liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-06-06 05:51:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added streaming option for HNSW

Browse Source
This commit is contained in:
Andrew Kane
2024-09-22 12:02:48 -07:00
parent 97cf990e0f
commit 80cbd32dab
8 changed files with 421 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
test/t/039_hnsw_streaming.pl Normal file
View File

@@ -0,0 +1,43 @@
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;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($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 = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.streaming = on;
SET work_mem = '8MB';
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
));
is($count, 10);
my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.streaming = on;
SET work_mem = '2MB';
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
));
like($stderr, qr/iterative search exceeded work_mem after \d+ tuples/);
done_testing();

131
test/t/040_hnsw_streaming_recall.pl Normal file
View File

@@ -0,0 +1,131 @@
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 $dim);
my @cs = (100, 1000);
sub test_recall
{
my ($c, $ef_search, $min, $operator) = @_;
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.streaming = on;
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.streaming = on;
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);
}
# 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, 100000) 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, $res);
}
if ($c == 100)
{
test_recall($c, 40, 0.99, $operator);
}
else
{
if ($operator eq "<->")
{
test_recall($c, 40, 0.99, $operator);
}
else
{
test_recall($c, 40, 0.99, $operator);
}
}
}
$node->safe_psql("postgres", "DROP INDEX idx;");
}
done_testing();