Updated [skip ci]

.github/workflows/build.yml

@@ -37,10 +37,10 @@ jobs:
       - run: make installcheck
       - if: ${{ failure() }}
         run: cat regression.diffs
-      - run: |
-          sudo apt-get update
-          sudo apt-get install libipc-run-perl
-      - run: make prove_installcheck
+      # - run: |
+      #     sudo apt-get update
+      #     sudo apt-get install libipc-run-perl
+      # - run: make prove_installcheck
   mac:
     runs-on: ${{ matrix.os }}
     if: ${{ !startsWith(github.ref_name, 'windows') }}
@@ -65,21 +65,21 @@ jobs:
       - if: ${{ failure() }}
         run: cat regression.diffs
       # Homebrew Postgres does not enable TAP tests, so need to download
-      - run: |
-          brew install cpanm
-          cpanm --notest IPC::Run
-          wget -q https://github.com/postgres/postgres/archive/refs/tags/$TAG.tar.gz
-          tar xf $TAG.tar.gz
-          mv postgres-$TAG postgres
-        env:
-          TAG: ${{ matrix.postgres == 18 && 'REL_18_0' || 'REL_14_19' }}
-      - run: make prove_installcheck PROVE_FLAGS="-I ./postgres/src/test/perl -I ./test/perl"
-        env:
-          PERL5LIB: /Users/runner/perl5/lib/perl5
-      - run: make clean && $(brew --prefix llvm@$LLVM_VERSION)/bin/scan-build --status-bugs make
-        env:
-          LLVM_VERSION: ${{ matrix.os == 'macos-26' && 20 || 18 }}
-          PG_CFLAGS: -DUSE_ASSERT_CHECKING
+      # - run: |
+      #     brew install cpanm
+      #     cpanm --notest IPC::Run
+      #     wget -q https://github.com/postgres/postgres/archive/refs/tags/$TAG.tar.gz
+      #     tar xf $TAG.tar.gz
+      #     mv postgres-$TAG postgres
+      #   env:
+      #     TAG: ${{ matrix.postgres == 18 && 'REL_18_0' || 'REL_14_19' }}
+      # - run: make prove_installcheck PROVE_FLAGS="-I ./postgres/src/test/perl -I ./test/perl"
+      #   env:
+      #     PERL5LIB: /Users/runner/perl5/lib/perl5
+      # - run: make clean && $(brew --prefix llvm@$LLVM_VERSION)/bin/scan-build --status-bugs make
+      #   env:
+      #     LLVM_VERSION: ${{ matrix.os == 'macos-26' && 20 || 18 }}
+      #     PG_CFLAGS: -DUSE_ASSERT_CHECKING
   windows:
     runs-on: ${{ matrix.os }}
     if: ${{ !startsWith(github.ref_name, 'mac') }}
@@ -106,38 +106,4 @@ jobs:
         shell: cmd
       - if: ${{ failure() }}
         run: cat regression.diffs
-  i386:
-    if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
-    runs-on: ubuntu-latest
-    container:
-      image: debian:12
-      options: --platform linux/386
-    steps:
-      - run: apt-get update && apt-get install -y build-essential git libipc-run-perl postgresql-15 postgresql-server-dev-15 sudo
-      - run: service postgresql start
-      - run: |
-          git clone https://github.com/${{ github.repository }}.git pgvector
-          cd pgvector
-          git fetch origin ${{ github.ref }}
-          git reset --hard FETCH_HEAD
-          make
-          make install
-          chown -R postgres .
-          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
-      - if: ${{ failure() }}
-        run: cat pgvector/regression.diffs
-  valgrind:
-    if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v5
-      - uses: ankane/setup-postgres-valgrind@v1
-        with:
-          postgres-version: 18
-          check-ub: yes
-      - run: make OPTFLAGS=""
-      - run: sudo --preserve-env=PG_CONFIG make install
-      - run: make installcheck
+

CHANGELOG.md

@@ -1,7 +1,3 @@
-## 0.9.0 (unreleased)
-
-- Added support for inline filtering with HNSW
-
 ## 0.8.2 (unreleased)
 
 - Improved `install` target on Windows

README.md

@@ -467,12 +467,6 @@ If filtering by many different values, consider [partitioning](https://www.postg
 CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(category_id);
 ```
 
-Or a composite HNSW index (added in 0.9.0)
-
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_l2_ops, category_id);
-```
-
 ## Iterative Index Scans
 
 With approximate indexes, queries with filtering can return less results since filtering is applied *after* the index is scanned. Starting with 0.8.0, you can enable iterative index scans, which will automatically scan more of the index until enough results are found (or it reaches `hnsw.max_scan_tuples` or `ivfflat.max_probes`).
@@ -809,6 +803,7 @@ Raku | [pgvector-raku](https://github.com/pgvector/pgvector-raku)
 Ruby | [pgvector-ruby](https://github.com/pgvector/pgvector-ruby), [Neighbor](https://github.com/ankane/neighbor)
 Rust | [pgvector-rust](https://github.com/pgvector/pgvector-rust)
 Swift | [pgvector-swift](https://github.com/pgvector/pgvector-swift)
+Tcl | [pgvector-tcl](https://github.com/pgvector/pgvector-tcl)
 Zig | [pgvector-zig](https://github.com/pgvector/pgvector-zig)
 
 ## Frequently Asked Questions
@@ -1288,7 +1283,6 @@ Thanks to:
 - [k-means++: The Advantage of Careful Seeding](https://theory.stanford.edu/~sergei/papers/kMeansPP-soda.pdf)
 - [Concept Decompositions for Large Sparse Text Data using Clustering](https://www.cs.utexas.edu/users/inderjit/public_papers/concept_mlj.pdf)
 - [Efficient and Robust Approximate Nearest Neighbor Search using Hierarchical Navigable Small World Graphs](https://arxiv.org/ftp/arxiv/papers/1603/1603.09320.pdf)
-- [HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints](https://arxiv.org/pdf/2207.07940.pdf)
 
 ## History
 

sql/vector--0.8.1--0.9.0.sql

@@ -1,10 +0,0 @@
--- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "ALTER EXTENSION vector UPDATE TO '0.9.0'" to load this file. \quit
-
-CREATE FUNCTION hnsw_attribute_distance(integer, integer) RETURNS float8
-	AS 'MODULE_PATHNAME', 'hnsw_int4_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE OPERATOR CLASS vector_integer_ops
-	DEFAULT FOR TYPE integer USING hnsw AS
-	OPERATOR 2 = (integer, integer),
-	FUNCTION 4 hnsw_attribute_distance(integer, integer);

sql/vector.sql

@@ -916,13 +916,3 @@ CREATE OPERATOR CLASS sparsevec_l1_ops
 	OPERATOR 1 <+> (sparsevec, sparsevec) FOR ORDER BY float_ops,
 	FUNCTION 1 l1_distance(sparsevec, sparsevec),
 	FUNCTION 3 hnsw_sparsevec_support(internal);
-
--- hnsw attributes
-
-CREATE FUNCTION hnsw_attribute_distance(integer, integer) RETURNS float8
-	AS 'MODULE_PATHNAME', 'hnsw_int4_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE OPERATOR CLASS vector_integer_ops
-	DEFAULT FOR TYPE integer USING hnsw AS
-	OPERATOR 2 = (integer, integer),
-	FUNCTION 4 hnsw_attribute_distance(integer, integer);

src/bitvec.c

@@ -2,6 +2,7 @@
 
 #include "bitutils.h"
 #include "bitvec.h"
+#include "fmgr.h"
 #include "utils/varbit.h"
 #include "vector.h"
 

src/halfutils.c

@@ -1,5 +1,7 @@
 #include "postgres.h"
 
+#include <math.h>
+
 #include "halfutils.h"
 #include "halfvec.h"
 

src/halfvec.c

@@ -13,12 +13,16 @@
 #include "port.h"				/* for strtof() */
 #include "sparsevec.h"
 #include "utils/array.h"
-#include "utils/builtins.h"
 #include "utils/float.h"
+#include "utils/fmgrprotos.h"
 #include "utils/lsyscache.h"
-#include "utils/numeric.h"
+#include "utils/varbit.h"
 #include "vector.h"
 
+#if PG_VERSION_NUM >= 160000
+#include "varatt.h"
+#endif
+
 #define STATE_DIMS(x) (ARR_DIMS(x)[0] - 1)
 #define CreateStateDatums(dim) palloc(sizeof(Datum) * (dim + 1))
 

src/hnsw.c

@@ -1,18 +1,28 @@
 #include "postgres.h"
 
 #include <float.h>
+#include <limits.h>
 #include <math.h>
 
 #include "access/amapi.h"
+#include "access/genam.h"
 #include "access/reloptions.h"
 #include "commands/progress.h"
 #include "commands/vacuum.h"
+#include "fmgr.h"
 #include "hnsw.h"
 #include "miscadmin.h"
+#include "nodes/nodes.h"
+#include "nodes/pathnodes.h"
+#include "nodes/pg_list.h"
+#include "storage/lockdefs.h"
+#include "storage/shmem.h"
 #include "utils/float.h"
 #include "utils/guc.h"
+#include "utils/relcache.h"
 #include "utils/selfuncs.h"
 #include "utils/spccache.h"
+#include "vector.h"
 
 #if PG_VERSION_NUM < 150000
 #define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
@@ -263,7 +273,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 	IndexAmRoutine *amroutine = makeNode(IndexAmRoutine);
 
 	amroutine->amstrategies = 0;
