Added support for inline filtering with IVFFlat

Fixed sortdesc for multiple attributes [skip ci]
List assignment does not change with scaling [skip ci]
2026-07-22 03:57:34 +08:00 · 2024-10-10 17:07:47 -07:00 · 2024-10-10 15:22:23 -07:00 · 2024-10-10 15:16:08 -07:00 · 2024-10-10 14:24:26 -07:00 · 2024-10-10 12:54:13 -07:00
21 changed files with 792 additions and 456 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,7 +1,9 @@
 ## 0.8.0 (unreleased)

+- Added support for inline filtering with IVFFlat
 - Added casts for arrays to `sparsevec`
 - Improved cost estimation
+- Improved performance of HNSW inserts and on-disk index builds
 - Reduced memory usage for HNSW index scans
 - Dropped support for Postgres 12

--- a/README.md
+++ b/README.md
@@ -439,6 +439,12 @@ Create an index on one [or more](https://www.postgresql.org/docs/current/indexes
 CREATE INDEX ON items (category_id);
 ```

+Or a composite IVFFlat index for approximate search (added in 0.8.0)
+
+```sql
+CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops, category_id) WITH (lists = 100);
+```
+
 Or a [partial index](https://www.postgresql.org/docs/current/indexes-partial.html) on the vector column for approximate search

 ```sql
--- a/sql/vector--0.7.4--0.8.0.sql
+++ b/sql/vector--0.7.4--0.8.0.sql
@@ -24,3 +24,5 @@ CREATE CAST (double precision[] AS sparsevec)

 CREATE CAST (numeric[] AS sparsevec)
 	WITH FUNCTION array_to_sparsevec(numeric[], integer, boolean) AS ASSIGNMENT;
+
+-- TODO add ivfflat attributes
--- a/sql/vector.sql
+++ b/sql/vector.sql
@@ -916,3 +916,13 @@ 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);
+
+-- ivfflat attributes
+
+CREATE OPERATOR CLASS vector_integer_ops
+	DEFAULT FOR TYPE integer USING ivfflat AS
+	OPERATOR 2 < ,
+	OPERATOR 3 <= ,
+	OPERATOR 4 = ,
+	OPERATOR 5 >= ,
+	OPERATOR 6 > ;
--- a/src/hnsw.c
+++ b/src/hnsw.c
@@ -100,10 +100,8 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 {
 	GenericCosts costs;
 	int			m;
-	int			entryLevel;
-	int			layer0TuplesMax;
-	double		layer0Selectivity;
-	double		scalingFactor = 0.55;
+	double		ratio;
+	double		startupPages;
 	double		spc_seq_page_cost;
 	Relation	index;

@@ -120,6 +118,8 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,

 	MemSet(&costs, 0, sizeof(costs));

+	genericcostestimate(root, path, loop_count, &costs);
+
 	index = index_open(path->indexinfo->indexoid, NoLock);
 	HnswGetMetaPageInfo(index, &m, NULL);
 	index_close(index, NoLock);
@@ -151,30 +151,38 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	 * at L0, accounting for previously visited tuples, multiplied by the
 	 * "scalingFactor" (currently hardcoded).
 	 */
-	entryLevel = (int) (log(path->indexinfo->tuples + 1) * HnswGetMl(m));
-	layer0TuplesMax = HnswGetLayerM(m, 0) * hnsw_ef_search;
-	layer0Selectivity = (scalingFactor * log(path->indexinfo->tuples + 1)) /
-		(log(m) * (1 + log(hnsw_ef_search)));
+	if (path->indexinfo->tuples > 0)
+	{
+		double		scalingFactor = 0.55;
+		int			entryLevel = (int) (log(path->indexinfo->tuples) * HnswGetMl(m));
+		int			layer0TuplesMax = HnswGetLayerM(m, 0) * hnsw_ef_search;
+		double		layer0Selectivity = scalingFactor * log(path->indexinfo->tuples) / (log(m) * (1 + log(hnsw_ef_search)));

-	costs.numIndexTuples = (entryLevel * m) +
-		(layer0TuplesMax * layer0Selectivity);
+		ratio = (entryLevel * m + layer0TuplesMax * layer0Selectivity) / path->indexinfo->tuples;

-	genericcostestimate(root, path, loop_count, &costs);
+		if (ratio > 1)
+			ratio = 1;
+	}
+	else
+		ratio = 1;

 	get_tablespace_page_costs(path->indexinfo->reltablespace, NULL, &spc_seq_page_cost);

+	/* Startup cost is cost before returning the first row */
+	costs.indexStartupCost = costs.indexTotalCost * ratio;
+
 	/* Adjust cost if needed since TOAST not included in seq scan cost */
-	if (costs.numIndexPages > path->indexinfo->rel->pages)
+	startupPages = costs.numIndexPages * ratio;
+	if (startupPages > path->indexinfo->rel->pages && ratio < 0.5)
 	{
 		/* Change all page cost from random to sequential */
-		costs.indexTotalCost -= costs.numIndexPages * (costs.spc_random_page_cost - spc_seq_page_cost);
+		costs.indexStartupCost -= startupPages * (costs.spc_random_page_cost - spc_seq_page_cost);

 		/* Remove cost of extra pages */
-		costs.indexTotalCost -= (costs.numIndexPages - path->indexinfo->rel->pages) * spc_seq_page_cost;
+		costs.indexStartupCost -= (startupPages - path->indexinfo->rel->pages) * spc_seq_page_cost;
 	}

-	/* Use total cost since most work happens before first tuple is returned */
-	*indexStartupCost = costs.indexTotalCost;
+	*indexStartupCost = costs.indexStartupCost;
 	*indexTotalCost = costs.indexTotalCost;
 	*indexSelectivity = costs.indexSelectivity;
 	*indexCorrelation = costs.indexCorrelation;
--- a/src/hnsw.h
+++ b/src/hnsw.h
@@ -88,6 +88,9 @@
 /* Ensure fits on page and in uint8 */
 #define HnswGetMaxLevel(m) Min(((BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - offsetof(HnswNeighborTupleData, indextids) - sizeof(ItemIdData)) / (sizeof(ItemPointerData)) / (m)) - 2, 255)

+#define HnswGetSearchCandidate(membername, ptr) pairingheap_container(HnswSearchCandidate, membername, ptr)
+#define HnswGetSearchCandidateConst(membername, ptr) pairingheap_const_container(HnswSearchCandidate, membername, ptr)
+
 #define HnswGetValue(base, element) PointerGetDatum(HnswPtrAccess(base, (element)->value))

 #if PG_VERSION_NUM < 140005
@@ -160,7 +163,7 @@ typedef struct HnswSearchCandidate
 	pairingheap_node c_node;
 	pairingheap_node w_node;
 	HnswElementPtr element;
-	float		distance;
+	double		distance;
 }			HnswSearchCandidate;

 /* HNSW index options */
@@ -185,8 +188,8 @@ typedef struct HnswGraph

 	/* Allocations state */
 	LWLock		allocatorLock;
-	long		memoryUsed;
-	long		memoryTotal;
+	Size		memoryUsed;
+	Size		memoryTotal;

 	/* Flushed state */
 	LWLock		flushLock;
@@ -237,6 +240,18 @@ typedef struct HnswTypeInfo
 	void		(*checkValue) (Pointer v);
 }			HnswTypeInfo;

+typedef struct HnswSupport
+{
+	FmgrInfo   *procinfo;
+	FmgrInfo   *normprocinfo;
+	Oid			collation;
+}			HnswSupport;
+
+typedef struct HnswQuery
+{
+	Datum		value;
+}			HnswQuery;
+
 typedef struct HnswBuildState
 {
 	/* Info */
@@ -256,9 +271,7 @@ typedef struct HnswBuildState
 	double		reltuples;

 	/* Support functions */
-	FmgrInfo   *procinfo;
-	FmgrInfo   *normprocinfo;
-	Oid			collation;
+	HnswSupport support;

 	/* Variables */
 	HnswGraph	graphData;
@@ -325,6 +338,19 @@ typedef struct HnswNeighborTupleData

 typedef HnswNeighborTupleData * HnswNeighborTuple;

+typedef union
+{
+	struct pointerhash_hash *pointers;
+	struct offsethash_hash *offsets;
+	struct tidhash_hash *tids;
+}			visited_hash;
+
+typedef union
+{
+	HnswElement element;
+	ItemPointerData indextid;
+}			HnswUnvisited;
+
 typedef struct HnswScanOpaqueData
 {
 	const		HnswTypeInfo *typeInfo;
@@ -333,9 +359,7 @@ typedef struct HnswScanOpaqueData
 	MemoryContext tmpCtx;

 	/* Support functions */
-	FmgrInfo   *procinfo;
-	FmgrInfo   *normprocinfo;
-	Oid			collation;
+	HnswSupport support;
 }			HnswScanOpaqueData;

 typedef HnswScanOpaqueData * HnswScanOpaque;
@@ -353,8 +377,7 @@ typedef struct HnswVacuumState
 	int			efConstruction;

 	/* Support functions */
-	FmgrInfo   *procinfo;
-	Oid			collation;
+	HnswSupport support;

 	/* Variables */
 	struct tidhash_hash *deleted;
@@ -370,30 +393,33 @@ typedef struct HnswVacuumState
 int			HnswGetM(Relation index);
 int			HnswGetEfConstruction(Relation index);
 FmgrInfo   *HnswOptionalProcInfo(Relation index, uint16 procnum);
+void		HnswInitSupport(HnswSupport * support, Relation index);
 Datum		HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value);
-bool		HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value);
+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, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
+List	   *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement);
 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, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
-HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
+void		HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing);
+HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, 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, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
-void		HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
+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);
-void		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, float *maxDistance);
+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, 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		HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support);
+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);
--- a/src/hnswbuild.c
+++ b/src/hnswbuild.c
@@ -366,7 +366,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
 * Update neighbors
 */
 static void
-UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m)
+UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -388,7 +388,7 @@ UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswEleme
 			Assert(neighborElement);

