row)
DROP TABLE t;