-	amroutine->amsupport = 4;
+	amroutine->amsupport = 3;
 	amroutine->amoptsprocnum = 0;
 	amroutine->amcanorder = false;
 	amroutine->amcanorderbyop = true;
@@ -274,7 +284,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 #endif
 	amroutine->amcanbackward = false;	/* can change direction mid-scan */
 	amroutine->amcanunique = false;
-	amroutine->amcanmulticol = true;
+	amroutine->amcanmulticol = false;
 	amroutine->amoptionalkey = true;
 	amroutine->amsearcharray = false;
 	amroutine->amsearchnulls = false;
@@ -334,17 +344,3 @@ hnswhandler(PG_FUNCTION_ARGS)
 
 	PG_RETURN_POINTER(amroutine);
 }
-
-/*
- * Get the distance between two int4 attributes
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(hnsw_int4_attribute_distance);
-Datum
-hnsw_int4_attribute_distance(PG_FUNCTION_ARGS)
-{
-	int32		a = PG_GETARG_INT32(0);
-	int32		b = PG_GETARG_INT32(1);
-	double		distance = ((double) a) - ((double) b);
-
-	PG_RETURN_FLOAT8(distance);
-}

src/hnsw.h

@@ -3,6 +3,8 @@
 
 #include "postgres.h"
 
+#include <math.h>
+
 #include "access/genam.h"
 #include "access/parallel.h"
 #include "lib/pairingheap.h"
@@ -12,6 +14,10 @@
 #include "utils/sampling.h"
 #include "vector.h"
 
+#if PG_VERSION_NUM >= 190000
+typedef Pointer Item;
+#endif
+
 #define HNSW_MAX_DIM 2000
 #define HNSW_MAX_NNZ 1000
 
@@ -19,7 +25,6 @@
 #define HNSW_DISTANCE_PROC 1
 #define HNSW_NORM_PROC 2
 #define HNSW_TYPE_INFO_PROC 3
-#define HNSW_ATTRIBUTE_DISTANCE_PROC 4
 
 #define HNSW_VERSION	1
 #define HNSW_MAGIC_NUMBER 0xA953A953
@@ -108,8 +113,6 @@
 #define HnswPtrPointer(hp) (hp).ptr
 #define HnswPtrOffset(hp) relptr_offset((hp).relptr)
 
-#define HnswUseIndexTuple(index) (IndexRelationGetNumberOfAttributes(index) > 1)
-
 /* Variables */
 extern int	hnsw_ef_search;
 extern int	hnsw_iterative_scan;
@@ -137,7 +140,6 @@ HnswPtrDeclare(HnswElementData, HnswElementRelptr, HnswElementPtr);
 HnswPtrDeclare(HnswNeighborArray, HnswNeighborArrayRelptr, HnswNeighborArrayPtr);
 HnswPtrDeclare(HnswNeighborArrayPtr, HnswNeighborsRelptr, HnswNeighborsPtr);
 HnswPtrDeclare(char, DatumRelptr, DatumPtr);
-HnswPtrDeclare(IndexTupleData, IndexTupleRelptr, IndexTuplePtr);
 
 struct HnswElementData
 {
@@ -154,7 +156,6 @@ struct HnswElementData
 	OffsetNumber neighborOffno;
 	BlockNumber neighborPage;
 	DatumPtr	value;
-	IndexTuplePtr itup;
 	LWLock		lock;
 };
 
@@ -180,7 +181,6 @@ typedef struct HnswSearchCandidate
 	pairingheap_node w_node;
 	HnswElementPtr element;
 	double		distance;
-	bool		matches;
 }			HnswSearchCandidate;
 
 /* HNSW index options */
@@ -259,16 +259,14 @@ typedef struct HnswTypeInfo
 
 typedef struct HnswSupport
 {
-	FmgrInfo   *procinfo[2];
+	FmgrInfo   *procinfo;
 	FmgrInfo   *normprocinfo;
-	Oid		   *collation;
+	Oid			collation;
 }			HnswSupport;
 
 typedef struct HnswQuery
 {
 	Datum		value;
-	IndexTuple	itup;
-	ScanKeyData *keyData;
 }			HnswQuery;
 
 typedef struct HnswBuildState
@@ -297,8 +295,6 @@ typedef struct HnswBuildState
 	HnswGraph  *graph;
 	double		ml;
 	int			maxLevel;
-	bool		useIndexTuple;
-	TupleDesc	tupdesc;
 
 	/* Memory */
 	MemoryContext graphCtx;
@@ -427,32 +423,30 @@ bool		HnswCheckNorm(HnswSupport * support, Datum value);
 Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
 void		HnswInit(void);
-List	   *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, bool inMemory, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
+List	   *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
 HnswElement HnswGetEntryPoint(Relation index);
 void		HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
 void	   *HnswAlloc(HnswAllocator * allocator, Size size);
 HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
 HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
-void		HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool inMemory);
-HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, HnswSupport * support, bool loadVec, bool inMemory);
+void		HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing);
+HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec);
 void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
 void		HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
 void		HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
 HnswNeighborArray *HnswInitNeighborArray(int lm, HnswAllocator * allocator);
 void		HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
-bool		HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, ItemPointer heaptid, bool building, TupleDesc tupdesc);
+bool		HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building);
 void		HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building);
-void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index);
-void		HnswLoadElement(HnswElement element, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance);
-void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool useIndexTuple);
+void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
+void		HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance);
+bool		HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support);
+void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
 void		HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support);
-bool		HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc);
 bool		HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc);
 void		HnswInitLockTranche(void);
 const		HnswTypeInfo *HnswGetTypeInfo(Relation index);
 PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
-Size		HnswGetElementTupleSize(char *base, HnswElement element, bool useIndexTuple);
-bool		HnswIndexTupleIsEqual(IndexTuple a, IndexTuple b, TupleDesc tupdesc);
 
 /* Index access methods */
 IndexBuildResult *hnswbuild(Relation heap, Relation index, IndexInfo *indexInfo);

src/hnswbuild.c

@@ -36,23 +36,47 @@
  */
 #include "postgres.h"
 
-#include <math.h>
-
+#include "access/genam.h"
 #include "access/parallel.h"
+#include "access/relscan.h"
 #include "access/table.h"
 #include "access/tableam.h"
+#include "access/tupdesc.h"
 #include "access/xact.h"
 #include "access/xloginsert.h"
 #include "catalog/index.h"
 #include "catalog/pg_type_d.h"
 #include "commands/progress.h"
+#include "common/relpath.h"
 #include "hnsw.h"
 #include "miscadmin.h"
+#include "nodes/execnodes.h"
 #include "optimizer/optimizer.h"
+#include "storage/block.h"
+#include "storage/buf.h"
 #include "storage/bufmgr.h"
+#include "storage/bufpage.h"
+#include "storage/condition_variable.h"
+#include "storage/dsm.h"
+#include "storage/itemid.h"
+#include "storage/itemptr.h"
+#include "storage/lockdefs.h"
+#include "storage/lwlock.h"
+#include "storage/off.h"
+#include "storage/shm_toc.h"
+#include "storage/shmem.h"
+#include "storage/spin.h"
 #include "tcop/tcopprot.h"
 #include "utils/datum.h"
 #include "utils/memutils.h"
+#include "utils/rel.h"
+#include "utils/relcache.h"
+#include "utils/snapmgr.h"
+#include "utils/snapshot.h"
+
+#if PG_VERSION_NUM < 190000
+#include "storage/item.h"
+#endif
 
 #if PG_VERSION_NUM >= 160000
 #include "varatt.h"
@@ -66,6 +90,11 @@
 
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_status.h"
+#endif
+
+#if PG_VERSION_NUM >= 170000
+#include "utils/wait_event_types.h"
+#elif PG_VERSION_NUM >= 140000
 #include "utils/wait_event.h"
 #endif
 
@@ -152,7 +181,6 @@ CreateGraphPages(HnswBuildState * buildstate)
 	Page		page;
 	HnswElementPtr iter = buildstate->graph->head;
 	char	   *base = buildstate->hnswarea;
-	bool		useIndexTuple = buildstate->useIndexTuple;
 
 	/* Calculate sizes */
 	maxSize = HNSW_MAX_SIZE;
@@ -172,6 +200,7 @@ CreateGraphPages(HnswBuildState * buildstate)
 		Size		etupSize;
 		Size		ntupSize;
 		Size		combinedSize;
+		Pointer		valuePtr = HnswPtrAccess(base, element->value);
 
 		/* Update iterator */
 		iter = element->next;
@@ -180,7 +209,7 @@ CreateGraphPages(HnswBuildState * buildstate)
 		MemSet(etup, 0, HNSW_TUPLE_ALLOC_SIZE);
 
 		/* Calculate sizes */
-		etupSize = HnswGetElementTupleSize(base, element, useIndexTuple);
+		etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(valuePtr));
 		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, buildstate->m);
