liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-11 07:06:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added filtering for text columns

Browse Source
This commit is contained in:
Andrew Kane
2024-02-13 13:14:13 -08:00
parent f712847781
commit dbc56491f4
3 changed files with 14 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
sql/vector--0.6.1--0.7.0.sql
View File

@@ -4,3 +4,7 @@
CREATE OPERATOR CLASS vector_integer_ops CREATE OPERATOR CLASS vector_integer_ops
DEFAULT FOR TYPE integer USING hnsw AS DEFAULT FOR TYPE integer USING hnsw AS
OPERATOR 2 = (integer, integer); OPERATOR 2 = (integer, integer);
CREATE OPERATOR CLASS vector_text_ops
DEFAULT FOR TYPE text USING hnsw AS
OPERATOR 2 = (text, text);

4
sql/vector.sql
View File

@@ -296,3 +296,7 @@ CREATE OPERATOR CLASS vector_cosine_ops
CREATE OPERATOR CLASS vector_integer_ops CREATE OPERATOR CLASS vector_integer_ops
DEFAULT FOR TYPE integer USING hnsw AS DEFAULT FOR TYPE integer USING hnsw AS
OPERATOR 2 = (integer, integer); OPERATOR 2 = (integer, integer);
CREATE OPERATOR CLASS vector_text_ops
DEFAULT FOR TYPE text USING hnsw AS
OPERATOR 2 = (text, text);

12
test/t/020_hnsw_filtering.pl
View File

@@ -21,7 +21,7 @@ sub test_recall
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] ORDER BY v $operator '$queries[0]' LIMIT $limit; EXPLAIN ANALYZE SELECT i FROM tst WHERE c = '$cs[0]' ORDER BY v $operator '$queries[0]' LIMIT $limit;
)); ));
like($explain, qr/Index Cond/); like($explain, qr/Index Cond/);
@@ -29,7 +29,7 @@ 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] ORDER BY v $operator '$queries[$i]' LIMIT $limit; SELECT i FROM tst WHERE c = '$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;
@@ -58,13 +58,13 @@ $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 int4);"); $node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c text);");
$node->safe_psql("postgres", $node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc FROM generate_series(1, 10000) i;" "INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc FROM generate_series(1, 10000) i;"
); );
$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, c);"); $node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, c);");
$node->safe_psql("postgres", $node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc FROM generate_series(1, 10000) i;" "INSERT INTO tst SELECT i, ARRAY[$array_sql], (i % $nc)::text FROM generate_series(1, 10000) i;"
); );
# Generate queries # Generate queries
@@ -85,7 +85,7 @@ 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 $limit; SELECT i FROM tst WHERE c = '$cs[$i]' ORDER BY v <-> '$queries[$i]' LIMIT $limit;
)); ));
push(@expected, $res); push(@expected, $res);
} }
@@ -94,7 +94,7 @@ for my $i (0 .. $#queries)
test_recall(0.99, '<->'); test_recall(0.99, '<->');
# Test vacuum # Test vacuum
$node->safe_psql("postgres", "DELETE FROM tst WHERE c > 5;"); $node->safe_psql("postgres", "DELETE FROM tst WHERE c > '5';");
$node->safe_psql("postgres", "VACUUM tst;"); $node->safe_psql("postgres", "VACUUM tst;");
# Test columns # Test columns