 			LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
-			HnswUpdateConnection(base, e, hc, lm, lc, NULL, NULL, procinfo, collation);
+			HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, NULL, support);
 			LWLockRelease(&neighborElement->lock);
 		}
 	}
@@ -398,7 +398,7 @@ UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswEleme
 * Update graph in memory
 */
 static void
-UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
+UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
 {
 	HnswGraph  *graph = buildstate->graph;
 	char	   *base = buildstate->hnswarea;
@@ -411,7 +411,7 @@ UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int
 	AddElementInMemory(base, graph, element);

 	/* Update neighbors */
-	UpdateNeighborsInMemory(base, procinfo, collation, element, m);
+	UpdateNeighborsInMemory(base, support, element, m);

 	/* Update entry point if needed (already have lock) */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -424,9 +424,8 @@ UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int
 static void
 InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 {
-	FmgrInfo   *procinfo = buildstate->procinfo;
-	Oid			collation = buildstate->collation;
 	HnswGraph  *graph = buildstate->graph;
+	HnswSupport *support = &buildstate->support;
 	HnswElement entryPoint;
 	LWLock	   *entryLock = &graph->entryLock;
 	LWLock	   *entryWaitLock = &graph->entryWaitLock;
@@ -458,10 +457,10 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 	}

 	/* Find neighbors for element */
-	HnswFindElementNeighbors(base, element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
+	HnswFindElementNeighbors(base, element, entryPoint, NULL, support, m, efConstruction, false);

 	/* Update graph in memory */
-	UpdateGraphInMemory(procinfo, collation, element, m, efConstruction, entryPoint, buildstate);
+	UpdateGraphInMemory(support, element, m, efConstruction, entryPoint, buildstate);

 	/* Release entry lock */
 	LWLockRelease(entryLock);
@@ -473,30 +472,19 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 static bool
 InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, HnswBuildState * buildstate)
 {
-	const		HnswTypeInfo *typeInfo = buildstate->typeInfo;
 	HnswGraph  *graph = buildstate->graph;
 	HnswElement element;
 	HnswAllocator *allocator = &buildstate->allocator;
+	HnswSupport *support = &buildstate->support;
 	Size		valueSize;
 	Pointer		valuePtr;
 	LWLock	   *flushLock = &graph->flushLock;
 	char	   *base = buildstate->hnswarea;
+	Datum		value;

-	/* Detoast once for all calls */
-	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
-
-	/* Check value */
-	if (typeInfo->checkValue != NULL)
-		typeInfo->checkValue(DatumGetPointer(value));
-
-	/* Normalize if needed */
-	if (buildstate->normprocinfo != NULL)
-	{
-		if (!HnswCheckNorm(buildstate->normprocinfo, buildstate->collation, value))
-			return false;
-
-		value = HnswNormValue(typeInfo, buildstate->collation, value);
-	}
+	/* Form index value */
+	if (!HnswFormIndexValue(&value, values, isnull, buildstate->typeInfo, support))
+		return false;

 	/* Get datum size */
 	valueSize = VARSIZE_ANY(DatumGetPointer(value));
@@ -509,7 +497,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	{
 		LWLockRelease(flushLock);

-		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true);
+		return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
 	}

 	/*
@@ -541,7 +529,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn

 		LWLockRelease(flushLock);

-		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true);
+		return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
 	}

 	/* Ok, we can proceed to allocate the element */
@@ -607,7 +595,7 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
 * Initialize the graph
 */
 static void
-InitGraph(HnswGraph * graph, char *base, long memoryTotal)
+InitGraph(HnswGraph * graph, char *base, Size memoryTotal)
 {
 	/* Initialize the lock tranche if needed */
 	HnswInitLockTranche();
@@ -704,11 +692,9 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->indtuples = 0;

 	/* Get support functions */
-	buildstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-	buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	buildstate->collation = index->rd_indcollation[0];
+	HnswInitSupport(&buildstate->support, index);

-	InitGraph(&buildstate->graphData, NULL, maintenance_work_mem * 1024L);
+	InitGraph(&buildstate->graphData, NULL, (Size) maintenance_work_mem * 1024L);
 	buildstate->graph = &buildstate->graphData;
 	buildstate->ml = HnswGetMl(buildstate->m);
 	buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
--- a/src/hnswinsert.c
+++ b/src/hnswinsert.c
@@ -334,6 +334,107 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 		*updatedInsertPage = newInsertPage;
 }

+/*
+ * Load neighbors
+ */
+static HnswNeighborArray *
+HnswLoadNeighbors(HnswElement element, Relation index, int m, int lm, int lc)
+{
+	char	   *base = NULL;
+	HnswNeighborArray *neighbors = HnswInitNeighborArray(lm, NULL);
+	ItemPointerData indextids[HNSW_MAX_M * 2];
+
+	if (!HnswLoadNeighborTids(element, indextids, index, m, lm, lc))
+		return neighbors;
+
+	for (int i = 0; i < lm; i++)
+	{
+		ItemPointer indextid = &indextids[i];
+		HnswElement e;
+		HnswCandidate *hc;
+
+		if (!ItemPointerIsValid(indextid))
+			break;
+
+		e = HnswInitElementFromBlock(ItemPointerGetBlockNumber(indextid), ItemPointerGetOffsetNumber(indextid));
+		hc = &neighbors->items[neighbors->length++];
+		HnswPtrStore(base, hc->element, e);
+	}
+
+	return neighbors;
+}
+
+/*
+ * Load elements for insert
+ */
+static void
+LoadElementsForInsert(HnswNeighborArray * neighbors, HnswQuery * q, int *idx, Relation index, HnswSupport * support)
+{
+	char	   *base = NULL;
+
+	for (int i = 0; i < neighbors->length; i++)
+	{
+		HnswCandidate *hc = &neighbors->items[i];
+		HnswElement element = HnswPtrAccess(base, hc->element);
+		double		distance;
+
+		HnswLoadElement(element, &distance, q, index, support, true, NULL);
+		hc->distance = distance;
+
+		/* Prune element if being deleted */
+		if (element->heaptidsLength == 0)
+		{
+			*idx = i;
+			break;
+		}
+	}
+}
+
+/*
+ * Get update index
+ */
+static int
+GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int m, int lm, int lc, Relation index, HnswSupport * support, MemoryContext updateCtx)
+{
+	char	   *base = NULL;
+	int			idx = -1;
+	HnswNeighborArray *neighbors;
+	MemoryContext oldCtx = MemoryContextSwitchTo(updateCtx);
+
+	/*
+	 * Get latest neighbors since they may have changed. Do not lock yet since
+	 * selecting neighbors can take time. Could use optimistic locking to
+	 * retry if another update occurs before getting exclusive lock.
+	 */
+	neighbors = HnswLoadNeighbors(element, index, m, lm, lc);
+
+	/*
+	 * Could improve performance for vacuuming by checking neighbors against
+	 * list of elements being deleted to find index. It's important to exclude
+	 * already deleted elements for this since they can be replaced at any
+	 * time.
+	 */
+
+	if (neighbors->length < lm)
+		idx = -2;
+	else
+	{
+		HnswQuery	q;
+
+		q.value = HnswGetValue(base, element);
+
+		LoadElementsForInsert(neighbors, &q, &idx, index, support);
+
+		if (idx == -1)
+			HnswUpdateConnection(base, neighbors, newElement, distance, lm, &idx, index, support);
+	}
+
+	MemoryContextSwitchTo(oldCtx);
+	MemoryContextReset(updateCtx);
+
+	return idx;
+}
+
 /*
 * Check if connection already exists
 */
@@ -354,14 +455,94 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
 	return false;
 }

+/*
+ * Update neighbor
+ */
+static void
+UpdateNeighborOnDisk(HnswElement element, HnswElement newElement, int idx, int m, int lm, int lc, Relation index, bool checkExisting, bool building)
+{
+	Buffer		buf;
+	Page		page;
+	GenericXLogState *state;
+	HnswNeighborTuple ntup;
+	int			startIdx;
+	OffsetNumber offno = element->neighborOffno;
+
+	/* Register page */
+	buf = ReadBuffer(index, element->neighborPage);
+	LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
+	if (building)
+	{
+		state = NULL;
+		page = BufferGetPage(buf);
+	}
+	else
+	{
+		state = GenericXLogStart(index);
+		page = GenericXLogRegisterBuffer(state, buf, 0);
+	}
+
+	/* Get tuple */
+	ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, offno));
+
+	/* Calculate index for update */
+	startIdx = (element->level - lc) * m;
+
+	/* Check for existing connection */
+	if (checkExisting && ConnectionExists(newElement, ntup, startIdx, lm))
+		idx = -1;
+	else if (idx == -2)
+	{
+		/* Find free offset if still exists */
+		/* TODO Retry updating connections if not */
+		for (int j = 0; j < lm; j++)
+		{
+			if (!ItemPointerIsValid(&ntup->indextids[startIdx + j]))
+			{
+				idx = startIdx + j;
+				break;
+			}
+		}
+	}
+	else
+		idx += startIdx;
+
+	/* Make robust to issues */
+	if (idx >= 0 && idx < ntup->count)
+	{
+		ItemPointer indextid = &ntup->indextids[idx];
+
+		/* Update neighbor on the buffer */
+		ItemPointerSet(indextid, newElement->blkno, newElement->offno);
+
+		/* Commit */
+		if (building)
+			MarkBufferDirty(buf);
+		else
+			GenericXLogFinish(state);
+	}
+	else if (!building)
+		GenericXLogAbort(state);
+
+	UnlockReleaseBuffer(buf);
+}
+
 /*
 * Update neighbors
 */
 void
-HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building)
+HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building)
 {
 	char	   *base = NULL;