 		combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 
@@ -190,7 +219,7 @@ CreateGraphPages(HnswBuildState * buildstate)
 					(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
 					 errmsg("index tuple too large")));
 
-		HnswSetElementTuple(base, etup, element, useIndexTuple);
+		HnswSetElementTuple(base, etup, element);
 
 		/* Keep element and neighbors on the same page if possible */
 		if (PageGetFreeSpace(page) < etupSize || (combinedSize <= maxSize && PageGetFreeSpace(page) < combinedSize))
@@ -331,18 +360,19 @@ AddDuplicateInMemory(HnswElement element, HnswElement dup)
  * Find duplicate element
  */
 static bool
-FindDuplicateInMemory(char *base, HnswElement element, bool useIndexTuple, TupleDesc tupdesc)
+FindDuplicateInMemory(char *base, HnswElement element)
 {
 	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
-	IndexTuple	itup = HnswPtrAccess(base, element->itup);
+	Datum		value = HnswGetValue(base, element);
 
 	for (int i = 0; i < neighbors->length; i++)
 	{
 		HnswCandidate *neighbor = &neighbors->items[i];
 		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
+		Datum		neighborValue = HnswGetValue(base, neighborElement);
 
 		/* Exit early since ordered by distance */
-		if (!HnswIndexTupleIsEqual(itup, HnswPtrAccess(base, neighborElement->itup), tupdesc))
+		if (!datumIsEqual(value, neighborValue, false, -1))
 			return false;
 
 		/* Check for space */
@@ -369,7 +399,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
  * Update neighbors
  */
 static void
-UpdateNeighborsInMemory(char *base, Relation index, HnswSupport * support, HnswElement e, int m)
+UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -391,7 +421,7 @@ UpdateNeighborsInMemory(char *base, Relation index, HnswSupport * support, HnswE
 			Assert(neighborElement);
 
 			LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
-			HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, index, support);
+			HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, NULL, support);
 			LWLockRelease(&neighborElement->lock);
 		}
 	}
@@ -407,14 +437,14 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, HnswEleme
 	char	   *base = buildstate->hnswarea;
 
 	/* Look for duplicate */
-	if (FindDuplicateInMemory(base, element, buildstate->useIndexTuple, buildstate->tupdesc))
+	if (FindDuplicateInMemory(base, element))
 		return;
 
 	/* Add element */
 	AddElementInMemory(base, graph, element);
 
 	/* Update neighbors */
-	UpdateNeighborsInMemory(base, buildstate->index, support, element, m);
+	UpdateNeighborsInMemory(base, support, element, m);
 
 	/* Update entry point if needed (already have lock) */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -427,7 +457,6 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, HnswEleme
 static void
 InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 {
-	Relation	index = buildstate->index;
 	HnswGraph  *graph = buildstate->graph;
 	HnswSupport *support = &buildstate->support;
 	HnswElement entryPoint;
@@ -461,7 +490,7 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 	}
 
 	/* Find neighbors for element */
-	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false, true);
+	HnswFindElementNeighbors(base, element, entryPoint, NULL, support, m, efConstruction, false);
 
 	/* Update graph in memory */
 	UpdateGraphInMemory(support, element, m, entryPoint, buildstate);
@@ -480,20 +509,18 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	HnswElement element;
 	HnswAllocator *allocator = &buildstate->allocator;
 	HnswSupport *support = &buildstate->support;
+	Size		valueSize;
+	Pointer		valuePtr;
 	LWLock	   *flushLock = &graph->flushLock;
 	char	   *base = buildstate->hnswarea;
-	TupleDesc	tupdesc = buildstate->tupdesc;
-	IndexTuple	itup;
-	Size		itupSize;
-	IndexTuple	itupShared;
-	bool		unused;
+	Datum		value;
 
-	/* Form index tuple */
-	if (!HnswFormIndexTuple(&itup, values, isnull, buildstate->typeInfo, support, tupdesc))
+	/* Form index value */
+	if (!HnswFormIndexValue(&value, values, isnull, buildstate->typeInfo, support))
 		return false;
 
-	/* Get tuple size */
-	itupSize = IndexTupleSize(itup);
+	/* Get datum size */
+	valueSize = VARSIZE_ANY(DatumGetPointer(value));
 
 	/* Ensure graph not flushed when inserting */
 	LWLockAcquire(flushLock, LW_SHARED);
@@ -503,7 +530,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	{
 		LWLockRelease(flushLock);
 
-		return HnswInsertTupleOnDisk(index, support, itup, heaptid, true, tupdesc);
+		return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
 	}
 
 	/*
@@ -535,12 +562,12 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 
 		LWLockRelease(flushLock);
 
-		return HnswInsertTupleOnDisk(index, support, itup, heaptid, true, tupdesc);
+		return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
 	}
 
 	/* Ok, we can proceed to allocate the element */
 	element = HnswInitElement(base, heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel, allocator);
-	itupShared = HnswAlloc(allocator, itupSize);
+	valuePtr = HnswAlloc(allocator, valueSize);
 
 	/*
 	 * We have now allocated the space needed for the element, so we don't
@@ -549,10 +576,9 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	 */
 	LWLockRelease(&graph->allocatorLock);
 
-	/* Copy the tuple */
-	memcpy(itupShared, itup, itupSize);
-	HnswPtrStore(base, element->itup, itupShared);
-	HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itupShared, 1, tupdesc, &unused)));
+	/* Copy the datum */
+	memcpy(valuePtr, DatumGetPointer(value), valueSize);
+	HnswPtrStore(base, element->value, (char *) valuePtr);
 
 	/* Create a lock for the element */
 	LWLockInitialize(&element->lock, hnsw_lock_tranche_id);
@@ -679,19 +705,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 				 errmsg("type not supported for hnsw index")));
 
-	/* TODO See if needed */
-	if (IndexRelationGetNumberOfKeyAttributes(index) > 2)
-		elog(ERROR, "index cannot have more than two columns");
-
-	if (!OidIsValid(index_getprocid(index, 1, HNSW_DISTANCE_PROC)))
-		elog(ERROR, "first column must be a vector");
-
-	for (int i = 1; i < IndexRelationGetNumberOfKeyAttributes(index); i++)
-	{
-		if (!OidIsValid(index_getprocid(index, i + 1, HNSW_ATTRIBUTE_DISTANCE_PROC)))
-			elog(ERROR, "column %d cannot be a vector", i + 1);
-	}
-
 	/* Require column to have dimensions to be indexed */
 	if (buildstate->dimensions < 0)
 		ereport(ERROR,
@@ -718,8 +731,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->graph = &buildstate->graphData;
 	buildstate->ml = HnswGetMl(buildstate->m);
 	buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
-	buildstate->useIndexTuple = HnswUseIndexTuple(index);
-	buildstate->tupdesc = RelationGetDescr(index);
 
 	buildstate->graphCtx = GenerationContextCreate(CurrentMemoryContext,
 												   "Hnsw build graph context",

src/hnswinsert.c

@@ -1,13 +1,27 @@
 #include "postgres.h"
 
-#include <math.h>
-
+#include "access/genam.h"
 #include "access/generic_xlog.h"
+#include "common/relpath.h"
 #include "hnsw.h"
+#include "nodes/execnodes.h"
+#include "storage/block.h"
+#include "storage/buf.h"
 #include "storage/bufmgr.h"
+#include "storage/bufpage.h"
+#include "storage/itemid.h"
+#include "storage/itemptr.h"
 #include "storage/lmgr.h"
+#include "storage/lockdefs.h"
+#include "storage/off.h"
 #include "utils/datum.h"
 #include "utils/memutils.h"
+#include "utils/rel.h"
+#include "utils/relcache.h"
+
+#if PG_VERSION_NUM < 190000
+#include "storage/item.h"
+#endif
 
 #if PG_VERSION_NUM >= 160000
 #include "varatt.h"
@@ -160,10 +174,9 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 	BlockNumber newInsertPage = InvalidBlockNumber;
 	uint8		tupleVersion;
 	char	   *base = NULL;
-	bool		useIndexTuple = HnswUseIndexTuple(index);
 
 	/* Calculate sizes */
-	etupSize = HnswGetElementTupleSize(base, e, useIndexTuple);
+	etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(HnswPtrAccess(base, e->value)));
 	ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 	combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 	maxSize = HNSW_MAX_SIZE;
