liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-11 23:26:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

Started half indexing

Browse Source
This commit is contained in:
Andrew Kane
2023-12-03 15:12:50 -08:00
parent 422667f6c6
commit 47852e8d15
4 changed files with 107 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
sql/vector--0.5.1--0.6.0.sql
View File

@@ -75,3 +75,8 @@ CREATE OPERATOR <=> (
LEFTARG = half[], RIGHTARG = half[], PROCEDURE = cosine_distance, LEFTARG = half[], RIGHTARG = half[], PROCEDURE = cosine_distance,
COMMUTATOR = '<=>' COMMUTATOR = '<=>'
); );
CREATE OPERATOR CLASS half_l2_ops
FOR TYPE half[] USING hnsw AS
OPERATOR 1 <-> (half[], half[]) FOR ORDER BY float_ops,
FUNCTION 1 half_l2_squared_distance(half[], half[]);

7
sql/vector.sql
View File

@@ -377,3 +377,10 @@ CREATE OPERATOR <=> (
LEFTARG = half[], RIGHTARG = half[], PROCEDURE = cosine_distance, LEFTARG = half[], RIGHTARG = half[], PROCEDURE = cosine_distance,
COMMUTATOR = '<=>' COMMUTATOR = '<=>'
); );
-- half opclasses
CREATE OPERATOR CLASS half_l2_ops
FOR TYPE half[] USING hnsw AS
OPERATOR 1 <-> (half[], half[]) FOR ORDER BY float_ops,
FUNCTION 1 half_l2_squared_distance(half[], half[]);

4
src/hnswbuild.c
View File

@@ -462,8 +462,8 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod; buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
/* Require column to have dimensions to be indexed */ /* Require column to have dimensions to be indexed */
if (buildstate->dimensions < 0) // if (buildstate->dimensions < 0)
elog(ERROR, "column does not have dimensions"); // elog(ERROR, "column does not have dimensions");
if (buildstate->dimensions > HNSW_MAX_DIM) if (buildstate->dimensions > HNSW_MAX_DIM)
elog(ERROR, "column cannot have more than %d dimensions for hnsw index", HNSW_MAX_DIM); elog(ERROR, "column cannot have more than %d dimensions for hnsw index", HNSW_MAX_DIM);

93
test/t/019_hnsw_half.pl Normal file
View File

@@ -0,0 +1,93 @@
use strict;
use warnings;
use PostgresNode;
use TestLib;
use Test::More;
my $node;
my @queries = ();
my @expected;
my $limit = 20;
sub test_recall
{
my ($min, $operator) = @_;
my $correct = 0;
my $total = 0;
my $explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v $operator '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Scan/);
for my $i (0 .. $#queries)
{
my $actual = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit;
));
my @actual_ids = split("\n", $actual);
my %actual_set = map { $_ => 1 } @actual_ids;
my @expected_ids = split("\n", $expected[$i]);
foreach (@expected_ids)
{
if (exists($actual_set{$_}))
{
$correct++;
}
$total++;
}
}
cmp_ok($correct / $total, ">=", $min, $operator);
}
# Initialize node
$node = get_new_node('node');
$node->init;
$node->start;
# Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v half[3]);");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()]::numeric[]::half[] FROM generate_series(1, 10000) i;"
);
# Generate queries
for (1 .. 20)
{
my $r1 = rand();
my $r2 = rand();
my $r3 = rand();
push(@queries, "{$r1,$r2,$r3}");
}
# Check each index type
my @operators = ("<->");
my @opclasses = ("half_l2_ops");
for my $i (0 .. $#operators)
{
my $operator = $operators[$i];
my $opclass = $opclasses[$i];
# Get exact results
@expected = ();
foreach (@queries)
{
my $res = $node->safe_psql("postgres", "SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;");
push(@expected, $res);
}
# Add index
$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v $opclass);");
my $min = $operator eq "<#>" ? 0.80 : 0.99;
test_recall($min, $operator);
}
done_testing();