Added test for arrays

.github/workflows/build.yml

@@ -28,7 +28,7 @@ jobs:
           dev-files: true
       - run: make
         env:
-          PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
+          PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
       - run: |
           export PG_CONFIG=`which pg_config`
           sudo --preserve-env=PG_CONFIG make install
@@ -49,7 +49,7 @@ jobs:
           postgres-version: 14
       - run: make
         env:
-          PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter
+          PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter
       - run: make install
       - run: make installcheck
       - if: ${{ failure() }}
@@ -97,15 +97,4 @@ jobs:
           sudo -u postgres make installcheck
           sudo -u postgres make prove_installcheck
         env:
-          PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
+          PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
-  valgrind:
-    if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ankane/setup-postgres-valgrind@v1
-        with:
-          postgres-version: 16
-      - run: make
-      - run: sudo --preserve-env=PG_CONFIG make install
-      - run: make installcheck

CHANGELOG.md

@@ -1,7 +1,6 @@
 ## 0.6.1 (unreleased)
 
 - Fixed error with `ANALYZE` and vectors with different dimensions
-- Fixed error with `shared_preload_libraries`
 
 ## 0.6.0 (2024-01-29)
 

Makefile

@@ -71,9 +71,11 @@ PG_MAJOR ?= 16
 .PHONY: docker
 
 docker:
-	docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
+	docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
+	docker build --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
 
 .PHONY: docker-release
 
 docker-release:
-	docker buildx build --push --pull --no-cache --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
+	docker buildx build --push --pull --no-cache --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
+	docker buildx build --push --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .

README.md

@@ -28,7 +28,7 @@ make install # may need sudo
 
 See the [installation notes](#installation-notes) if you run into issues
 
-You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), [pkg](#pkg), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres). There are also instructions for [GitHub Actions](https://github.com/pgvector/setup-pgvector).
+You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres). There are also instructions for [GitHub Actions](https://github.com/pgvector/setup-pgvector).
 
 ### Windows
 
@@ -716,21 +716,6 @@ sudo dnf install pgvector_16
 
 Note: Replace `16` with your Postgres server version
 
-### pkg
-
-Install the FreeBSD package with:
-
-```sh
-pkg install postgresql15-pg_vector
-```
-
-or the port with:
-
-```sh
-cd /usr/ports/databases/pgvector
-make install
-```
-
 ### conda-forge
 
 With Conda Postgres, install from [conda-forge](https://anaconda.org/conda-forge/pgvector) with:

src/hnsw.c

@@ -8,7 +8,6 @@
 #include "commands/progress.h"
 #include "commands/vacuum.h"
 #include "hnsw.h"
-#include "miscadmin.h"
 #include "utils/guc.h"
 #include "utils/selfuncs.h"
 
@@ -29,7 +28,7 @@ static relopt_kind hnsw_relopt_kind;
  * this grows bigger, we should use a shmem_request_hook and
  * RequestAddinShmemSpace() to pre-reserve space for this.
  */
-void
+static void
 HnswInitLockTranche(void)
 {
 	int		   *tranche_ids;
@@ -54,8 +53,7 @@ HnswInitLockTranche(void)
 void
 HnswInit(void)
 {
-	if (!process_shared_preload_libraries_in_progress)
+	HnswInitLockTranche();
-		HnswInitLockTranche();
 
 	hnsw_relopt_kind = add_reloption_kind();
 	add_int_reloption(hnsw_relopt_kind, "m", "Max number of connections",

src/hnsw.h

@@ -389,7 +389,6 @@ void		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation i
 void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
 void		HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
 void		HnswLoadNeighbors(HnswElement element, Relation index, int m);
-void		HnswInitLockTranche(void);
 PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
 
 /* Index access methods */

src/hnswbuild.c

@@ -176,7 +176,7 @@ CreateGraphPages(HnswBuildState * buildstate)
 		Size		etupSize;
 		Size		ntupSize;
 		Size		combinedSize;
-		Pointer		valuePtr = HnswPtrAccess(base, element->value);
+		void	   *valuePtr = HnswPtrAccess(base, element->value);
 
 		/* Update iterator */
 		iter = element->next;
@@ -601,9 +601,6 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 static void
 InitGraph(HnswGraph * graph, char *base, long memoryTotal)
 {
-	/* Initialize the lock tranche if needed */
-	HnswInitLockTranche();
-
 	HnswPtrStore(base, graph->head, (HnswElement) NULL);
 	HnswPtrStore(base, graph->entryPoint, (HnswElement) NULL);
 	graph->memoryUsed = 0;
@@ -672,10 +669,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->efConstruction = HnswGetEfConstruction(index);
 	buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
 