@@ -171,7 +184,7 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 
 	/* Prepare element tuple */
 	etup = palloc0(etupSize);
-	HnswSetElementTuple(base, etup, e, useIndexTuple);
+	HnswSetElementTuple(base, etup, e);
 
 	/* Prepare neighbor tuple */
 	ntup = palloc0(ntupSize);
@@ -388,9 +401,8 @@ LoadElementsForInsert(HnswNeighborArray * neighbors, HnswQuery * q, int *idx, Re
 		HnswCandidate *hc = &neighbors->items[i];
 		HnswElement element = HnswPtrAccess(base, hc->element);
 		double		distance;
-		bool		matches;
 
-		HnswLoadElement(element, &distance, &matches, q, index, support, true, NULL);
+		HnswLoadElement(element, &distance, q, index, support, true, NULL);
 		hc->distance = distance;
 
 		/* Prune element if being deleted */
@@ -434,8 +446,6 @@ GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int
 		HnswQuery	q;
 
 		q.value = HnswGetValue(base, element);
-		q.itup = HnswPtrAccess(base, element->itup);
-		q.keyData = NULL;
 
 		LoadElementsForInsert(neighbors, &q, &idx, index, support);
 
@@ -641,30 +651,21 @@ AddDuplicateOnDisk(Relation index, HnswElement element, HnswElement dup, bool bu
  * Find duplicate element
  */
 static bool
-FindDuplicateOnDisk(Relation index, HnswElement element, bool building, TupleDesc tupdesc)
+FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
 {
 	char	   *base = NULL;
 	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
 	Datum		value = HnswGetValue(base, element);
-	IndexTuple	itup = HnswPtrAccess(base, element->itup);
 
 	for (int i = 0; i < neighbors->length; i++)
 	{
 		HnswCandidate *neighbor = &neighbors->items[i];
 		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
+		Datum		neighborValue = HnswGetValue(base, neighborElement);
 
-		if (HnswUseIndexTuple(index))
-		{
-			/* Exit early since ordered by distance */
-			if (!HnswIndexTupleIsEqual(itup, HnswPtrAccess(base, neighborElement->itup), tupdesc))
-				return false;
-		}
-		else
-		{
-			/* Exit early since ordered by distance */
-			if (!datumIsEqual(value, HnswGetValue(base, neighborElement), false, -1))
-				return false;
-		}
+		/* Exit early since ordered by distance */
+		if (!datumIsEqual(value, neighborValue, false, -1))
+			return false;
 
 		if (AddDuplicateOnDisk(index, element, neighborElement, building))
 			return true;
@@ -677,12 +678,12 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building, TupleDes
  * Update graph on disk
  */
 static void
-UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, HnswElement entryPoint, bool building, TupleDesc tupdesc)
+UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, HnswElement entryPoint, bool building)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
 	/* Look for duplicate */
-	if (FindDuplicateOnDisk(index, element, building, tupdesc))
+	if (FindDuplicateOnDisk(index, element, building))
 		return;
 
 	/* Add element */
@@ -704,7 +705,7 @@ UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, in
  * Insert a tuple into the index
  */
 bool
-HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, ItemPointer heaptid, bool building, TupleDesc tupdesc)
+HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building)
 {
 	HnswElement entryPoint;
 	HnswElement element;
@@ -712,7 +713,6 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, It
 	int			efConstruction = HnswGetEfConstruction(index);
 	LOCKMODE	lockmode = ShareLock;
 	char	   *base = NULL;
-	bool		unused;
 
 	/*
 	 * Get a shared lock. This allows vacuum to ensure no in-flight inserts
@@ -726,8 +726,7 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, It
 
 	/* Create an element */
 	element = HnswInitElement(base, heaptid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
-	HnswPtrStore(base, element->itup, itup);
-	HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itup, 1, tupdesc, &unused)));
+	HnswPtrStore(base, element->value, (char *) DatumGetPointer(value));
 
 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -744,10 +743,10 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, It
 	}
 
 	/* Find neighbors for element */
-	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false, false);
+	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false);
 
 	/* Update graph on disk */
-	UpdateGraphOnDisk(index, support, element, m, entryPoint, building, tupdesc);
+	UpdateGraphOnDisk(index, support, element, m, entryPoint, building);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -761,18 +760,17 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, It
 static void
 HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid)
 {
-	IndexTuple	itup;
+	Datum		value;
 	const		HnswTypeInfo *typeInfo = HnswGetTypeInfo(index);
-	TupleDesc	tupdesc = RelationGetDescr(index);
 	HnswSupport support;
 
 	HnswInitSupport(&support, index);
 
-	/* Form index tuple */
-	if (!HnswFormIndexTuple(&itup, values, isnull, typeInfo, &support, tupdesc))
+	/* Form index value */
+	if (!HnswFormIndexValue(&value, values, isnull, typeInfo, &support))
 		return;
 
-	HnswInsertTupleOnDisk(index, &support, itup, heaptid, false, tupdesc);
+	HnswInsertTupleOnDisk(index, &support, value, heaptid, false);
 }
 
 /*

src/hnswscan.c

@@ -1,12 +1,25 @@
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/relscan.h"
+#include "access/sdir.h"
+#include "access/skey.h"
 #include "hnsw.h"
+#include "lib/pairingheap.h"
+#include "miscadmin.h"
+#include "nodes/pg_list.h"
 #include "pgstat.h"
-#include "storage/bufmgr.h"
+#include "storage/itemptr.h"
 #include "storage/lmgr.h"
+#include "storage/lockdefs.h"
 #include "utils/float.h"
 #include "utils/memutils.h"
+#include "utils/relcache.h"
+#include "utils/snapmgr.h"
+
+#if PG_VERSION_NUM >= 160000
+#include "varatt.h"
+#endif
 
 /*
  * Algorithm 5 from paper
@@ -22,30 +35,26 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	int			m;
 	HnswElement entryPoint;
 	char	   *base = NULL;
-	bool		inMemory = false;
 	HnswQuery  *q = &so->q;
 
-	q->value = value;
-	q->itup = NULL;
-	q->keyData = scan->keyData;
-
 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
 
+	q->value = value;
 	so->m = m;
 
 	if (entryPoint == NULL)
 		return NIL;
 
-	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, false, inMemory));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, false));
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, inMemory, NULL, NULL, true, NULL);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, NULL, NULL, true, NULL);
 		ep = w;
 	}
 
-	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, inMemory, &so->v, hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF ? &so->discarded : NULL, true, &so->tuples);
+	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, &so->v, hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF ? &so->discarded : NULL, true, &so->tuples);
 }
 
 /*
@@ -76,7 +85,7 @@ ResumeScanItems(IndexScanDesc scan)
 		ep = lappend(ep, sc);
 	}
 
-	return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, false, &so->v, &so->discarded, false, &so->tuples);
+	return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, &so->v, &so->discarded, false, &so->tuples);
 }
 
 /*
@@ -100,7 +109,7 @@ GetScanValue(IndexScanDesc scan)
 
 		/* Normalize if needed */
 		if (so->support.normprocinfo != NULL)
-			value = HnswNormValue(so->typeInfo, so->support.collation[0], value);
+			value = HnswNormValue(so->typeInfo, so->support.collation, value);
 	}
 
 	return value;
@@ -287,7 +296,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		element = HnswPtrAccess(base, sc->element);
 
 		/* Move to next element if no valid heap TIDs */
-		if (!sc->matches || element->heaptidsLength == 0)
+		if (element->heaptidsLength == 0)
 		{
 			so->w = list_delete_last(so->w);
 

src/hnswutils.c

@@ -2,18 +2,28 @@
 
 #include <math.h>
 
+#include "access/genam.h"
 #include "access/generic_xlog.h"
-#include "catalog/pg_type.h"
-#include "catalog/pg_type_d.h"
 #include "common/hashfn.h"
+#include "common/relpath.h"
 #include "fmgr.h"
 #include "hnsw.h"
 #include "lib/pairingheap.h"
+#include "nodes/pg_list.h"
+#include "port/atomics.h"