+	/* Use separate memory context to improve performance for larger vectors */
+	MemoryContext updateCtx = GenerationContextCreate(CurrentMemoryContext,
+													  "Hnsw insert update context",
+#if PG_VERSION_NUM >= 150000
+													  128 * 1024, 128 * 1024,
+#endif
+													  128 * 1024);
+
 	for (int lc = e->level; lc >= 0; lc--)
 	{
 		int			lm = HnswGetLayerM(m, lc);
@@ -370,96 +551,20 @@ HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, Hns
 		for (int i = 0; i < neighbors->length; i++)
 		{
 			HnswCandidate *hc = &neighbors->items[i];
-			Buffer		buf;
-			Page		page;
-			GenericXLogState *state;
-			HnswNeighborTuple ntup;
-			int			idx = -1;
-			int			startIdx;
 			HnswElement neighborElement = HnswPtrAccess(base, hc->element);
-			OffsetNumber offno = neighborElement->neighborOffno;
+			int			idx;

-			/*
-			 * Get latest neighbors since they may have changed. Do not lock
-			 * yet since selecting neighbors can take time. Could use
-			 * optimistic locking to retry if another update occurs before
-			 * getting exclusive lock.
-			 */
-			HnswLoadNeighbors(neighborElement, index, m);
-
-			/*
-			 * Could improve performance for vacuuming by checking neighbors
-			 * against list of elements being deleted to find index. It's
-			 * important to exclude already deleted elements for this since
-			 * they can be replaced at any time.
-			 */
-
-			/* Select neighbors */
-			HnswUpdateConnection(NULL, e, hc, lm, lc, &idx, index, procinfo, collation);
+			idx = GetUpdateIndex(neighborElement, e, hc->distance, m, lm, lc, index, support, updateCtx);

 			/* New element was not selected as a neighbor */
 			if (idx == -1)
 				continue;

-			/* Register page */
-			buf = ReadBuffer(index, neighborElement->neighborPage);
-			LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-			if (building)
-			{
-				state = NULL;
-				page = BufferGetPage(buf);
-			}
-			else
-			{
-				state = GenericXLogStart(index);
-				page = GenericXLogRegisterBuffer(state, buf, 0);
-			}
-
-			/* Get tuple */
-			ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, offno));
-
-			/* Calculate index for update */
-			startIdx = (neighborElement->level - lc) * m;
-
-			/* Check for existing connection */
-			if (checkExisting && ConnectionExists(e, ntup, startIdx, lm))
-				idx = -1;
-			else if (idx == -2)
-			{
-				/* Find free offset if still exists */
-				/* TODO Retry updating connections if not */
-				for (int j = 0; j < lm; j++)
-				{
-					if (!ItemPointerIsValid(&ntup->indextids[startIdx + j]))
-					{
-						idx = startIdx + j;
-						break;
-					}
-				}
-			}
-			else
-				idx += startIdx;
-
-			/* Make robust to issues */
-			if (idx >= 0 && idx < ntup->count)
-			{
-				ItemPointer indextid = &ntup->indextids[idx];
-
-				/* Update neighbor on the buffer */
-				ItemPointerSet(indextid, e->blkno, e->offno);
-
-				/* Commit */
-				if (building)
-					MarkBufferDirty(buf);
-				else
-					GenericXLogFinish(state);
-			}
-			else if (!building)
-				GenericXLogAbort(state);
-
-			UnlockReleaseBuffer(buf);
+			UpdateNeighborOnDisk(neighborElement, e, idx, m, lm, lc, index, checkExisting, building);
 		}
 	}
+
+	MemoryContextDelete(updateCtx);
 }

 /*
@@ -549,7 +654,7 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
 * Update graph on disk
 */
 static void
-UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
+UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;

@@ -565,7 +670,7 @@ UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement
 		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);

 	/* Update neighbors */
-	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, false, building);
+	HnswUpdateNeighborsOnDisk(index, support, element, m, false, building);

 	/* Update entry point if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -576,14 +681,12 @@ UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement
 * Insert a tuple into the index
 */
 bool
-HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building)
+HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building)
 {
 	HnswElement entryPoint;
 	HnswElement element;
 	int			m;
 	int			efConstruction = HnswGetEfConstruction(index);
-	FmgrInfo   *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-	Oid			collation = index->rd_indcollation[0];
 	LOCKMODE	lockmode = ShareLock;
 	char	   *base = NULL;

@@ -598,7 +701,7 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
 	HnswGetMetaPageInfo(index, &m, &entryPoint);

 	/* Create an element */
-	element = HnswInitElement(base, heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
+	element = HnswInitElement(base, heaptid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
 	HnswPtrStore(base, element->value, DatumGetPointer(value));

 	/* Prevent concurrent inserts when likely updating entry point */
@@ -616,10 +719,10 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
 	}

 	/* Find neighbors for element */
-	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false);
+	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false);

 	/* Update graph on disk */
-	UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
+	UpdateGraphOnDisk(index, support, element, m, efConstruction, entryPoint, building);

 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -631,31 +734,19 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
 * Insert a tuple into the index
 */
 static void
-HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid)
+HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid)
 {
 	Datum		value;
 	const		HnswTypeInfo *typeInfo = HnswGetTypeInfo(index);
-	FmgrInfo   *normprocinfo;
-	Oid			collation = index->rd_indcollation[0];
+	HnswSupport support;

-	/* Detoast once for all calls */
-	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
+	HnswInitSupport(&support, index);

-	/* Check value */
-	if (typeInfo->checkValue != NULL)
-		typeInfo->checkValue(DatumGetPointer(value));
+	/* Form index value */
+	if (!HnswFormIndexValue(&value, values, isnull, typeInfo, &support))
+		return;

-	/* Normalize if needed */
-	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	if (normprocinfo != NULL)
-	{
-		if (!HnswCheckNorm(normprocinfo, collation, value))
-			return;
-
-		value = HnswNormValue(typeInfo, collation, value);
-	}
-
-	HnswInsertTupleOnDisk(index, value, values, isnull, heap_tid, false);
+	HnswInsertTupleOnDisk(index, &support, value, heaptid, false);
 }

 /*
--- a/src/hnswscan.c
+++ b/src/hnswscan.c
@@ -11,17 +11,19 @@
 * Algorithm 5 from paper
 */
 static List *
-GetScanItems(IndexScanDesc scan, Datum q)
+GetScanItems(IndexScanDesc scan, Datum value)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 	Relation	index = scan->indexRelation;
-	FmgrInfo   *procinfo = so->procinfo;
-	Oid			collation = so->collation;
+	HnswSupport *support = &so->support;
 	List	   *ep;
 	List	   *w;
 	int			m;
 	HnswElement entryPoint;
 	char	   *base = NULL;
+	HnswQuery	q;
+
+	q.value = value;

 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
@@ -29,15 +31,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	if (entryPoint == NULL)
 		return NIL;

-	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, false));
+	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, procinfo, collation, m, false, NULL);
+		w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, false, NULL);
 		ep = w;
 	}

-	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
+	return HnswSearchLayer(base, &q, ep, hnsw_ef_search, 0, index, support, m, false, NULL);
 }

 /*
@@ -60,8 +62,8 @@ GetScanValue(IndexScanDesc scan)
 		Assert(!VARATT_IS_EXTENDED(DatumGetPointer(value)));

 		/* Normalize if needed */
-		if (so->normprocinfo != NULL)
-			value = HnswNormValue(so->typeInfo, so->collation, value);
+		if (so->support.normprocinfo != NULL)
+			value = HnswNormValue(so->typeInfo, so->support.collation, value);
 	}

 	return value;
@@ -86,9 +88,7 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 									   ALLOCSET_DEFAULT_SIZES);

 	/* Set support functions */
-	so->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-	so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	so->collation = index->rd_indcollation[0];
+	HnswInitSupport(&so->support, index);

 	scan->opaque = so;

@@ -168,8 +168,8 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 	while (list_length(so->w) > 0)
 	{
 		char	   *base = NULL;
-		HnswSearchCandidate *hc = llast(so->w);
-		HnswElement element = HnswPtrAccess(base, hc->element);
+		HnswSearchCandidate *sc = llast(so->w);
+		HnswElement element = HnswPtrAccess(base, sc->element);
 		ItemPointer heaptid;

 		/* Move to next element if no valid heap TIDs */
--- a/src/hnswutils.c
+++ b/src/hnswutils.c
@@ -100,19 +100,6 @@ hash_offset(Size offset)
 #define SH_DEFINE
 #include "lib/simplehash.h"

-typedef union
-{
-	pointerhash_hash *pointers;
-	offsethash_hash *offsets;
-	tidhash_hash *tids;
-}			visited_hash;
-
-typedef union
-{
-	HnswElement element;
-	ItemPointerData indextid;
-}			HnswUnvisited;
-
 /*
 * Get the max number of connections in an upper layer for each element in the index
 */
@@ -153,6 +140,17 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
 	return index_getprocinfo(index, 1, procnum);
 }

+/*
+ * Init support functions
+ */
+void
+HnswInitSupport(HnswSupport * support, Relation index)
+{
+	support->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+	support->collation = index->rd_indcollation[0];
+	support->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
+}
+
 /*
 * Normalize value
 */
@@ -166,9 +164,9 @@ HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value)
 * Check if non-zero norm
 */
 bool
-HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value)
+HnswCheckNorm(HnswSupport * support, Datum value)
 {
-	return DatumGetFloat8(FunctionCall1Coll(procinfo, collation, value)) > 0;
+	return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation, value)) > 0;
 }

