mirror of
https://github.com/pgvector/pgvector.git
synced 2026-06-30 17:51:18 +08:00
Added test for HNSW insert recall with sparsevec
This commit is contained in:
@@ -98,6 +98,7 @@ for my $i (0 .. $#operators)
|
||||
push(@expected, $res);
|
||||
}
|
||||
|
||||
# Test approximate results
|
||||
my $min = $operator eq "<#>" ? 0.80 : 0.99;
|
||||
test_recall($min, $operator);
|
||||
|
||||
|
||||
@@ -105,6 +105,7 @@ for my $i (0 .. $#operators)
|
||||
push(@expected, $res);
|
||||
}
|
||||
|
||||
# Test approximate results
|
||||
my $min = $operator eq "<\%>" ? 0.95 : 0.98;
|
||||
test_recall($min, $operator);
|
||||
|
||||
|
||||
@@ -102,6 +102,7 @@ for my $i (0 .. $#operators)
|
||||
push(@expected, $res);
|
||||
}
|
||||
|
||||
# Test approximate results
|
||||
my $min = $operator eq "<#>" ? 0.95 : 0.98;
|
||||
test_recall($min, $operator);
|
||||
|
||||
|
||||
109
test/t/025_hnsw_sparsevec_insert_recall.pl
Normal file
109
test/t/025_hnsw_sparsevec_insert_recall.pl
Normal file
@@ -0,0 +1,109 @@
|
||||
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 serial, v sparsevec(3));");
|
||||
|
||||
# Generate queries
|
||||
for (1 .. 20)
|
||||
{
|
||||
my $r1 = rand();
|
||||
my $r2 = rand();
|
||||
my $r3 = rand();
|
||||
push(@queries, "{1:$r1,2:$r2,3:$r3}/3");
|
||||
}
|
||||
|
||||
# Check each index type
|
||||
my @operators = ("<->", "<#>", "<=>");
|
||||
my @opclasses = ("sparsevec_l2_ops", "sparsevec_ip_ops", "sparsevec_cosine_ops");
|
||||
|
||||
for my $i (0 .. $#operators)
|
||||
{
|
||||
my $operator = $operators[$i];
|
||||
my $opclass = $opclasses[$i];
|
||||
|
||||
# Add index
|
||||
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v $opclass);");
|
||||
|
||||
# Use concurrent inserts
|
||||
$node->pgbench(
|
||||
"--no-vacuum --client=10 --transactions=1000",
|
||||
0,
|
||||
[qr{actually processed}],
|
||||
[qr{^$}],
|
||||
"concurrent INSERTs",
|
||||
{
|
||||
"025_hnsw_sparsevec_insert_recall_$opclass" => "INSERT INTO tst (v) VALUES (ARRAY[random(), random(), random()]::vector::sparsevec);"
|
||||
}
|
||||
);
|
||||
|
||||
# Get exact results
|
||||
@expected = ();
|
||||
foreach (@queries)
|
||||
{
|
||||
my $res = $node->safe_psql("postgres", qq(
|
||||
SET enable_indexscan = off;
|
||||
SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;
|
||||
));
|
||||
push(@expected, $res);
|
||||
}
|
||||
|
||||
# Test approximate results
|
||||
my $min = $operator eq "<#>" ? 0.80 : 0.99;
|
||||
test_recall($min, $operator);
|
||||
|
||||
$node->safe_psql("postgres", "DROP INDEX idx;");
|
||||
$node->safe_psql("postgres", "TRUNCATE tst;");
|
||||
}
|
||||
|
||||
done_testing();
|
||||
Reference in New Issue
Block a user