 #include "sparsevec.h"
+#include "storage/block.h"
+#include "storage/buf.h"
 #include "storage/bufmgr.h"
+#include "storage/bufpage.h"
+#include "storage/itemptr.h"
+#include "storage/lwlock.h"
+#include "storage/off.h"
 #include "utils/datum.h"
 #include "utils/memdebug.h"
 #include "utils/rel.h"
+#include "utils/relcache.h"
+#include "vector.h"
 
 #if PG_VERSION_NUM >= 160000
 #include "varatt.h"
@@ -150,39 +160,11 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
 void
 HnswInitSupport(HnswSupport * support, Relation index)
 {
-	support->procinfo[0] = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-
-	if (IndexRelationGetNumberOfKeyAttributes(index) > 1)
-		support->procinfo[1] = index_getprocinfo(index, 2, HNSW_ATTRIBUTE_DISTANCE_PROC);
-
-	support->collation = index->rd_indcollation;
+	support->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+	support->collation = index->rd_indcollation[0];
 	support->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
 }
 
-/*
- * Get element tuple size
- */
-Size
-HnswGetElementTupleSize(char *base, HnswElement element, bool useIndexTuple)
-{
-	Size		size;
-
-	if (useIndexTuple)
-	{
-		IndexTuple	itup = HnswPtrAccess(base, element->itup);
-
-		size = IndexTupleSize(itup);
-	}
-	else
-	{
-		Pointer		valuePtr = HnswPtrAccess(base, element->value);
-
-		size = VARSIZE_ANY(valuePtr);
-	}
-
-	return HNSW_ELEMENT_TUPLE_SIZE(size);
-}
-
 /*
  * Normalize value
  */
@@ -198,38 +180,7 @@ HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value)
 bool
 HnswCheckNorm(HnswSupport * support, Datum value)
 {
-	return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation[0], value)) > 0;
-}
-
-/*
- * Check if index tuples are equal
- */
-bool
-HnswIndexTupleIsEqual(IndexTuple a, IndexTuple b, TupleDesc tupdesc)
-{
-	for (int i = 0; i < tupdesc->natts; i++)
-	{
-		bool		nullA;
-		bool		nullB;
-
-		Datum		datumA = index_getattr(a, i + 1, tupdesc, &nullA);
-		Datum		datumB = index_getattr(b, i + 1, tupdesc, &nullB);
-
-		if (nullA || nullB)
-		{
-			if (nullA != nullB)
-				return false;
-		}
-		else
-		{
-			Form_pg_attribute att = TupleDescAttr(tupdesc, i);
-
-			if (!datumIsEqual(datumA, datumB, att->attbyval, att->attlen))
-				return false;
-		}
-	}
-
-	return true;
+	return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation, value)) > 0;
 }
 
 /*
@@ -319,8 +270,7 @@ HnswInitElement(char *base, ItemPointer heaptid, int m, double ml, int maxLevel,
 
 	HnswInitNeighbors(base, element, m, allocator);
 
-	HnswPtrStore(base, element->value, (Pointer) NULL);
-	HnswPtrStore(base, element->itup, (IndexTuple) NULL);
+	HnswPtrStore(base, element->value, (char *) NULL);
 
 	return element;
 }
@@ -346,8 +296,7 @@ HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno)
 	element->blkno = blkno;
 	element->offno = offno;
 	HnswPtrStore(base, element->neighbors, (HnswNeighborArrayPtr *) NULL);
-	HnswPtrStore(base, element->value, (Pointer) NULL);
-	HnswPtrStore(base, element->itup, (IndexTuple) NULL);
+	HnswPtrStore(base, element->value, (char *) NULL);
 	return element;
 }
 
@@ -460,13 +409,11 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
 }
 
 /*
- * Form index tuple
+ * Form index value
  */
 bool
-HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc)
+HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support)
 {
-	Datum		newValues[2];
-
 	/* Detoast once for all calls */
 	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
 
@@ -480,14 +427,10 @@ HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeI
 		if (!HnswCheckNorm(support, value))
 			return false;
 
-		value = HnswNormValue(typeInfo, support->collation[0], value);
+		value = HnswNormValue(typeInfo, support->collation, value);
 	}
 
-	newValues[0] = value;
-	for (int i = 1; i < tupdesc->natts; i++)
-		newValues[i] = values[i];
-
-	*out = index_form_tuple(tupdesc, newValues, isnull);
+	*out = value;
 
 	return true;
 }
@@ -496,8 +439,10 @@ HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeI
  * Set element tuple, except for neighbor info
  */
 void
-HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool useIndexTuple)
+HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element)
 {
+	Pointer		valuePtr = HnswPtrAccess(base, element->value);
+
 	etup->type = HNSW_ELEMENT_TUPLE_TYPE;
 	etup->level = element->level;
 	etup->deleted = 0;
@@ -509,19 +454,7 @@ HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool
 		else
 			ItemPointerSetInvalid(&etup->heaptids[i]);
 	}
-
-	if (useIndexTuple)
-	{
-		IndexTuple	itup = HnswPtrAccess(base, element->itup);
-
-		memcpy(&etup->data, itup, IndexTupleSize(itup));
-	}
-	else
-	{
-		Pointer		valuePtr = HnswPtrAccess(base, element->value);
-
-		memcpy(&etup->data, valuePtr, VARSIZE_ANY(valuePtr));
-	}
+	memcpy(&etup->data, valuePtr, VARSIZE_ANY(valuePtr));
 }
 
 /*
@@ -563,7 +496,7 @@ HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
  * Load an element from a tuple
  */
 void
-HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index)
+HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec)
 {
 	element->level = etup->level;
 	element->deleted = etup->deleted;
@@ -587,128 +520,26 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
 	if (loadVec)
 	{
 		char	   *base = NULL;
+		Datum		value = datumCopy(PointerGetDatum(&etup->data), false, -1);
 
-		if (HnswUseIndexTuple(index))
-		{
-			IndexTuple	itup = CopyIndexTuple((IndexTuple) &etup->data);
-			TupleDesc	tupdesc = RelationGetDescr(index);
-			bool		unused;
-
-			HnswPtrStore(base, element->itup, itup);
-			HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itup, 1, tupdesc, &unused)));
-		}
-		else
-		{
-			Datum		value = datumCopy(PointerGetDatum(&etup->data), false, -1);
-
-			HnswPtrStore(base, element->value, DatumGetPointer(value));
-		}
+		HnswPtrStore(base, element->value, (char *) DatumGetPointer(value));
 	}
 }
 
-/*
- * Get the attribute distance
- */
-static inline double
-AttributeDistance(double e)
-{
-	/* TODO Better bias */
-	/* must be >> max(w * g) + 1 / log10(2) */
-	double		bias = 4.32;
-
-	return e > 0 ? bias - 1.0 / log10(e + 1) : 0;
-}
-
 /*
  * Calculate the distance between values
  */
-static double
-HnswGetDistance(IndexTuple itup, Datum vec, HnswQuery * q, Relation index, HnswSupport * support, bool *matches)
+static inline double
+HnswGetDistance(Datum a, Datum b, HnswSupport * support)
 {
-	double		g;
-
-	if (DatumGetPointer(q->value) == NULL)
-		g = 0;
-	else
-		g = DatumGetFloat8(FunctionCall2Coll(support->procinfo[0], support->collation[0], q->value, vec));
-
-	Assert(PointerIsValid(matches));
-	*matches = true;
-
-	if (IndexRelationGetNumberOfKeyAttributes(index) > 1)
-	{
-		double		w = 0.25;
-		double		e = 0.0;
-		TupleDesc	tupdesc = RelationGetDescr(index);
-
-		if (q->keyData)
-		{
-			/* TODO need to pass length of key data */
-			int			keyCount = 1;
-
-			for (int i = 0; i < keyCount; i++)
-			{
-				ScanKey		key = &q->keyData[i];
-				bool		isnull;
-				Datum		value = index_getattr(itup, key->sk_attno, tupdesc, &isnull);
-				bool		attnull = key->sk_flags & SK_ISNULL;
-
-				if (isnull || attnull)
-				{
-					if (isnull != attnull)
-					{
-						e += 1000;
-						*matches = false;
-					}
-				}
-				else if (!DatumGetBool(FunctionCall2Coll(&key->sk_func, key->sk_collation, value, key->sk_argument)))
-				{
-					double		ei = fabs(DatumGetFloat8(FunctionCall2Coll(support->procinfo[key->sk_attno - 1], support->collation[key->sk_attno - 1], value, key->sk_argument)));
-
-					if (ei > 0)
-						e += ei;
-					else
-						/* Distance is zero for inequality */
-						e += 1000;
-
-					*matches = false;
-				}
-			}
-
-			return w * g + AttributeDistance(e);
-		}
-		else if (q->itup)
-		{
-			int			keyCount = IndexRelationGetNumberOfKeyAttributes(index) - 1;
-
-			for (int i = 0; i < keyCount; i++)
-			{
-				bool		isnull;
-				bool		attnull;
-				Datum		value = index_getattr(itup, i + 2, tupdesc, &isnull);
-				Datum		value2 = index_getattr(q->itup, i + 2, tupdesc, &attnull);
-
-				if (isnull || attnull)
-				{
-					if (isnull != attnull)
-						e += 1000;
-				}