 /*
@@ -197,7 +195,7 @@ HnswInitPage(Buffer buf, Page page)
 /*
 * Allocate a neighbor array
 */
-static HnswNeighborArray *
+HnswNeighborArray *
 HnswInitNeighborArray(int lm, HnswAllocator * allocator)
 {
 	HnswNeighborArray *a = HnswAlloc(allocator, HNSW_NEIGHBOR_ARRAY_SIZE(lm));
@@ -394,6 +392,33 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
 	UnlockReleaseBuffer(buf);
 }

+/*
+ * Form index value
+ */
+bool
+HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support)
+{
+	/* Detoast once for all calls */
+	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
+
+	/* Check value */
+	if (typeInfo->checkValue != NULL)
+		typeInfo->checkValue(DatumGetPointer(value));
+
+	/* Normalize if needed */
+	if (support->normprocinfo != NULL)
+	{
+		if (!HnswCheckNorm(support, value))
+			return false;
+
+		value = HnswNormValue(typeInfo, support->collation, value);
+	}
+
+	*out = value;
+
+	return true;
+}
+
 /*
 * Set element tuple, except for neighbor info
 */
@@ -449,69 +474,6 @@ HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
 	ntup->count = idx;
 }

-/*
- * Load neighbors from page
- */
-static void
-LoadNeighborsFromPage(HnswElement element, Relation index, Page page, int m)
-{
-	char	   *base = NULL;
-
-	HnswNeighborTuple ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
-	int			neighborCount = (element->level + 2) * m;
-
-	Assert(HnswIsNeighborTuple(ntup));
-
-	HnswInitNeighbors(base, element, m, NULL);
-
-	/* Ensure expected neighbors */
-	if (ntup->count != neighborCount)
-		return;
-
-	for (int i = 0; i < neighborCount; i++)
-	{
-		HnswElement e;
-		int			level;
-		HnswCandidate *hc;
-		ItemPointer indextid;
-		HnswNeighborArray *neighbors;
-
-		indextid = &ntup->indextids[i];
-
-		if (!ItemPointerIsValid(indextid))
-			continue;
-
-		e = HnswInitElementFromBlock(ItemPointerGetBlockNumber(indextid), ItemPointerGetOffsetNumber(indextid));
-
-		/* Calculate level based on offset */
-		level = element->level - i / m;
-		if (level < 0)
-			level = 0;
-
-		neighbors = HnswGetNeighbors(base, element, level);
-		hc = &neighbors->items[neighbors->length++];
-		HnswPtrStore(base, hc->element, e);
-	}
-}
-
-/*
- * Load neighbors
- */
-void
-HnswLoadNeighbors(HnswElement element, Relation index, int m)
-{
-	Buffer		buf;
-	Page		page;
-
-	buf = ReadBuffer(index, element->neighborPage);
-	LockBuffer(buf, BUFFER_LOCK_SHARE);
-	page = BufferGetPage(buf);
-
-	LoadNeighborsFromPage(element, index, page, m);
-
-	UnlockReleaseBuffer(buf);
-}
-
 /*
 * Load an element from a tuple
 */
@@ -545,11 +507,20 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
 	}
 }

+/*
+ * Calculate the distance between values
+ */
+static inline double
+HnswGetDistance(Datum a, Datum b, HnswSupport * support)
+{
+	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, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, float *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;
@@ -567,10 +538,10 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, float *distance, Datu
 	/* Calculate distance */
 	if (distance != NULL)
 	{
-		if (DatumGetPointer(*q) == NULL)
+		if (DatumGetPointer(q->value) == NULL)
 			*distance = 0;
 		else
-			*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->data)));
+			*distance = HnswGetDistance(q->value, PointerGetDatum(&etup->data), support);
 	}

 	/* Load element */
@@ -589,41 +560,39 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, float *distance, Datu
 * Load an element and optionally get its distance from q
 */
 void
-HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, float *maxDistance)
+HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
 {
-	HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, procinfo, collation, loadVec, maxDistance, &element);
+	HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, support, loadVec, maxDistance, &element);
 }

 /*
 * Get the distance for an element
 */
-static float
-GetElementDistance(char *base, HnswElement element, Datum q, FmgrInfo *procinfo, Oid collation)
+static double
+GetElementDistance(char *base, HnswElement element, HnswQuery * q, HnswSupport * support)
 {
 	Datum		value = HnswGetValue(base, element);

-	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, value));
+	return HnswGetDistance(q->value, value, support);
 }

 /*
 * Create a candidate for the entry point
 */
 HnswSearchCandidate *
-HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
+HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec)
 {
-	HnswSearchCandidate *hc = palloc(sizeof(HnswSearchCandidate));
+	HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
+	bool		inMemory = index == NULL;

-	HnswPtrStore(base, hc->element, entryPoint);
-	if (index == NULL)
-		hc->distance = GetElementDistance(base, entryPoint, q, procinfo, collation);
+	HnswPtrStore(base, sc->element, entryPoint);
+	if (inMemory)
+		sc->distance = GetElementDistance(base, entryPoint, q, support);
 	else
-		HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec, NULL);
-	return hc;
+		HnswLoadElement(entryPoint, &sc->distance, q, index, support, loadVec, NULL);
+	return sc;
 }

-#define HnswGetSearchCandidate(membername, ptr) pairingheap_container(HnswSearchCandidate, membername, ptr)
-#define HnswGetSearchCandidateConst(membername, ptr) pairingheap_const_container(HnswSearchCandidate, membername, ptr)
-
 /*
 * Compare candidate distances
 */
@@ -658,9 +627,9 @@ CompareFurthestCandidates(const pairingheap_node *a, const pairingheap_node *b,
 * Init visited
 */
 static inline void
-InitVisited(char *base, visited_hash * v, Relation index, int ef, int m)
+InitVisited(char *base, visited_hash * v, bool inMemory, int ef, int m)
 {
-	if (index != NULL)
+	if (!inMemory)
 		v->tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL);
 	else if (base != NULL)
 		v->offsets = offsethash_create(CurrentMemoryContext, ef * m * 2, NULL);
@@ -672,9 +641,9 @@ InitVisited(char *base, visited_hash * v, Relation index, int ef, int m)
 * Add to visited
 */
 static inline void
-AddToVisited(char *base, visited_hash * v, HnswElementPtr elementPtr, Relation index, bool *found)
+AddToVisited(char *base, visited_hash * v, HnswElementPtr elementPtr, bool inMemory, bool *found)
 {
-	if (index != NULL)
+	if (!inMemory)
 	{
 		HnswElement element = HnswPtrAccess(base, elementPtr);
 		ItemPointerData indextid;
@@ -735,7 +704,7 @@ HnswLoadUnvisitedFromMemory(char *base, HnswElement element, HnswUnvisited * unv
 		HnswCandidate *hc = &localNeighborhood->items[i];
 		bool		found;

-		AddToVisited(base, v, hc->element, NULL, &found);
+		AddToVisited(base, v, hc->element, true, &found);

 		if (!found)
 			unvisited[(*unvisitedLength)++].element = HnswPtrAccess(base, hc->element);
@@ -743,16 +712,15 @@ HnswLoadUnvisitedFromMemory(char *base, HnswElement element, HnswUnvisited * unv
 }

 /*
- * Load unvisited neighbors from disk
+ * Load neighbor index TIDs
 */
-static void
-HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *unvisitedLength, visited_hash * v, Relation index, int m, int lm, int lc)
+bool
+HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc)
 {
 	Buffer		buf;
 	Page		page;
 	HnswNeighborTuple ntup;
 	int			start;
-	ItemPointerData indextids[HNSW_MAX_M * 2];

 	buf = ReadBuffer(index, element->neighborPage);
 	LockBuffer(buf, BUFFER_LOCK_SHARE);
@@ -764,17 +732,30 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
 	if (ntup->count != (element->level + 2) * m)
 	{
 		UnlockReleaseBuffer(buf);
-		return;
+		return false;
 	}

 	/* Copy to minimize lock time */
 	start = (element->level - lc) * m;
-	memcpy(&indextids, ntup->indextids + start, lm * sizeof(ItemPointerData));
+	memcpy(indextids, ntup->indextids + start, lm * sizeof(ItemPointerData));

 	UnlockReleaseBuffer(buf);
+	return true;
+}
+
+/*
+ * Load unvisited neighbors from disk
+ */
+static void
+HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *unvisitedLength, visited_hash * v, Relation index, int m, int lm, int lc)
+{
+	ItemPointerData indextids[HNSW_MAX_M * 2];

 	*unvisitedLength = 0;

+	if (!HnswLoadNeighborTids(element, indextids, index, m, lm, lc))
+		return;
+
 	for (int i = 0; i < lm; i++)
 	{
 		ItemPointer indextid = &indextids[i];
@@ -794,7 +775,7 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
 * Algorithm 2 from paper
 */
 List *
-HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
+HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement)
 {
 	List	   *w = NIL;
 	pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
@@ -807,11 +788,12 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 	int			lm = HnswGetLayerM(m, lc);
 	HnswUnvisited *unvisited = palloc(lm * sizeof(HnswUnvisited));
 	int			unvisitedLength;
+	bool		inMemory = index == NULL;

-	InitVisited(base, &v, index, ef, m);
+	InitVisited(base, &v, inMemory, ef, m);