-	/* Require column to have dimensions to be indexed */
-	if (buildstate->dimensions < 0)
-		elog(ERROR, "column does not have dimensions");
-
 	if (buildstate->dimensions > HNSW_MAX_DIM)
 		elog(ERROR, "column cannot have more than %d dimensions for hnsw index", HNSW_MAX_DIM);
 
@@ -977,14 +970,6 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	/* Report less than allocated so never fails */
 	InitGraph(&hnswshared->graphData, hnswarea, esthnswarea - 1024 * 1024);
 
-	/*
-	 * Avoid base address for relptr for Postgres < 14.5
-	 * https://github.com/postgres/postgres/commit/7201cd18627afc64850537806da7f22150d1a83b
-	 */
-#if PG_VERSION_NUM < 140005
-	hnswshared->graphData.memoryUsed += MAXALIGN(1);
-#endif
-
 	shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_SHARED, hnswshared);
 	shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_AREA, hnswarea);
 

src/ivfbuild.c

@@ -904,27 +904,6 @@ IvfflatBeginParallel(IvfflatBuildState * buildstate, bool isconcurrent, int requ
 	WaitForParallelWorkersToAttach(pcxt);
 }
 
-/*
- * Compute parallel workers
- */
-static int
-ComputeParallelWorkers(Relation heap, Relation index)
-{
-	int			parallel_workers;
-
-	/* Make sure it's safe to use parallel workers */
-	parallel_workers = plan_create_index_workers(RelationGetRelid(heap), RelationGetRelid(index));
-	if (parallel_workers == 0)
-		return 0;
-
-	/* Use parallel_workers storage parameter on table if set */
-	parallel_workers = RelationGetParallelWorkers(heap, -1);
-	if (parallel_workers != -1)
-		return Min(parallel_workers, max_parallel_maintenance_workers);
-
-	return max_parallel_maintenance_workers;
-}
-
 /*
  * Scan table for tuples to index
  */
@@ -944,7 +923,7 @@ AssignTuples(IvfflatBuildState * buildstate)
 
 	/* Calculate parallel workers */
 	if (buildstate->heap != NULL)
-		parallel_workers = ComputeParallelWorkers(buildstate->heap, buildstate->index);
+		parallel_workers = plan_create_index_workers(RelationGetRelid(buildstate->heap), RelationGetRelid(buildstate->index));
 
 	/* Attempt to launch parallel worker scan when required */
 	if (parallel_workers > 0)

test/t/020_hnsw_array.pl

@@ -0,0 +1,113 @@
+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 float4[3]);");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 10000) i;"
+);
+
+$node->safe_psql("postgres", qq(
+	CREATE FUNCTION float4_l2_distance(float4[], float4[]) RETURNS float8
+		AS 'BEGIN RETURN l2_distance(\$1::vector, \$2::vector); END;'
+		LANGUAGE plpgsql IMMUTABLE STRICT PARALLEL SAFE;
+
+	CREATE FUNCTION float4_l2_squared_distance(float4[], float4[]) RETURNS float8
+		AS 'BEGIN RETURN vector_l2_squared_distance(\$1::vector, \$2::vector); END;'
+		LANGUAGE plpgsql IMMUTABLE STRICT PARALLEL SAFE;
+
+	CREATE OPERATOR <-> (
+		LEFTARG = float4[], RIGHTARG = float4[], PROCEDURE = float4_l2_distance,
+		COMMUTATOR = '<->'
+	);
+
+	CREATE OPERATOR CLASS float4_l2_ops
+		FOR TYPE float4[] USING hnsw AS
+		OPERATOR 1 <-> (float4[], float4[]) FOR ORDER BY float_ops,
+		FUNCTION 1 float4_l2_squared_distance(float4[], float4[]);
+));
+
+# 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 = ("float4_l2_ops");
+
+for my $i (0 .. $#operators)
+{
+	my $operator = $operators[$i];
+	my $opclass = $opclasses[$i];
+
+	# Get exact results
+	@expected = ();
+	foreach (@queries)
+	{
+		my $res = $node->safe_psql("postgres", "SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;");
+		push(@expected, $res);
+	}
+
+	# Add index
+	$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v $opclass);");
+
+	my $min = $operator eq "<#>" ? 0.80 : 0.99;
+	test_recall($min, $operator);
+}
+
+done_testing();