-				else
-					e += fabs(DatumGetFloat8(FunctionCall2Coll(support->procinfo[i + 1], support->collation[i + 1], value, value2)));
-			}
-
-			return w * g + AttributeDistance(e);
-		}
-	}
-
-	return g;
+	return DatumGetFloat8(FunctionCall2Coll(support->procinfo, support->collation, a, b));
 }
 
 /*
  * Load an element and optionally get its distance from q
  */
 static void
-HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
+HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
 {
 	Buffer		buf;
 	Page		page;
@@ -726,23 +557,10 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, boo
 	/* Calculate distance */
 	if (distance != NULL)
 	{
-		IndexTuple	itup = NULL;
-		Datum		value;
-
-		if (HnswUseIndexTuple(index))
-		{
-			TupleDesc	tupdesc = RelationGetDescr(index);
-			bool		unused;
-
-			itup = (IndexTuple) &etup->data;
-			value = index_getattr(itup, 1, tupdesc, &unused);
-		}
+		if (DatumGetPointer(q->value) == NULL)
+			*distance = 0;
 		else
-		{
-			value = PointerGetDatum(&etup->data);
-		}
-
-		*distance = HnswGetDistance(itup, value, q, index, support, matches);
+			*distance = HnswGetDistance(q->value, PointerGetDatum(&etup->data), support);
 	}
 
 	/* Load element */
@@ -751,7 +569,7 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, boo
 		if (*element == NULL)
 			*element = HnswInitElementFromBlock(blkno, offno);
 
-		HnswLoadElementFromTuple(*element, etup, true, loadVec, index);
+		HnswLoadElementFromTuple(*element, etup, true, loadVec);
 	}
 
 	UnlockReleaseBuffer(buf);
@@ -761,34 +579,32 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, boo
  * Load an element and optionally get its distance from q
  */
 void
-HnswLoadElement(HnswElement element, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
+HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
 {
-	HnswLoadElementImpl(element->blkno, element->offno, distance, matches, q, index, support, loadVec, maxDistance, &element);
+	HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, support, loadVec, maxDistance, &element);
 }
 
 /*
  * Get the distance for an element
  */
 static double
-GetElementDistance(char *base, HnswElement element, bool *matches, HnswQuery * q, Relation index, HnswSupport * support)
+GetElementDistance(char *base, HnswElement element, HnswQuery * q, HnswSupport * support)
 {
 	Datum		value = HnswGetValue(base, element);
-	IndexTuple	itup = HnswPtrAccess(base, element->itup);
 
-	return HnswGetDistance(itup, value, q, index, support, matches);
+	return HnswGetDistance(q->value, value, support);
 }
 
 /*
  * Allocate a search candidate
  */
 static HnswSearchCandidate *
-HnswInitSearchCandidate(char *base, HnswElement element, double distance, bool matches)
+HnswInitSearchCandidate(char *base, HnswElement element, double distance)
 {
 	HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
 
 	HnswPtrStore(base, sc->element, element);
 	sc->distance = distance;
-	sc->matches = matches;
 	return sc;
 }
 
@@ -796,17 +612,17 @@ HnswInitSearchCandidate(char *base, HnswElement element, double distance, bool m
  * Create a candidate for the entry point
  */
 HnswSearchCandidate *
-HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, bool inMemory)
+HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec)
 {
+	bool		inMemory = index == NULL;
 	double		distance;
-	bool		matches;
 
 	if (inMemory)
-		distance = GetElementDistance(base, entryPoint, &matches, q, index, support);
+		distance = GetElementDistance(base, entryPoint, q, support);
 	else
-		HnswLoadElement(entryPoint, &distance, &matches, q, index, support, loadVec, NULL);
+		HnswLoadElement(entryPoint, &distance, q, index, support, loadVec, NULL);
 
-	return HnswInitSearchCandidate(base, entryPoint, distance, matches);
+	return HnswInitSearchCandidate(base, entryPoint, distance);
 }
 
 /*
@@ -1009,7 +825,7 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, bool inMemory, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
+HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
 {
 	List	   *w = NIL;
 	pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
@@ -1022,8 +838,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 	int			lm = HnswGetLayerM(m, lc);
 	HnswUnvisited *unvisited = palloc(lm * sizeof(HnswUnvisited));
 	int			unvisitedLength;
-	uint64		additional = 0;
-	uint64		maxAdditional = q->keyData && lc == 0 ? 10000 : 0;
+	bool		inMemory = index == NULL;
 
 	if (v == NULL)
 	{
@@ -1064,10 +879,6 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 		pairingheap_add(C, &sc->c_node);
 		pairingheap_add(W, &sc->w_node);
 
-		/* Do not count elements that do not match filter towards ef */
-		if (!sc->matches && ++additional <= maxAdditional)
-			continue;
-
 		/*
 		 * Do not count elements being deleted towards ef when vacuuming. It
 		 * would be ideal to do this for inserts as well, but this could
@@ -1102,7 +913,6 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 			HnswElement eElement;
 			HnswSearchCandidate *e;
 			double		eDistance;
-			bool		eMatches;
 			bool		alwaysAdd = wlen < ef;
 
 			f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
@@ -1110,7 +920,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 			if (inMemory)
 			{
 				eElement = unvisited[i].element;
-				eDistance = GetElementDistance(base, eElement, &eMatches, q, index, support);
+				eDistance = GetElementDistance(base, eElement, q, support);
 			}
 			else
 			{
@@ -1120,18 +930,18 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 
 				/* Avoid any allocations if not adding */
 				eElement = NULL;
-				HnswLoadElementImpl(blkno, offno, &eDistance, &eMatches, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
+				HnswLoadElementImpl(blkno, offno, &eDistance, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
 
 				if (eElement == NULL)
 					continue;
 			}
 
-			if (eElement == NULL || !(eDistance < f->distance || alwaysAdd))
+			if (!(eDistance < f->distance || alwaysAdd))
 			{
 				if (discarded != NULL)
 				{
 					/* Create a new candidate */
-					e = HnswInitSearchCandidate(base, eElement, eDistance, eMatches);
+					e = HnswInitSearchCandidate(base, eElement, eDistance);
 					pairingheap_add(*discarded, &e->w_node);
 				}
 
@@ -1143,7 +953,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 				continue;
 
 			/* Create a new candidate */
-			e = HnswInitSearchCandidate(base, eElement, eDistance, eMatches);
+			e = HnswInitSearchCandidate(base, eElement, eDistance);
 			pairingheap_add(C, &e->c_node);
 			pairingheap_add(W, &e->w_node);
 
@@ -1154,10 +964,6 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 			 */
 			if (CountElement(skipElement, eElement))
 			{
-				/* Do not count elements that do not match filter towards ef */
-				if (!e->matches && ++additional <= maxAdditional)
-					continue;
-
 				wlen++;
 
 				/* No need to decrement wlen */
@@ -1235,24 +1041,18 @@ CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
  * Check if an element is closer to q than any element from R
  */
 static bool
-CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, HnswSupport * support)
+CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support)
 {
 	HnswElement eElement = HnswPtrAccess(base, e->element);
-	HnswQuery	q;
+	Datum		eValue = HnswGetValue(base, eElement);
 	ListCell   *lc2;
 
-	q.value = HnswGetValue(base, eElement);
-	q.itup = HnswPtrAccess(base, eElement->itup);
-	q.keyData = NULL;
-
 	foreach(lc2, r)
 	{
 		HnswCandidate *ri = lfirst(lc2);
 		HnswElement riElement = HnswPtrAccess(base, ri->element);
 		Datum		riValue = HnswGetValue(base, riElement);
-		IndexTuple	ritup = HnswPtrAccess(base, riElement->itup);
-		bool		matches;
-		float		distance = HnswGetDistance(ritup, riValue, &q, index, support, &matches);
+		float		distance = HnswGetDistance(eValue, riValue, support);
 
 		if (distance <= e->distance)
 			return false;
@@ -1265,7 +1065,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, HnswS
  * Algorithm 4 from paper
  */
 static List *
-SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
+SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
 {
 	List	   *r = NIL;
 	List	   *w = list_copy(c);
@@ -1299,7 +1099,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * suppo
 
 		/* Use previous state of r and wd to skip work when possible */
 		if (mustCalculate)
-			e->closer = CheckElementCloser(base, e, r, index, support);
+			e->closer = CheckElementCloser(base, e, r, support);
 		else if (list_length(added) > 0)
 		{
 			/* Keep Valgrind happy for in-memory, parallel builds */
@@ -1312,7 +1112,8 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * suppo
 			 */
 			if (e->closer)
 			{
-				e->closer = CheckElementCloser(base, e, added, index, support);
+				e->closer = CheckElementCloser(base, e, added, support);
+
 				if (!e->closer)
 					removedAny = true;
 			}
@@ -1324,7 +1125,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * suppo
 				 */
 				if (removedAny)
 				{
-					e->closer = CheckElementCloser(base, e, r, index, support);
+					e->closer = CheckElementCloser(base, e, r, support);
 					if (e->closer)
 						added = lappend(added, e);
 				}
@@ -1332,7 +1133,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * suppo
 		}
 		else if (e == newCandidate)
 		{
-			e->closer = CheckElementCloser(base, e, r, index, support);
+			e->closer = CheckElementCloser(base, e, r, support);
 			if (e->closer)
 				added = lappend(added, e);
 		}
@@ -1409,7 +1210,7 @@ HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newE
 			c = lappend(c, &neighbors->items[i]);
 		c = lappend(c, &newHc);
 
-		SelectNeighbors(base, c, lm, index, support, &neighbors->closerSet, &newHc, &pruned, true);
+		SelectNeighbors(base, c, lm, support, &neighbors->closerSet, &newHc, &pruned, true);
 
 		/* Should not happen */
 		if (pruned == NULL)
@@ -1480,19 +1281,17 @@ PrecomputeHash(char *base, HnswElement element)
  * Algorithm 1 from paper
  */
 void
-HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool inMemory)
+HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing)
 {
 	List	   *ep;
 	List	   *w;
 	int			level = element->level;
 	int			entryLevel;
 	HnswQuery	q;
-
 	HnswElement skipElement = existing ? element : NULL;
+	bool		inMemory = index == NULL;
 
 	q.value = HnswGetValue(base, element);
-	q.itup = HnswPtrAccess(base, element->itup);
-	q.keyData = NULL;
 
 	/* Precompute hash */
 	if (inMemory)
@@ -1503,13 +1302,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		return;
 
 	/* Get entry point and level */
-	ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, support, true, inMemory));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, support, true));
 	entryLevel = entryPoint->level;
 
 	/* 1st phase: greedy search to insert level */
 	for (int lc = entryLevel; lc >= level + 1; lc--)
 	{
-		w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, inMemory, NULL, NULL, true, NULL);
+		w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
 		ep = w;
 	}
 
@@ -1528,7 +1327,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		List	   *lw = NIL;
 		ListCell   *lc2;
 
-		w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, inMemory, NULL, NULL, true, NULL);
+		w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
 
 		/* Convert search candidates to candidates */
 		foreach(lc2, w)
@@ -1552,7 +1351,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		 * sortCandidates to true for in-memory builds to enable closer
 		 * caching, but there does not seem to be a difference in performance.
 		 */
-		neighbors = SelectNeighbors(base, lw, lm, index, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
+		neighbors = SelectNeighbors(base, lw, lm, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
 
 		AddConnections(base, element, neighbors, lc);
 

src/hnswvacuum.c

@@ -1,13 +1,26 @@
 #include "postgres.h"
 
-#include <math.h>
-
+#include "access/genam.h"
 #include "access/generic_xlog.h"
 #include "commands/vacuum.h"
+#include "common/relpath.h"
 #include "hnsw.h"
+#include "nodes/pg_list.h"
+#include "storage/block.h"
+#include "storage/buf.h"
 #include "storage/bufmgr.h"
+#include "storage/bufpage.h"
+#include "storage/itemptr.h"
 #include "storage/lmgr.h"
+#include "storage/lockdefs.h"
+#include "storage/off.h"
 #include "utils/memutils.h"
+#include "utils/rel.h"
+#include "utils/relcache.h"
+
+#if PG_VERSION_NUM < 190000
+#include "storage/item.h"
+#endif
 
 #if PG_VERSION_NUM >= 160000
 #include "varatt.h"
@@ -178,7 +191,12 @@ NeedsUpdated(HnswVacuumState * vacuumstate, HnswElement element)
 	/* Also update if layer 0 is not full */
 	/* This could indicate too many candidates being deleted during insert */
 	if (!needsUpdated)
+	{
+		/* Keep clang-tidy happy */
+		Assert(ntup->count > 0);
+
 		needsUpdated = !ItemPointerIsValid(&ntup->indextids[ntup->count - 1]);
+	}
 
 	UnlockReleaseBuffer(buf);
 
@@ -212,7 +230,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	element->heaptidsLength = 0;
 
 	/* Find neighbors for element, skipping itself */
-	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true, false);
+	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true);
 
 	/* Zero memory for each element */
 	MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
@@ -264,7 +282,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 		LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
 
 		/* Load element */
-		HnswLoadElement(highestPoint, NULL, NULL, NULL, index, support, true, NULL);
+		HnswLoadElement(highestPoint, NULL, NULL, index, support, true, NULL);
 
 		/* Repair if needed */
 		if (NeedsUpdated(vacuumstate, highestPoint))
@@ -302,7 +320,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 			 * is outdated, this can remove connections at higher levels in
 			 * the graph until they are repaired, but this should be fine.
 			 */
-			HnswLoadElement(entryPoint, NULL, NULL, NULL, index, support, true, NULL);
+			HnswLoadElement(entryPoint, NULL, NULL, index, support, true, NULL);
 
 			if (NeedsUpdated(vacuumstate, entryPoint))
 			{
@@ -378,7 +396,7 @@ RepairGraph(HnswVacuumState * vacuumstate)
 
 			/* Create an element */
 			element = HnswInitElementFromBlock(blkno, offno);
-			HnswLoadElementFromTuple(element, etup, false, true, index);
+			HnswLoadElementFromTuple(element, etup, false, true);
 
 			elements = lappend(elements, element);
 		}
@@ -448,7 +466,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	BlockNumber insertPage = InvalidBlockNumber;
 	Relation	index = vacuumstate->index;
 	BufferAccessStrategy bas = vacuumstate->bas;
-	bool		useIndexTuple = HnswUseIndexTuple(index);
 
 	/*
 	 * Wait for index scans to complete. Scans before this point may contain
@@ -529,15 +546,9 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 			ntup = (HnswNeighborTuple) PageGetItem(npage, PageGetItemId(npage, neighborOffno));
 
 			/* Overwrite element */
+			/* Use memset instead of MemSet to keep clang-tidy happy */
 			etup->deleted = 1;
-			if (useIndexTuple)
-			{
-				IndexTuple	itup = (IndexTuple) &etup->data;
-
-				MemSet(itup, 0, IndexTupleSize(itup));
-			}
-			else
-				MemSet(&etup->data, 0, VARSIZE_ANY(&etup->data));
+			memset(&etup->data, 0, VARSIZE_ANY(&etup->data));
 
 			/* Overwrite neighbors */
 			for (int i = 0; i < ntup->count; i++)

src/ivfbuild.c

@@ -2,23 +2,52 @@
 
 #include <float.h>
 
+#include "access/attnum.h"
+#include "access/genam.h"
+#include "access/generic_xlog.h"
+#include "access/itup.h"
+#include "access/relscan.h"
 #include "access/table.h"
 #include "access/tableam.h"
+#include "access/tupdesc.h"
 #include "access/parallel.h"
 #include "access/xact.h"
-#include "bitvec.h"
+#include "access/xloginsert.h"
 #include "catalog/index.h"
 #include "catalog/pg_operator_d.h"
 #include "catalog/pg_type_d.h"
 #include "commands/progress.h"
-#include "halfvec.h"
+#include "common/relpath.h"
+#include "executor/tuptable.h"
+#include "fmgr.h"
 #include "ivfflat.h"
 #include "miscadmin.h"
+#include "nodes/execnodes.h"
 #include "optimizer/optimizer.h"
+#include "storage/block.h"
+#include "storage/buf.h"
 #include "storage/bufmgr.h"
+#include "storage/bufpage.h"