 	/* Create local memory for neighborhood if needed */
-	if (index == NULL)
+	if (inMemory)
 	{
 		neighborhoodSize = HNSW_NEIGHBOR_ARRAY_SIZE(lm);
 		localNeighborhood = palloc(neighborhoodSize);
@@ -820,20 +802,20 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 	/* Add entry points to v, C, and W */
 	foreach(lc2, ep)
 	{
-		HnswSearchCandidate *hc = (HnswSearchCandidate *) lfirst(lc2);
+		HnswSearchCandidate *sc = (HnswSearchCandidate *) lfirst(lc2);
 		bool		found;

-		AddToVisited(base, &v, hc->element, index, &found);
+		AddToVisited(base, &v, sc->element, inMemory, &found);

-		pairingheap_add(C, &hc->c_node);
-		pairingheap_add(W, &hc->w_node);
+		pairingheap_add(C, &sc->c_node);
+		pairingheap_add(W, &sc->w_node);

 		/*
 		 * Do not count elements being deleted towards ef when vacuuming. It
 		 * would be ideal to do this for inserts as well, but this could
 		 * affect insert performance.
 		 */
-		if (CountElement(skipElement, HnswPtrAccess(base, hc->element)))
+		if (CountElement(skipElement, HnswPtrAccess(base, sc->element)))
 			wlen++;
 	}

@@ -848,7 +830,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F

 		cElement = HnswPtrAccess(base, c->element);

-		if (index == NULL)
+		if (inMemory)
 			HnswLoadUnvisitedFromMemory(base, cElement, unvisited, &unvisitedLength, &v, lc, localNeighborhood, neighborhoodSize);
 		else
 			HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, &v, index, m, lm, lc);
@@ -857,15 +839,15 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 		{
 			HnswElement eElement;
 			HnswSearchCandidate *e;
-			float		eDistance;
+			double		eDistance;
 			bool		alwaysAdd = wlen < ef;

 			f = HnswGetSearchCandidate(w_node, pairingheap_first(W));

-			if (index == NULL)
+			if (inMemory)
 			{
 				eElement = unvisited[i].element;
-				eDistance = GetElementDistance(base, eElement, q, procinfo, collation);
+				eDistance = GetElementDistance(base, eElement, q, support);
 			}
 			else
 			{
@@ -875,7 +857,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F

 				/* Avoid any allocations if not adding */
 				eElement = NULL;
-				HnswLoadElementImpl(blkno, offno, &eDistance, &q, index, procinfo, collation, inserting, alwaysAdd ? NULL : &f->distance, &eElement);
+				HnswLoadElementImpl(blkno, offno, &eDistance, q, index, support, inserting, alwaysAdd ? NULL : &f->distance, &eElement);

 				if (eElement == NULL)
 					continue;
@@ -916,9 +898,9 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 	/* Add each element of W to w */
 	while (!pairingheap_is_empty(W))
 	{
-		HnswSearchCandidate *hc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
+		HnswSearchCandidate *sc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));

-		w = lappend(w, hc);
+		w = lappend(w, sc);
 	}

 	return w;
@@ -972,32 +954,22 @@ CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
 	return 0;
 }

-/*
- * Calculate the distance between elements
- */
-static float
-HnswGetDistance(char *base, HnswElement a, HnswElement b, FmgrInfo *procinfo, Oid collation)
-{
-	Datum		aValue = HnswGetValue(base, a);
-	Datum		bValue = HnswGetValue(base, b);
-
-	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, aValue, bValue));
-}
-
 /*
 * Check if an element is closer to q than any element from R
 */
 static bool
-CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, Oid collation)
+CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support)
 {
 	HnswElement eElement = HnswPtrAccess(base, e->element);
+	Datum		eValue = HnswGetValue(base, eElement);
 	ListCell   *lc2;

 	foreach(lc2, r)
 	{
 		HnswCandidate *ri = lfirst(lc2);
 		HnswElement riElement = HnswPtrAccess(base, ri->element);
-		float		distance = HnswGetDistance(base, eElement, riElement, procinfo, collation);
+		Datum		riValue = HnswGetValue(base, riElement);
+		float		distance = HnswGetDistance(eValue, riValue, support);

 		if (distance <= e->distance)
 			return false;
@@ -1010,15 +982,14 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, O
 * Algorithm 4 from paper
 */
 static List *
-SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, 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);
 	HnswCandidate **wd;
 	int			wdlen = 0;
 	int			wdoff = 0;
-	HnswNeighborArray *neighbors = HnswGetNeighbors(base, e2, lc);
-	bool		mustCalculate = !neighbors->closerSet;
+	bool		mustCalculate = !(*closerSet);
 	List	   *added = NIL;
 	bool		removedAny = false;

@@ -1045,7 +1016,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col

 		/* Use previous state of r and wd to skip work when possible */
 		if (mustCalculate)
-			e->closer = CheckElementCloser(base, e, r, procinfo, collation);
+			e->closer = CheckElementCloser(base, e, r, support);
 		else if (list_length(added) > 0)
 		{
 			/* Keep Valgrind happy for in-memory, parallel builds */
@@ -1058,7 +1029,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
 			 */
 			if (e->closer)
 			{
-				e->closer = CheckElementCloser(base, e, added, procinfo, collation);
+				e->closer = CheckElementCloser(base, e, added, support);

 				if (!e->closer)
 					removedAny = true;
@@ -1071,7 +1042,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
 				 */
 				if (removedAny)
 				{
-					e->closer = CheckElementCloser(base, e, r, procinfo, collation);
+					e->closer = CheckElementCloser(base, e, r, support);
 					if (e->closer)
 						added = lappend(added, e);
 				}
@@ -1079,7 +1050,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
 		}
 		else if (e == newCandidate)
 		{
-			e->closer = CheckElementCloser(base, e, r, procinfo, collation);
+			e->closer = CheckElementCloser(base, e, r, support);
 			if (e->closer)
 				added = lappend(added, e);
 		}
@@ -1095,7 +1066,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
 	}

 	/* Cached value can only be used in future if sorted deterministically */
-	neighbors->closerSet = sortCandidates;
+	*closerSet = sortCandidates;

 	/* Keep pruned connections */
 	while (wdoff < wdlen && list_length(r) < lm)
@@ -1130,18 +1101,16 @@ AddConnections(char *base, HnswElement element, List *neighbors, int lc)
 * Update connections
 */
 void
-HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation)
+HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support)
 {
-	HnswElement hce = HnswPtrAccess(base, hc->element);
-	HnswNeighborArray *currentNeighbors = HnswGetNeighbors(base, hce, lc);
-	HnswCandidate hc2;
+	HnswCandidate newHc;

-	HnswPtrStore(base, hc2.element, element);
-	hc2.distance = hc->distance;
+	HnswPtrStore(base, newHc.element, newElement);
+	newHc.distance = distance;

-	if (currentNeighbors->length < lm)
+	if (neighbors->length < lm)
 	{
-		currentNeighbors->items[currentNeighbors->length++] = hc2;
+		neighbors->items[neighbors->length++] = newHc;

 		/* Track update */
 		if (updateIdx != NULL)
@@ -1150,54 +1119,26 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm
 	else
 	{
 		/* Shrink connections */
+		List	   *c = NIL;
 		HnswCandidate *pruned = NULL;

-		/* Load elements on insert */
-		if (index != NULL)
-		{
-			Datum		q = HnswGetValue(base, hce);
+		/* Add candidates */
+		for (int i = 0; i < neighbors->length; i++)
+			c = lappend(c, &neighbors->items[i]);
+		c = lappend(c, &newHc);

-			for (int i = 0; i < currentNeighbors->length; i++)
-			{
-				HnswCandidate *hc3 = &currentNeighbors->items[i];
-				HnswElement hc3Element = HnswPtrAccess(base, hc3->element);
-
-				if (HnswPtrIsNull(base, hc3Element->value))
-					HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true, NULL);
-				else
-					hc3->distance = GetElementDistance(base, hc3Element, q, procinfo, collation);
-
-				/* Prune element if being deleted */
-				if (hc3Element->heaptidsLength == 0)
-				{
-					pruned = &currentNeighbors->items[i];
-					break;
-				}
-			}
-		}
+		SelectNeighbors(base, c, lm, support, &neighbors->closerSet, &newHc, &pruned, true);

+		/* Should not happen */
 		if (pruned == NULL)
-		{
-			List	   *c = NIL;
-
-			/* Add candidates */
-			for (int i = 0; i < currentNeighbors->length; i++)
-				c = lappend(c, &currentNeighbors->items[i]);
-			c = lappend(c, &hc2);
-
-			SelectNeighbors(base, c, lm, lc, procinfo, collation, hce, &hc2, &pruned, true);
-
-			/* Should not happen */
-			if (pruned == NULL)
-				return;
-		}
+			return;

 		/* Find and replace the pruned element */
-		for (int i = 0; i < currentNeighbors->length; i++)
+		for (int i = 0; i < neighbors->length; i++)
 		{
-			if (HnswPtrEqual(base, currentNeighbors->items[i].element, pruned->element))
+			if (HnswPtrEqual(base, neighbors->items[i].element, pruned->element))
 			{
-				currentNeighbors->items[i] = hc2;
+				neighbors->items[i] = newHc;

 				/* Track update */
 				if (updateIdx != NULL)
@@ -1257,17 +1198,20 @@ PrecomputeHash(char *base, HnswElement element)
 * Algorithm 1 from paper
 */
 void
-HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing)
+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;
-	Datum		q = HnswGetValue(base, element);
+	HnswQuery	q;
 	HnswElement skipElement = existing ? element : NULL;
+	bool		inMemory = index == NULL;
+
+	q.value = HnswGetValue(base, element);

 	/* Precompute hash */
-	if (index == NULL)
+	if (inMemory)
 		PrecomputeHash(base, element);

