liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-05 12:10:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into intvec

Browse Source
This commit is contained in:
Andrew Kane
2024-10-13 19:21:59 -07:00
parent 67de46487e 049972a4a3
commit a344ecb60d
33 changed files with 1609 additions and 572 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
test/t/002_ivfflat_vacuum.pl
View File

@@ -6,13 +6,7 @@ use Test::More;
my $dim = 3;
my @r = ();
for (1 .. $dim)
{
my $v = int(rand(1000)) + 1;
push(@r, "i % $v");
}
my $array_sql = join(", ", @r);
my $array_sql = join(",", ('random()') x $dim);
# Initialize node
my $node = PostgreSQL::Test::Cluster->new('node');
@@ -23,19 +17,20 @@ $node->start;
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
);
$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
# Get size
my $size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");
# Store values
$node->safe_psql("postgres", "CREATE TABLE tmp AS SELECT * FROM tst;");
# Delete all, vacuum, and insert same data
$node->safe_psql("postgres", "DELETE FROM tst;");
$node->safe_psql("postgres", "VACUUM tst;");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
);
$node->safe_psql("postgres", "INSERT INTO tst SELECT * FROM tmp;");
# Check size
my $new_size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");

6
test/t/009_ivfflat_filtering.pl
View File

@@ -94,8 +94,7 @@ like($explain, qr/Seq Scan/);
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query';
));
# TODO Do not use index
like($explain, qr/Index Scan using idx/);
like($explain, qr/Seq Scan/);
# Test attribute index
$node->safe_psql("postgres", "CREATE INDEX attribute_idx ON tst (c);");
@@ -110,7 +109,6 @@ $node->safe_psql("postgres", "CREATE INDEX partial_idx ON tst USING ivfflat (v v
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
));
# TODO Use partial index
like($explain, qr/Index Scan using idx/);
like($explain, qr/Index Scan using partial_idx/);
done_testing();

26
test/t/017_hnsw_filtering.pl
View File

@@ -18,9 +18,13 @@ $node->start;
# Create table and index
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c int4, t text);");
$node->safe_psql("postgres", "CREATE TABLE cat (i int4 PRIMARY KEY, t text, b boolean);");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc, 'test ' || i FROM generate_series(1, 10000) i;"
);
$node->safe_psql("postgres",
"INSERT INTO cat SELECT i, 'cat ' || i, i % 5 = 0 FROM generate_series(1, $nc) i;"
);
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
$node->safe_psql("postgres", "ANALYZE tst;");
@@ -37,8 +41,7 @@ my $c = int(rand() * $nc);
my $explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
));
# TODO Do not use index
like($explain, qr/Index Scan using idx/);
like($explain, qr/Seq Scan/);
# Test attribute filtering with few rows removed
$explain = $node->safe_psql("postgres", qq(
@@ -56,8 +59,7 @@ like($explain, qr/Index Scan using idx/);
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c < 1 ORDER BY v <-> '$query' LIMIT $limit;
));
# TODO Do not use index
like($explain, qr/Index Scan using idx/);
like($explain, qr/Seq Scan/);
# Test attribute filtering with few rows removed like
$explain = $node->safe_psql("postgres", qq(
@@ -96,13 +98,25 @@ $explain = $node->safe_psql("postgres", qq(
));
like($explain, qr/Seq Scan/);
# Test join
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT cat.t FROM cat INNER JOIN tst ON cat.i = tst.c ORDER BY v <-> '$query' LIMIT $limit;
));
like($explain, qr/Index Scan using idx/);
# Test join with attribute filtering
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT cat.t FROM cat INNER JOIN tst ON cat.i = tst.c WHERE cat.b = 't' ORDER BY v <-> '$query' LIMIT $limit;
));
like($explain, qr/Index Scan using idx/);
# Test attribute index
$node->safe_psql("postgres", "CREATE INDEX attribute_idx ON tst (c);");
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
));
# TODO Use attribute index
like($explain, qr/Index Scan using idx/);
# Use attribute index
like($explain, qr/Bitmap Index Scan on attribute_idx/);
# Test partial index
$node->safe_psql("postgres", "CREATE INDEX partial_idx ON tst USING hnsw (v vector_l2_ops) WHERE (c = $c);");

