liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-15 00:56:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added support for uuid

Browse Source
This commit is contained in:
Andrew Kane
2024-02-14 16:16:26 -08:00
parent 6fccacc66a
commit f076ec2954
3 changed files with 44 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
sql/vector--0.6.1--0.7.0.sql
View File

@@ -24,3 +24,11 @@ CREATE OPERATOR CLASS vector_text_ops
OPERATOR 4 = , OPERATOR 4 = ,
OPERATOR 5 >= , OPERATOR 5 >= ,
OPERATOR 6 > ; OPERATOR 6 > ;
CREATE OPERATOR CLASS vector_uuid_ops
DEFAULT FOR TYPE uuid USING hnsw AS
OPERATOR 2 < ,
OPERATOR 3 <= ,
OPERATOR 4 = ,
OPERATOR 5 >= ,
OPERATOR 6 > ;

8
sql/vector.sql
View File

@@ -316,3 +316,11 @@ CREATE OPERATOR CLASS vector_text_ops
OPERATOR 4 = , OPERATOR 4 = ,
OPERATOR 5 >= , OPERATOR 5 >= ,
OPERATOR 6 > ; OPERATOR 6 > ;
CREATE OPERATOR CLASS vector_uuid_ops
DEFAULT FOR TYPE uuid USING hnsw AS
OPERATOR 2 < ,
OPERATOR 3 <= ,
OPERATOR 4 = ,
OPERATOR 5 >= ,
OPERATOR 6 > ;

43
test/t/020_hnsw_filtering.pl
View File

@@ -12,19 +12,32 @@ my $limit = 20;
my $dim = 3; my $dim = 3;
my $array_sql = join(",", ('random()') x $dim); my $array_sql = join(",", ('random()') x $dim);
my $nc = 50; my $nc = 50;
my @types = ("int4", "int8", "text", "varchar"); my @types = ("int4", "int8", "text", "uuid", "varchar");
my $type = $types[rand(@types)]; my $type = $types[rand(@types)];
sub cast_c
{
my ($c) = @_;
if ($type eq "uuid")
{
return "('00000000-0000-0000-0000-0000000000' || LPAD(($c)::text, 2, '0'))::uuid";
}
else
{
return "($c)::$type";
}
}
sub test_recall sub test_recall
{ {
my ($min, $operator) = @_; my ($min, $operator) = @_;
my $correct = 0; my $correct = 0;
my $total = 0; my $total = 0;
my $cast = $type eq "int8" ? "::int8" : "";
my $explain = $node->safe_psql("postgres", qq( my $explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off; SET enable_seqscan = off;
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = '$cs[0]'$cast ORDER BY v $operator '$queries[0]' LIMIT $limit; EXPLAIN ANALYZE SELECT i FROM tst WHERE c = @{[cast_c($cs[0])]} ORDER BY v $operator '$queries[0]' LIMIT $limit;
)); ));
like($explain, qr/Index Cond/); like($explain, qr/Index Cond/);
@@ -32,7 +45,7 @@ sub test_recall
{ {
my $actual = $node->safe_psql("postgres", qq( my $actual = $node->safe_psql("postgres", qq(
SET enable_seqscan = off; SET enable_seqscan = off;
SELECT i FROM tst WHERE c = '$cs[$i]'$cast ORDER BY v $operator '$queries[$i]' LIMIT $limit; SELECT i FROM tst WHERE c = @{[cast_c($cs[$i])]} ORDER BY v $operator '$queries[$i]' LIMIT $limit;
)); ));
my @actual_ids = split("\n", $actual); my @actual_ids = split("\n", $actual);
my %actual_set = map { $_ => 1 } @actual_ids; my %actual_set = map { $_ => 1 } @actual_ids;
@@ -62,13 +75,13 @@ $node->start;
# Create table # Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;"); $node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c $type, c2 $type);"); $node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c $type, c2 $type);");
$node->safe_psql("postgres", $node->safe_psql("postgres", qq(
"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc, i % $nc FROM generate_series(1, 10000) i;" INSERT INTO tst SELECT i, ARRAY[$array_sql], @{[cast_c("i % $nc")]}, @{[cast_c("i % $nc")]} FROM generate_series(1, 10000) i;
); ));
$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, c, c2);"); $node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, c, c2);");
$node->safe_psql("postgres", $node->safe_psql("postgres", qq(
"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc, i % $nc FROM generate_series(1, 10000) i;" INSERT INTO tst SELECT i, ARRAY[$array_sql], @{[cast_c("i % $nc")]}, @{[cast_c("i % $nc")]} FROM generate_series(1, 10000) i;
); ));
$node->safe_psql("postgres", "ANALYZE tst;"); $node->safe_psql("postgres", "ANALYZE tst;");
# Generate queries # Generate queries
@@ -89,7 +102,7 @@ for my $i (0 .. $#queries)
{ {
my $res = $node->safe_psql("postgres", qq( my $res = $node->safe_psql("postgres", qq(
SET enable_indexscan = off; SET enable_indexscan = off;
SELECT i FROM tst WHERE c = '$cs[$i]' ORDER BY v <-> '$queries[$i]' LIMIT $limit; SELECT i FROM tst WHERE c = @{[cast_c($cs[$i])]} ORDER BY v <-> '$queries[$i]' LIMIT $limit;
)); ));
push(@expected, $res); push(@expected, $res);
} }
@@ -105,24 +118,24 @@ like($explain, qr/Index Scan/);
# Test range # Test range
$explain = $node->safe_psql("postgres", qq( $explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c >= '1' AND c <= '3' ORDER BY v <-> '$queries[0]' LIMIT $limit; EXPLAIN ANALYZE SELECT i FROM tst WHERE c >= @{[cast_c(1)]} AND c <= @{[cast_c(3)]} ORDER BY v <-> '$queries[0]' LIMIT $limit;
)); ));
like($explain, qr/Index Cond: \(\(\S+ >= \S+\) AND \(\S+ <= \S+\)\)/); like($explain, qr/Index Cond: \(\(\S+ >= \S+\) AND \(\S+ <= \S+\)\)/);
# Test multiple conditions # Test multiple conditions
$explain = $node->safe_psql("postgres", qq( $explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = '$cs[0]' AND c2 = '$cs[0]' ORDER BY v <-> '$queries[0]' LIMIT $limit; EXPLAIN ANALYZE SELECT i FROM tst WHERE c = @{[cast_c($cs[0])]} AND c2 = @{[cast_c($cs[0])]} ORDER BY v <-> '$queries[0]' LIMIT $limit;
)); ));
like($explain, qr/Index Cond: \(\(\S+ = \S+\) AND \(\S+ = \S+\)\)/); like($explain, qr/Index Cond: \(\(\S+ = \S+\) AND \(\S+ = \S+\)\)/);
# Test no order # Test no order
$explain = $node->safe_psql("postgres", qq( $explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = '$cs[0]' LIMIT $limit; EXPLAIN ANALYZE SELECT i FROM tst WHERE c = @{[cast_c($cs[0])]} LIMIT $limit;
)); ));
like($explain, qr/Seq Scan/); like($explain, qr/Seq Scan/);
# Test vacuum # Test vacuum
$node->safe_psql("postgres", "DELETE FROM tst WHERE c > '5';"); $node->safe_psql("postgres", "DELETE FROM tst WHERE c > @{[cast_c(5)]};");
$node->safe_psql("postgres", "VACUUM tst;"); $node->safe_psql("postgres", "VACUUM tst;");
# Test columns # Test columns