 	/* No neighbors if no entry point */
@@ -1275,13 +1219,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		return;

 	/* Get entry point and level */
-	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, true));
+	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, procinfo, collation, m, true, skipElement);
+		w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement);
 		ep = w;
 	}

@@ -1300,7 +1244,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		List	   *lw = NIL;
 		ListCell   *lc2;

-		w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
+		w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement);

 		/* Convert search candidates to candidates */
 		foreach(lc2, w)
@@ -1316,7 +1260,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint

 		/* Elements being deleted or skipped can help with search */
 		/* but should be removed before selecting neighbors */
-		if (index != NULL)
+		if (!inMemory)
 			lw = RemoveElements(base, lw, skipElement);

 		/*
@@ -1324,7 +1268,7 @@ 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, lc, procinfo, collation, element, NULL, NULL, false);
+		neighbors = SelectNeighbors(base, lw, lm, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);

 		AddConnections(base, element, neighbors, lc);

--- a/src/hnswvacuum.c
+++ b/src/hnswvacuum.c
@@ -184,13 +184,12 @@ static void
 RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswElement entryPoint)
 {
 	Relation	index = vacuumstate->index;
+	HnswSupport *support = &vacuumstate->support;
 	Buffer		buf;
 	Page		page;
 	GenericXLogState *state;
 	int			m = vacuumstate->m;
 	int			efConstruction = vacuumstate->efConstruction;
-	FmgrInfo   *procinfo = vacuumstate->procinfo;
-	Oid			collation = vacuumstate->collation;
 	BufferAccessStrategy bas = vacuumstate->bas;
 	HnswNeighborTuple ntup = vacuumstate->ntup;
 	Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
@@ -205,7 +204,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	element->heaptidsLength = 0;

 	/* Find neighbors for element, skipping itself */
-	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, true);
+	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true);

 	/* Zero memory for each element */
 	MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
@@ -229,7 +228,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);

 	/* Update neighbors */
-	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, true, false);
+	HnswUpdateNeighborsOnDisk(index, support, element, m, true, false);
 }

 /*
@@ -239,6 +238,7 @@ static void
 RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 {
 	Relation	index = vacuumstate->index;
+	HnswSupport *support = &vacuumstate->support;
 	HnswElement highestPoint = &vacuumstate->highestPoint;
 	HnswElement entryPoint;
 	MemoryContext oldCtx = MemoryContextSwitchTo(vacuumstate->tmpCtx);
@@ -256,7 +256,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 		LockPage(index, HNSW_UPDATE_LOCK, ShareLock);

 		/* Load element */
-		HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL);
+		HnswLoadElement(highestPoint, NULL, NULL, index, support, true, NULL);

 		/* Repair if needed */
 		if (NeedsUpdated(vacuumstate, highestPoint))
@@ -294,7 +294,7 @@ 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, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL);
+			HnswLoadElement(entryPoint, NULL, NULL, index, support, true, NULL);

 			if (NeedsUpdated(vacuumstate, entryPoint))
 			{
@@ -573,13 +573,13 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	vacuumstate->callback_state = callback_state;
 	vacuumstate->efConstruction = HnswGetEfConstruction(index);
 	vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
-	vacuumstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-	vacuumstate->collation = index->rd_indcollation[0];
 	vacuumstate->ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
 	vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
 												"Hnsw vacuum temporary context",
 												ALLOCSET_DEFAULT_SIZES);

+	HnswInitSupport(&vacuumstate->support, index);
+
 	/* Get m from metapage */
 	HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);

--- a/src/ivfbuild.c
+++ b/src/ivfbuild.c
@@ -138,7 +138,7 @@ SampleRows(IvfflatBuildState * buildstate)
 * Add tuple to sort
 */
 static void
-AddTupleToSort(Relation index, ItemPointer tid, Datum *values, IvfflatBuildState * buildstate)
+AddTupleToSort(Relation index, ItemPointer tid, Datum *values, bool *isnull, IvfflatBuildState * buildstate)
 {
 	double		distance;
 	double		minDistance = DBL_MAX;
@@ -184,6 +184,11 @@ AddTupleToSort(Relation index, ItemPointer tid, Datum *values, IvfflatBuildState
 	slot->tts_isnull[1] = false;
 	slot->tts_values[2] = value;
 	slot->tts_isnull[2] = false;
+	for (int i = 1; i < buildstate->tupdesc->natts; i++)
+	{
+		slot->tts_values[2 + i] = values[i];
+		slot->tts_isnull[2 + i] = isnull[i];
+	}
 	ExecStoreVirtualTuple(slot);

 	/*
@@ -215,7 +220,7 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
 	oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);

 	/* Add tuple to sort */
-	AddTupleToSort(index, tid, values, buildstate);
+	AddTupleToSort(index, tid, values, isnull, buildstate);

 	/* Reset memory context */
 	MemoryContextSwitchTo(oldCtx);
@@ -226,19 +231,20 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
 * Get index tuple from sort state
 */
 static inline void
-GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, IndexTuple *itup, int *list)
+GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, Datum *values, bool *isnull, IndexTuple *itup, int *list)
 {
-	Datum		value;
-	bool		isnull;
-
 	if (tuplesort_gettupleslot(sortstate, true, false, slot, NULL))
 	{
-		*list = DatumGetInt32(slot_getattr(slot, 1, &isnull));
-		value = slot_getattr(slot, 3, &isnull);
+		bool		unused;
+
+		*list = DatumGetInt32(slot_getattr(slot, 1, &unused));
+
+		for (int i = 0; i < tupdesc->natts; i++)
+			values[i] = slot_getattr(slot, 3 + i, &isnull[i]);

 		/* Form the index tuple */
-		*itup = index_form_tuple(tupdesc, &value, &isnull);
-		(*itup)->t_tid = *((ItemPointer) DatumGetPointer(slot_getattr(slot, 2, &isnull)));
+		*itup = index_form_tuple(tupdesc, values, isnull);
+		(*itup)->t_tid = *((ItemPointer) DatumGetPointer(slot_getattr(slot, 2, &unused)));
 	}
 	else
 		*list = -1;
@@ -254,14 +260,16 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 	IndexTuple	itup = NULL;	/* silence compiler warning */
 	int64		inserted = 0;

-	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsMinimalTuple);
-	TupleDesc	tupdesc = RelationGetDescr(index);
+	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsMinimalTuple);
+	TupleDesc	tupdesc = buildstate->tupdesc;
+	Datum	   *values = palloc(tupdesc->natts * sizeof(Datum));
+	bool	   *isnull = palloc(tupdesc->natts * sizeof(bool));

 	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);

 	pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_TOTAL, buildstate->indtuples);

-	GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
+	GetNextTuple(buildstate->sortstate, tupdesc, slot, values, isnull, &itup, &list);

 	for (int i = 0; i < buildstate->centers->length; i++)
 	{
@@ -297,7 +305,7 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)

 			pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE, ++inserted);

-			GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
+			GetNextTuple(buildstate->sortstate, tupdesc, slot, values, isnull, &itup, &list);
 		}

 		insertPage = BufferGetBlockNumber(buf);
@@ -307,6 +315,9 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 		/* Set the start and insert pages */
 		IvfflatUpdateList(index, buildstate->listInfo[i], insertPage, InvalidBlockNumber, startPage, forkNum);
 	}
+
+	pfree(values);
+	pfree(isnull);
 }

 /*
@@ -319,6 +330,7 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 	buildstate->index = index;
 	buildstate->indexInfo = indexInfo;
 	buildstate->typeInfo = IvfflatGetTypeInfo(index);
+	buildstate->tupdesc = RelationGetDescr(index);

 	buildstate->lists = IvfflatGetLists(index);
 	buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
@@ -329,6 +341,19 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 				 errmsg("type not supported for ivfflat index")));

+	/* TODO See if needed */
+	if (IndexRelationGetNumberOfKeyAttributes(index) > 3)
+		elog(ERROR, "index cannot have more than three columns");
+
+	if (!OidIsValid(index_getprocid(index, 1, IVFFLAT_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, IVFFLAT_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,
@@ -356,12 +381,13 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 				 errmsg("dimensions must be greater than one for this opclass")));

 	/* Create tuple description for sorting */
-	buildstate->tupdesc = CreateTemplateTupleDesc(3);
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 3, "vector", RelationGetDescr(index)->attrs[0].atttypid, -1, 0);
+	buildstate->sortdesc = CreateTemplateTupleDesc(2 + buildstate->tupdesc->natts);
+	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
+	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
+	for (int i = 0; i < buildstate->tupdesc->natts; i++)
+		TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) (3 + i), NULL, buildstate->tupdesc->attrs[i].atttypid, -1, 0);

-	buildstate->slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsVirtual);
+	buildstate->slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsVirtual);

 	buildstate->centers = VectorArrayInit(buildstate->lists, buildstate->dimensions, buildstate->typeInfo->itemSize(buildstate->dimensions));
 	buildstate->listInfo = palloc(sizeof(ListInfo) * buildstate->lists);
@@ -633,7 +659,7 @@ IvfflatParallelScanAndSort(IvfflatSpool * ivfspool, IvfflatShared * ivfshared, S
 	InitBuildState(&buildstate, ivfspool->heap, ivfspool->index, indexInfo);
 	memcpy(buildstate.centers->items, ivfcenters, buildstate.centers->itemsize * buildstate.centers->maxlen);
 	buildstate.centers->length = buildstate.centers->maxlen;
-	ivfspool->sortstate = InitBuildSortState(buildstate.tupdesc, sortmem, coordinate);
+	ivfspool->sortstate = InitBuildSortState(buildstate.sortdesc, sortmem, coordinate);
 	buildstate.sortstate = ivfspool->sortstate;
 	scan = table_beginscan_parallel(ivfspool->heap,
 									ParallelTableScanFromIvfflatShared(ivfshared));
@@ -950,7 +976,7 @@ AssignTuples(IvfflatBuildState * buildstate)
 	}