+#include "storage/condition_variable.h"
+#include "storage/dsm.h"
+#include "storage/itemptr.h"
+#include "storage/lockdefs.h"
+#include "storage/off.h"
+#include "storage/shm_toc.h"
+#include "storage/shmem.h"
+#include "storage/spin.h"
 #include "tcop/tcopprot.h"
 #include "utils/memutils.h"
-#include "vector.h"
+#include "utils/rel.h"
+#include "utils/relcache.h"
+#include "utils/sampling.h"
+#include "utils/snapmgr.h"
+#include "utils/snapshot.h"
+#include "utils/tuplesort.h"
+
+#if PG_VERSION_NUM < 190000
+#include "storage/item.h"
+#endif
 
 #if PG_VERSION_NUM >= 160000
 #include "varatt.h"
@@ -32,6 +61,11 @@
 
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_status.h"
+#endif
+
+#if PG_VERSION_NUM >= 170000
+#include "utils/wait_event_types.h"
+#elif PG_VERSION_NUM >= 140000
 #include "utils/wait_event.h"
 #endif
 

src/ivfflat.c

@@ -3,14 +3,22 @@
 #include <float.h>
 
 #include "access/amapi.h"
+#include "access/genam.h"
 #include "access/reloptions.h"
 #include "commands/progress.h"
 #include "commands/vacuum.h"
+#include "fmgr.h"
 #include "ivfflat.h"
+#include "nodes/nodes.h"
+#include "nodes/pathnodes.h"
+#include "nodes/pg_list.h"
+#include "storage/lockdefs.h"
 #include "utils/float.h"
 #include "utils/guc.h"
+#include "utils/relcache.h"
 #include "utils/selfuncs.h"
 #include "utils/spccache.h"
+#include "vector.h"
 
 #if PG_VERSION_NUM < 150000
 #define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)

src/ivfflat.h

@@ -25,6 +25,10 @@
 #include "portability/instr_time.h"
 #endif
 
+#if PG_VERSION_NUM >= 190000
+typedef Pointer Item;
+#endif
+
 #define IVFFLAT_MAX_DIM 2000
 
 /* Support functions */

src/ivfinsert.c

@@ -2,11 +2,29 @@
 
 #include <float.h>
 
+#include "access/genam.h"
 #include "access/generic_xlog.h"
+#include "access/itup.h"
+#include "common/relpath.h"
+#include "fmgr.h"
 #include "ivfflat.h"
+#include "nodes/execnodes.h"
+#include "storage/block.h"
+#include "storage/buf.h"
 #include "storage/bufmgr.h"
+#include "storage/bufpage.h"
+#include "storage/itemid.h"
+#include "storage/itemptr.h"
 #include "storage/lmgr.h"
+#include "storage/lockdefs.h"
+#include "storage/off.h"
 #include "utils/memutils.h"
+#include "utils/rel.h"
+#include "utils/relcache.h"
+
+#if PG_VERSION_NUM < 190000
+#include "storage/item.h"
+#endif
 
 /*
  * Find the list that minimizes the distance function

src/ivfkmeans.c

@@ -1,17 +1,15 @@
 #include "postgres.h"
 
 #include <float.h>
+#include <limits.h>
 #include <math.h>
 
-#include "bitvec.h"
-#include "halfutils.h"
-#include "halfvec.h"
+#include "access/genam.h"
+#include "fmgr.h"
 #include "ivfflat.h"
 #include "miscadmin.h"
-#include "utils/builtins.h"
-#include "utils/datum.h"
 #include "utils/memutils.h"
-#include "vector.h"
+#include "utils/relcache.h"
 
 #if PG_VERSION_NUM >= 160000
 #include "varatt.h"

src/ivfscan.c

@@ -2,15 +2,38 @@
 
 #include <float.h>
 
+#include "access/attnum.h"
+#include "access/genam.h"
+#include "access/itup.h"
 #include "access/relscan.h"
+#include "access/sdir.h"
+#include "access/skey.h"
+#include "access/tupdesc.h"
 #include "catalog/pg_operator_d.h"
 #include "catalog/pg_type_d.h"
+#include "common/relpath.h"
+#include "executor/tuptable.h"
+#include "fmgr.h"
 #include "lib/pairingheap.h"
 #include "ivfflat.h"
 #include "miscadmin.h"
 #include "pgstat.h"
+#include "storage/block.h"
+#include "storage/buf.h"
 #include "storage/bufmgr.h"
+#include "storage/bufpage.h"
+#include "storage/itemid.h"
+#include "storage/itemptr.h"
+#include "storage/off.h"
 #include "utils/memutils.h"
+#include "utils/rel.h"
+#include "utils/relcache.h"
+#include "utils/snapmgr.h"
+#include "utils/tuplesort.h"
+
+#if PG_VERSION_NUM >= 160000
+#include "varatt.h"
+#endif
 
 #define GetScanList(ptr) pairingheap_container(IvfflatScanList, ph_node, ptr)
 #define GetScanListConst(ptr) pairingheap_const_container(IvfflatScanList, ph_node, ptr)

src/ivfutils.c

@@ -1,13 +1,23 @@
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/generic_xlog.h"
-#include "bitvec.h"
-#include "catalog/pg_type.h"
+#include "common/relpath.h"
 #include "fmgr.h"
 #include "halfutils.h"
 #include "halfvec.h"
 #include "ivfflat.h"
+#include "storage/block.h"
+#include "storage/buf.h"
 #include "storage/bufmgr.h"
+#include "storage/bufpage.h"
+#include "utils/relcache.h"
+#include "utils/varbit.h"
+#include "vector.h"
+
+#if PG_VERSION_NUM >= 160000
+#include "varatt.h"
+#endif
 
 /*
  * Allocate a vector array

src/ivfvacuum.c

@@ -1,9 +1,18 @@
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/generic_xlog.h"
+#include "access/itup.h"
 #include "commands/vacuum.h"
+#include "common/relpath.h"
 #include "ivfflat.h"
+#include "storage/block.h"
+#include "storage/buf.h"
 #include "storage/bufmgr.h"
+#include "storage/bufpage.h"
+#include "storage/itemptr.h"
+#include "storage/off.h"
+#include "utils/relcache.h"
 
 #if PG_VERSION_NUM >= 180000
 #define vacuum_delay_point() vacuum_delay_point(false)

src/sparsevec.c

@@ -5,18 +5,23 @@
 
 #include "catalog/pg_type.h"
 #include "common/shortest_dec.h"
-#include "common/string.h"
 #include "fmgr.h"
 #include "halfutils.h"
 #include "halfvec.h"
+#include "lib/stringinfo.h"
 #include "libpq/pqformat.h"
 #include "sparsevec.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/float.h"
+#include "utils/fmgrprotos.h"
 #include "utils/lsyscache.h"
 #include "vector.h"
 
+#if PG_VERSION_NUM >= 160000
+#include "varatt.h"
+#endif
+
 typedef struct SparseInputElement
 {
 	int32		index;

src/vector.c

@@ -16,10 +16,10 @@
 #include "port.h"				/* for strtof() */
 #include "sparsevec.h"
 #include "utils/array.h"
-#include "utils/builtins.h"
 #include "utils/float.h"
+#include "utils/fmgrprotos.h"
 #include "utils/lsyscache.h"
-#include "utils/numeric.h"
+#include "utils/varbit.h"
 #include "vector.h"
 
 #if PG_VERSION_NUM >= 160000

test/t/045_hnsw_hqann.pl

@@ -1,113 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @cs = ();
-my @expected;
-my $limit = 20;
-my $dim = 3;
-my $array_sql = join(",", ('random()') x $dim);
-my $nc = 1000;
-
-sub test_recall
-{
-	my ($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 WHERE c = $cs[0] ORDER BY v $operator '$queries[0]' LIMIT $limit;
-	));
-	like($explain, qr/Index Cond/);
-
-	for my $i (0 .. $#queries)
-	{
-		my $actual = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SELECT i FROM tst WHERE c = $cs[$i] ORDER BY v $operator '$queries[$i]' LIMIT $limit;
-		));
-		my @actual_ids = split("\n", $actual);
-		my %actual_set = map { $_ => 1 } @actual_ids;
-
-		is(scalar(@actual_ids), $limit);
-
-		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 = 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($dim), c int4);");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc FROM generate_series(1, 20000) i;"
-);
-
-# Generate queries
-for (1 .. 20)
-{
-	my @r = ();
-	for (1 .. $dim)
-	{
-		push(@r, rand());
-	}
-	push(@queries, "[" . join(",", @r) . "]");
-	push(@cs, int(rand() * $nc));
-}
-
-# Get exact results
-@expected = ();
-for my $i (0 .. $#queries)
-{
-	my $res = $node->safe_psql("postgres", "SELECT i FROM tst WHERE c = $cs[$i] ORDER BY v <=> '$queries[$i]' LIMIT $limit;");
-	push(@expected, $res);
-}
-
-# Add index
-$node->safe_psql("postgres", qq(
-	SET maintenance_work_mem = '256MB';
-	SET max_parallel_maintenance_workers = 2;
-	CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, c);
-));
-
-# Test recall
-test_recall(0.99, '<=>');
-
-# Test vacuum
-$node->safe_psql("postgres", "DELETE FROM tst WHERE c > 5;");
-$node->safe_psql("postgres", "VACUUM tst;");
-
-# Test columns
-my ($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c);");
-like($stderr, qr/first column must be a vector/);
-
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c, v vector_cosine_ops);");
-like($stderr, qr/first column must be a vector/);
-
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, c, c);");
-like($stderr, qr/index cannot have more than two columns/);
-
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, v vector_cosine_ops);");
-like($stderr, qr/column 2 cannot be a vector/);
-
-done_testing();