60
test/t/039_hnsw_cost.pl Normal file
View File

@@ -0,0 +1,60 @@
use strict;
use warnings FATAL => 'all';
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
my @dims = (384, 1536);
my $limit = 10;
# Initialize node
my $node = PostgreSQL::Test::Cluster->new('node');
$node->init;
$node->start;
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
for my $dim (@dims)
{
my $array_sql = join(",", ('random()') x $dim);
# Create table and index
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 2000) i;"
);
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
$node->safe_psql("postgres", "ANALYZE tst;");
# Generate query
my @r = ();
for (1 .. $dim)
{
push(@r, rand());
}
my $query = "[" . join(",", @r) . "]";
my $explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v <-> '$query' LIMIT $limit;
));
like($explain, qr/Index Scan using idx/);
# 3x the rows are needed for distance filters
# since the planner uses DEFAULT_INEQ_SEL for the selectivity (should be 1)
# Recreate index for performance
$node->safe_psql("postgres", "DROP INDEX idx;");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(2001, 6000) i;"
);
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
$node->safe_psql("postgres", "ANALYZE tst;");
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query' LIMIT $limit;
));
like($explain, qr/Index Scan using idx/);
$node->safe_psql("postgres", "DROP TABLE tst;");
}
done_testing();

50
test/t/040_ivfflat_cost.pl Normal file
View File

@@ -0,0 +1,50 @@
use strict;
use warnings FATAL => 'all';
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
my @dims = (384, 1536);
my $limit = 10;
# Initialize node
my $node = PostgreSQL::Test::Cluster->new('node');
$node->init;
$node->start;
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
for my $dim (@dims)
{
my $array_sql = join(",", ('random()') x $dim);
# Create table and index
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 5000) i;"
);
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING ivfflat (v vector_l2_ops) WITH (lists = 5);");
$node->safe_psql("postgres", "ANALYZE tst;");
# Generate query
my @r = ();
for (1 .. $dim)
{
push(@r, rand());
}
my $query = "[" . join(",", @r) . "]";
my $explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v <-> '$query' LIMIT $limit;
));
like($explain, qr/Index Scan using idx/);
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query' LIMIT $limit;
));
like($explain, qr/Index Scan using idx/);
$node->safe_psql("postgres", "DROP TABLE tst;");
}
done_testing();

54
test/t/041_ivfflat_iterative_search.pl Normal file
View File

@@ -0,0 +1,54 @@
use strict;
use warnings FATAL => 'all';
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
my $dim = 3;
my $array_sql = join(",", ('random()') x $dim);
# Initialize node
my $node = PostgreSQL::Test::Cluster->new('node');
$node->init;
$node->start;
# Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4 PRIMARY KEY, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
);
$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
my $count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = 10;
SET ivfflat.iterative_search = relaxed_order;
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
));
is($count, 10);
foreach ((30, 50, 70))
{
my $max_probes = $_;
my $expected = $max_probes / 10;
my $sum = 0;
for my $i (1 .. 20)
{
$count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = 10;
SET ivfflat.iterative_search = relaxed_order;
SET ivfflat.max_probes = $max_probes;
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst WHERE i = $i) LIMIT 11) t;
));
$sum += $count;
}
my $avg = $sum / 20;
cmp_ok($avg, '>', $expected - 2);
cmp_ok($avg, '<', $expected + 2);
}
done_testing();

125
test/t/042_ivfflat_iterative_search_recall.pl Normal file
View File

@@ -0,0 +1,125 @@
use strict;
use warnings FATAL => 'all';
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
my $node;
my @queries = ();
my @expected;
my $limit = 20;
my @cs = (100, 1000);
sub test_recall
{
my ($c, $probes, $min, $operator) = @_;
my $correct = 0;
my $total = 0;
my $explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = $probes;
SET ivfflat.iterative_search = relaxed_order;
EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Scan using idx on tst/);
for my $i (0 .. $#queries)
{
my $actual = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = $probes;
SET ivfflat.iterative_search = relaxed_order;
SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
));
my @actual_ids = split("\n", $actual);
my @expected_ids = split("\n", $expected[$i]);
my %expected_set = map { $_ => 1 } @expected_ids;
foreach (@actual_ids)
{
if (exists($expected_set{$_}))
{
$correct++;
}
}
$total += $limit;
}
cmp_ok($correct / $total, ">=", $min, "$operator $c");
}
# Initialize node
$node = PostgreSQL::Test::Cluster->new('node');
$node->init;
$node->start;
# Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector(3));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 100000) 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 = ("vector_l2_ops", "vector_cosine_ops");
for my $i (0 .. $#operators)
{
my $operator = $operators[$i];
my $opclass = $opclasses[$i];
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING ivfflat (v $opclass);");
foreach (@cs)
{
my $c = $_;
# Get exact results
@expected = ();
foreach (@queries)
{
my $res = $node->safe_psql("postgres", qq(
SET enable_indexscan = off;
WITH top AS (
SELECT v $operator '$_' AS distance FROM tst WHERE i % $c = 0 ORDER BY distance LIMIT $limit
)
SELECT i FROM tst WHERE (v $operator '$_') <= (SELECT MAX(distance) FROM top)
));
push(@expected, $res);
}
if ($c == 100)
{
test_recall($c, 1, 0.57, $operator);
test_recall($c, 10, 0.98, $operator);
}
else
{
if ($operator eq "<->")
{
test_recall($c, 1, 0.80, $operator);
}
else
{
test_recall($c, 1, 0.88, $operator);
}
}
}
$node->safe_psql("postgres", "DROP INDEX idx;");
}
done_testing();