 	/* Begin serial/leader tuplesort */
-	buildstate->sortstate = InitBuildSortState(buildstate->tupdesc, maintenance_work_mem, coordinate);
+	buildstate->sortstate = InitBuildSortState(buildstate->sortdesc, maintenance_work_mem, coordinate);

 	/* Add tuples to sort */
 	if (buildstate->heap != NULL)
--- a/src/ivfflat.c
+++ b/src/ivfflat.c
@@ -69,6 +69,8 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	GenericCosts costs;
 	int			lists;
 	double		ratio;
+	double		sequentialRatio = 0.5;
+	double		startupPages;
 	double		spc_seq_page_cost;
 	Relation	index;

@@ -96,25 +98,23 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	if (ratio > 1.0)
 		ratio = 1.0;

-	/* Set startup cost since most work happens before first tuple is returned */
-	costs.indexStartupCost = costs.indexTotalCost * ratio;
-	costs.numIndexPages *= ratio;
-
 	get_tablespace_page_costs(path->indexinfo->reltablespace, NULL, &spc_seq_page_cost);

+	/* Change some page cost from random to sequential */
+	costs.indexTotalCost -= sequentialRatio * costs.numIndexPages * (costs.spc_random_page_cost - spc_seq_page_cost);
+
+	/* Startup cost is cost before returning the first row */
+	costs.indexStartupCost = costs.indexTotalCost * ratio;
+
 	/* Adjust cost if needed since TOAST not included in seq scan cost */
-	if (costs.numIndexPages > path->indexinfo->rel->pages && ratio < 0.5)
+	startupPages = costs.numIndexPages * ratio;
+	if (startupPages > path->indexinfo->rel->pages && ratio < 0.5)
 	{
-		/* Change all page cost from random to sequential */
-		costs.indexStartupCost -= costs.numIndexPages * (costs.spc_random_page_cost - spc_seq_page_cost);
+		/* Change rest of page cost from random to sequential */
+		costs.indexStartupCost -= (1 - sequentialRatio) * startupPages * (costs.spc_random_page_cost - spc_seq_page_cost);

 		/* Remove cost of extra pages */
-		costs.indexStartupCost -= (costs.numIndexPages - path->indexinfo->rel->pages) * spc_seq_page_cost;
-	}
-	else
-	{
-		/* Change some page cost from random to sequential */
-		costs.indexStartupCost -= 0.5 * costs.numIndexPages * (costs.spc_random_page_cost - spc_seq_page_cost);
+		costs.indexStartupCost -= (startupPages - path->indexinfo->rel->pages) * spc_seq_page_cost;
 	}

 	*indexStartupCost = costs.indexStartupCost;
@@ -122,9 +122,6 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	*indexSelectivity = costs.indexSelectivity;
 	*indexCorrelation = costs.indexCorrelation;
 	*indexPages = costs.numIndexPages;
-
-	Assert(*indexStartupCost > 0);
-	Assert(*indexTotalCost > 0);
 }

 /*
@@ -170,7 +167,7 @@ ivfflathandler(PG_FUNCTION_ARGS)
 	amroutine->amcanorderbyop = true;
 	amroutine->amcanbackward = false;	/* can change direction mid-scan */
 	amroutine->amcanunique = false;
-	amroutine->amcanmulticol = false;
+	amroutine->amcanmulticol = true;
 	amroutine->amoptionalkey = true;
 	amroutine->amsearcharray = false;
 	amroutine->amsearchnulls = false;
--- a/src/ivfflat.h
+++ b/src/ivfflat.h
@@ -165,6 +165,7 @@ typedef struct IvfflatBuildState
 	Relation	index;
 	IndexInfo  *indexInfo;
 	const		IvfflatTypeInfo *typeInfo;
+	TupleDesc	tupdesc;

 	/* Settings */
 	int			dimensions;
@@ -198,7 +199,7 @@ typedef struct IvfflatBuildState

 	/* Sorting */
 	Tuplesortstate *sortstate;
-	TupleDesc	tupdesc;
+	TupleDesc	sortdesc;
 	TupleTableSlot *slot;

 	/* Memory */
--- a/src/ivfinsert.c
+++ b/src/ivfinsert.c
@@ -78,6 +78,8 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
 	BlockNumber insertPage = InvalidBlockNumber;
 	ListInfo	listInfo;
 	BlockNumber originalInsertPage;
+	TupleDesc	tupdesc = RelationGetDescr(index);
+	Datum	   *newValues = palloc(tupdesc->natts * sizeof(Datum));

 	/* Detoast once for all calls */
 	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -98,12 +100,16 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
 	IvfflatGetMetaPageInfo(index, NULL, NULL);

 	/* Find the insert page - sets the page and list info */
-	FindInsertPage(index, values, &insertPage, &listInfo);
+	FindInsertPage(index, &value, &insertPage, &listInfo);
 	Assert(BlockNumberIsValid(insertPage));
 	originalInsertPage = insertPage;

+	newValues[0] = value;
+	for (int i = 1; i < tupdesc->natts; i++)
+		newValues[i] = values[i];
+
 	/* Form tuple */
-	itup = index_form_tuple(RelationGetDescr(index), &value, isnull);
+	itup = index_form_tuple(tupdesc, newValues, isnull);
 	itup->t_tid = *heap_tid;

 	/* Get tuple size */
--- a/src/ivfscan.c
+++ b/src/ivfscan.c
@@ -104,6 +104,34 @@ GetScanLists(IndexScanDesc scan, Datum value)
 	}
 }

+/*
+ * Check if matches scan keys
+ */
+static bool
+MatchesScanKeys(IndexScanDesc scan, IndexTuple itup, TupleDesc tupdesc)
+{
+	for (int i = 0; i < scan->numberOfKeys; i++)
+	{
+		ScanKey		key = &scan->keyData[i];
+		bool		attnull = key->sk_flags & SK_ISNULL;
+		bool		isnull;
+		Datum		value = index_getattr(itup, key->sk_attno, tupdesc, &isnull);
+
+		if (isnull || attnull)
+		{
+			if (isnull != attnull)
+				return false;
+		}
+		else
+		{
+			if (!DatumGetBool(FunctionCall2Coll(&key->sk_func, key->sk_collation, value, key->sk_argument)))
+				return false;
+		}
+	}
+
+	return true;
+}
+
 /*
 * Get items
 */
@@ -140,6 +168,10 @@ GetScanItems(IndexScanDesc scan, Datum value)
 				ItemId		itemid = PageGetItemId(page, offno);

 				itup = (IndexTuple) PageGetItem(page, itemid);
+
+				if (!MatchesScanKeys(scan, itup, tupdesc))
+					continue;
+
 				datum = index_getattr(itup, 1, tupdesc, &isnull);

 				/*
--- a/test/t/002_ivfflat_vacuum.pl
+++ b/test/t/002_ivfflat_vacuum.pl
@@ -6,13 +6,7 @@ use Test::More;

 my $dim = 3;

-my @r = ();
-for (1 .. $dim)
-{
-	my $v = int(rand(1000)) + 1;
-	push(@r, "i % $v");
-}
-my $array_sql = join(", ", @r);
+my $array_sql = join(",", ('random()') x $dim);

 # Initialize node
 my $node = PostgreSQL::Test::Cluster->new('node');
@@ -23,19 +17,20 @@ $node->start;
 $node->safe_psql("postgres", "CREATE EXTENSION vector;");
 $node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
 $node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
 );
 $node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");

 # Get size
 my $size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");

+# Store values
+$node->safe_psql("postgres", "CREATE TABLE tmp AS SELECT * FROM tst;");
+
 # Delete all, vacuum, and insert same data
 $node->safe_psql("postgres", "DELETE FROM tst;");
 $node->safe_psql("postgres", "VACUUM tst;");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
-);
+$node->safe_psql("postgres", "INSERT INTO tst SELECT * FROM tmp;");

 # Check size
 my $new_size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");
--- a/test/t/017_hnsw_filtering.pl
+++ b/test/t/017_hnsw_filtering.pl
@@ -41,8 +41,7 @@ my $c = int(rand() * $nc);
 my $explain = $node->safe_psql("postgres", qq(
 	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
 ));
-# TODO Do not use index
-like($explain, qr/Index Scan using idx/);
+like($explain, qr/Seq Scan/);

 # Test attribute filtering with few rows removed
 $explain = $node->safe_psql("postgres", qq(
@@ -60,8 +59,7 @@ like($explain, qr/Index Scan using idx/);
 $explain = $node->safe_psql("postgres", qq(
 	EXPLAIN ANALYZE SELECT i FROM tst WHERE c < 1 ORDER BY v <-> '$query' LIMIT $limit;
 ));
-# TODO Do not use index
-like($explain, qr/Index Scan using idx/);
+like($explain, qr/Seq Scan/);

 # Test attribute filtering with few rows removed like
 $explain = $node->safe_psql("postgres", qq(
--- a/test/t/039_hnsw_cost.pl
+++ b/test/t/039_hnsw_cost.pl
@@ -17,12 +17,11 @@ $node->safe_psql("postgres", "CREATE EXTENSION vector;");
 for my $dim (@dims)
 {
 	my $array_sql = join(",", ('random()') x $dim);
-	my $n = $dim == 384 ? 3000 : 1000;

