liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-13 16:16:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added HNSW index type - #181

Browse Source
This commit is contained in:
Andrew Kane
2023-08-08 16:42:47 -07:00
parent 19a6c81367
commit 51d292c93d
29 changed files with 3927 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

103
test/t/013_hnsw_insert_recall.pl Normal file
View File

@@ -0,0 +1,103 @@
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 int4, v vector(3));");
# 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 = ("<->", "<#>", "<=>");
foreach (@operators) {
my $operator = $_;
# Add index
my $opclass;
if ($operator eq "<->") {
$opclass = "vector_l2_ops";
} elsif ($operator eq "<#>") {
$opclass = "vector_ip_ops";
} else {
$opclass = "vector_cosine_ops";
}
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v $opclass);");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 10000) i;"
);
# 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, $res);
}
if ($operator eq "<#>") {
test_recall(0.80, $operator);
} else {
test_recall(0.99, $operator);
}
$node->safe_psql("postgres", "DROP INDEX idx;");
$node->safe_psql("postgres", "TRUNCATE tst;");
}
done_testing();