67
test/t/043_hnsw_iterative_search.pl Normal file
View File

@@ -0,0 +1,67 @@
use strict;
use warnings FATAL => 'all';
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
my $dim = 3;
my $array_sql = join(",", ('random()') x $dim);
# Initialize node
my $node = PostgreSQL::Test::Cluster->new('node');
$node->init;
$node->start;
# Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4 PRIMARY KEY, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
);
$node->safe_psql("postgres", qq(
SET maintenance_work_mem = '128MB';
SET max_parallel_maintenance_workers = 2;
CREATE INDEX ON tst USING hnsw (v vector_l2_ops)
));
my $count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.iterative_search = relaxed_order;
SET work_mem = '8MB';
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
));
is($count, 10);
foreach ((30000, 50000, 70000))
{
my $max_tuples = $_;
my $expected = $max_tuples / 10000;
my $sum = 0;
for my $i (1 .. 20)
{
$count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.iterative_search = relaxed_order;
SET hnsw.max_search_tuples = $max_tuples;
SET work_mem = '8MB';
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst WHERE i = $i) LIMIT 11) t;
));
$sum += $count;
}
my $avg = $sum / 20;
cmp_ok($avg, '>', $expected - 2);
cmp_ok($avg, '<', $expected + 2);
}
my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.iterative_search = relaxed_order;
SET client_min_messages = debug1;
SET work_mem = '2MB';
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
));
like($stderr, qr/hnsw index scan exceeded work_mem after \d+ tuples/);
done_testing();

118
test/t/044_hnsw_iterative_search_recall.pl Normal file
View File

@@ -0,0 +1,118 @@
use strict;
use warnings FATAL => 'all';
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
my $node;
my @queries = ();
my @expected;
my $limit = 20;
my $dim = 3;
my $array_sql = join(",", ('random()') x $dim);
my @cs = (50, 500);
sub test_recall
{
my ($c, $ef_search, $min, $operator, $mode) = @_;
my $correct = 0;
my $total = 0;
my $explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.ef_search = $ef_search;
SET hnsw.iterative_search = $mode;
EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Scan using idx on tst/);
for my $i (0 .. $#queries)
{
my $actual = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.ef_search = $ef_search;
SET hnsw.iterative_search = $mode;
SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
));
my @actual_ids = split("\n", $actual);
my @expected_ids = split("\n", $expected[$i]);
my %expected_set = map { $_ => 1 } @expected_ids;
foreach (@actual_ids)
{
if (exists($expected_set{$_}))
{
$correct++;
}
}
$total += $limit;
}
cmp_ok($correct / $total, ">=", $min, "$operator $mode $c");
}
# Initialize node
$node = PostgreSQL::Test::Cluster->new('node');
$node->init;
$node->start;
# Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 50000) i;"
);
# Generate queries
for (1 .. 20)
{
my @r = ();
for (1 .. $dim)
{
push(@r, rand());
}
push(@queries, "[" . join(",", @r) . "]");
}
# Check each index type
my @operators = ("<->", "<=>");
my @opclasses = ("vector_l2_ops", "vector_cosine_ops");
for my $i (0 .. $#operators)
{
my $operator = $operators[$i];
my $opclass = $opclasses[$i];
$node->safe_psql("postgres", qq(
SET maintenance_work_mem = '128MB';
CREATE INDEX idx ON tst USING hnsw (v $opclass);
));
foreach (@cs)
{
my $c = $_;
# Get exact results
@expected = ();
foreach (@queries)
{
my $res = $node->safe_psql("postgres", qq(
SET enable_indexscan = off;
WITH top AS (
SELECT v $operator '$_' AS distance FROM tst WHERE i % $c = 0 ORDER BY distance LIMIT $limit
)
SELECT i FROM tst WHERE (v $operator '$_') <= (SELECT MAX(distance) FROM top)
));
push(@expected, $res);
}
test_recall($c, 40, 0.99, $operator, "strict_order");
test_recall($c, 40, 0.99, $operator, "relaxed_order");
}
$node->safe_psql("postgres", "DROP INDEX idx;");
}
done_testing();