 	# Create table and index
 	$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
 	$node->safe_psql("postgres",
-		"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, $n) i;"
+		"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 2000) i;"
 	);
 	$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
 	$node->safe_psql("postgres", "ANALYZE tst;");
@@ -40,6 +39,16 @@ for my $dim (@dims)
 	));
 	like($explain, qr/Index Scan using idx/);

+	# 3x the rows are needed for distance filters
+	# since the planner uses DEFAULT_INEQ_SEL for the selectivity (should be 1)
+	# Recreate index for performance
+	$node->safe_psql("postgres", "DROP INDEX idx;");
+	$node->safe_psql("postgres",
+		"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(2001, 6000) i;"
+	);
+	$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
+	$node->safe_psql("postgres", "ANALYZE tst;");
+
 	$explain = $node->safe_psql("postgres", qq(
 		EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query' LIMIT $limit;
 	));
--- a/test/t/040_ivfflat_cost.pl
+++ b/test/t/040_ivfflat_cost.pl
@@ -21,7 +21,7 @@ for my $dim (@dims)
 	# Create table and index
 	$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
 	$node->safe_psql("postgres",
-		"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 6000) i;"
+		"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 5000) i;"
 	);
 	$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING ivfflat (v vector_l2_ops) WITH (lists = 5);");
 	$node->safe_psql("postgres", "ANALYZE tst;");
--- a/test/t/041_ivfflat_inline_filtering.pl
+++ b/test/t/041_ivfflat_inline_filtering.pl
@@ -0,0 +1,197 @@
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+my $node;
+my @queries = ();
+my @where = ();
+my @expected;
+my $limit = 20;
+my $dim = 3;
+my $array_sql = join(",", ('random()') x $dim);
+my $nc = 100;
+my $nc2 = 10;
+
+sub test_recall
+{
+	my ($probes, $min, $operator) = @_;
+	my $correct = 0;
+	my $total = 0;
+
+	for my $j (0 .. 2)
+	{
+		my $explain = $node->safe_psql("postgres", qq(
+			SET enable_seqscan = off;
+			SET ivfflat.probes = $probes;
+			EXPLAIN ANALYZE SELECT i FROM tst WHERE $where[$j] ORDER BY v $operator '$queries[$j]' LIMIT $limit;
+		));
+		like($explain, qr/Index Cond/);
+	}
+
+	for my $i (0 .. $#queries)
+	{
+		my $actual = $node->safe_psql("postgres", qq(
+			SET enable_seqscan = off;
+			SET ivfflat.probes = $probes;
+			SELECT i FROM tst WHERE $where[$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($dim), c int4, c2 int4);");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc, i % $nc2 FROM generate_series(1, 50000) i;"
+);
+
+# Generate queries
+for my $i (1 .. 100)
+{
+	my @r = ();
+	for (1 .. $dim)
+	{
+		push(@r, rand());
+	}
+	push(@queries, "[" . join(",", @r) . "]");
+
+	if ($i % 3 == 0)
+	{
+		my $c = int(rand() * $nc);
+		push(@where, "c = $c");
+	}
+	elsif ($i % 3 == 1)
+	{
+		my $c2 = int(rand() * $nc2);
+		push(@where, "c2 = $c2");
+	}
+	else
+	{
+		# use c2 to ensure results
+		my $c2 = int(rand() * $nc2);
+		push(@where, "c = $c2 AND c2 = $c2");
+	}
+}
+
+# Add index
+$node->safe_psql("postgres", qq(
+	CREATE INDEX ON tst USING ivfflat (v vector_l2_ops, c, c2) WITH (lists = 100);
+));
+
+# Insert more rows
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc, i % $nc2 FROM generate_series(1, 50000) i;"
+);
+
+# Get exact results
+@expected = ();
+for my $i (0 .. $#queries)
+{
+	my $res = $node->safe_psql("postgres", qq(
+		SET enable_indexscan = off;
+		SELECT i FROM tst WHERE $where[$i] ORDER BY v <-> '$queries[$i]' LIMIT $limit;
+	));
+	push(@expected, $res);
+}
+
+# Test recall
+test_recall(10, 0.99, '<->');
+
+# Test vacuum
+$node->safe_psql("postgres", "DELETE FROM tst WHERE c > 5;");
+$node->safe_psql("postgres", "VACUUM tst;");
+
+# Test less than
+my $explain = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c < 10 ORDER BY v <-> '$queries[0]' LIMIT $limit;
+));
+like($explain, qr/Index Cond: \(c < 10\)/);
+
+# Test less than or equal
+$explain = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c <= 10 ORDER BY v <-> '$queries[0]' LIMIT $limit;
+));
+like($explain, qr/Index Cond: \(c <= 10\)/);
+
+# Test greater than or equal
+$explain = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c >= 90 ORDER BY v <-> '$queries[0]' LIMIT $limit;
+));
+like($explain, qr/Index Cond: \(c >= 90\)/);
+
+# Test greater than
+$explain = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c > 90 ORDER BY v <-> '$queries[0]' LIMIT $limit;
+));
+like($explain, qr/Index Cond: \(c > 90\)/);
+
+# Test multiple attribute columns
+$explain = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = 1 AND c2 = 1 ORDER BY v <-> '$queries[0]' LIMIT $limit;
+));
+like($explain, qr/Index Cond: \(\(c = 1\) AND \(c2 = 1\)\)/);
+
+# Test only last attribute column
+$explain = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c2 = 1 ORDER BY v <-> '$queries[0]' LIMIT $limit;
+));
+like($explain, qr/Index Cond: \(c2 = 1\)/);
+
+# Test only vector column
+$explain = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v <-> '$queries[0]' LIMIT $limit;
+));
+like($explain, qr/Index Scan/);
+
+# Test only attribute columns
+$explain = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = 1;
+));
+like($explain, qr/Seq Scan/);
+
+# Test columns
+my ($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING ivfflat (c);");
+like($stderr, qr/first column must be a vector/);
+
+($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING ivfflat (c, v vector_cosine_ops);");
+like($stderr, qr/first column must be a vector/);
+
+($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_cosine_ops, c, c, c);");
+like($stderr, qr/index cannot have more than three columns/);
+
+($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_cosine_ops, v vector_cosine_ops);");
+like($stderr, qr/column 2 cannot be a vector/);
+
+done_testing();
Author	SHA1	Message	Date
Andrew Kane	116501f062	Added support for inline filtering with IVFFlat	2024-10-10 17:07:47 -07:00
Andrew Kane	48fe70c219	Fixed sortdesc for multiple attributes [skip ci]	2024-10-10 15:22:23 -07:00
Andrew Kane	29908405ab	List assignment does not change with scaling [skip ci]	2024-10-10 15:16:08 -07:00
Andrew Kane	08d0340655	Improved IVFFlat vacuum test [skip ci]	2024-10-10 14:24:26 -07:00
Andrew Kane	7d2eb49c2a	Fixed list assignment for cosine distance and non-normalized vectors for IVFFlat	2024-10-10 12:54:13 -07:00
Andrew Kane	772ab69de6	Updated IVFFlat to support multiple attributes (not enabled yet)	2024-10-10 12:34:03 -07:00
Andrew Kane	e13e9a9614	Improved scoping [skip ci]	2024-10-10 12:19:08 -07:00
Andrew Kane	e2fab306ac	Added tupdesc to buildstate [skip ci]	2024-10-10 12:18:41 -07:00
Andrew Kane	edc2126a4a	Renamed tupdesc to sortdesc [skip ci]	2024-10-10 12:16:57 -07:00
Andrew Kane	2cbd08b6c0	Moved unions and macros [skip ci]	2024-10-10 09:41:26 -07:00
Andrew Kane	fa6782985a	Added HnswQuery struct for query data	2024-10-09 23:45:47 -07:00
Andrew Kane	32ab27d72a	Added HnswSupport struct for support functions	2024-10-09 23:10:26 -07:00
Andrew Kane	064db12de7	Moved procinfo initialization for inserts [skip ci]	2024-10-09 21:59:21 -07:00
Andrew Kane	45a6eef9e0	Improved variable name [skip ci]	2024-10-09 21:52:10 -07:00
Andrew Kane	17266ed409	Use inMemory for conditionals	2024-10-09 21:49:32 -07:00
Andrew Kane	a98534e5ab	DRY HNSW procinfo	2024-10-09 21:03:18 -07:00
Andrew Kane	57c05c59a2	DRY code for forming index value	2024-10-09 20:50:17 -07:00
Andrew Kane	3126fbdb6f	Use double for distance [skip ci]	2024-10-09 17:04:25 -07:00
Andrew Kane	f4b67b078f	DRY HNSW distance calculations	2024-10-09 17:01:49 -07:00
Andrew Kane	77688b4309	Improve total cost for cost estimation (#686 )	2024-10-08 12:42:03 -07:00
Andrew Kane	d5f4a0e435	Fixed memory context leak in HnswUpdateNeighborsOnDisk - fixes #692	2024-10-08 12:21:26 -07:00
Andrew Kane	57248ba128	Use separate memory context for updating neighbors, which improves performance around 10% for larger vectors	2024-09-30 11:15:27 -07:00
Andrew Kane	ff6da4fcea	Moved logic to get update neighbor on disk to separate function	2024-09-30 10:30:01 -07:00
Andrew Kane	a8b4b6675a	Moved logic to get update index to separate function	2024-09-30 10:14:52 -07:00
Andrew Kane	d148b4e61b	Fixed insert logic	2024-09-30 09:59:12 -07:00
Andrew Kane	658d74e2f6	Use Size for memory [skip ci]	2024-09-29 23:48:58 -07:00
Andrew Kane	7ba593c492	Improved SelectNeighbors signature [skip ci]	2024-09-29 23:03:02 -07:00
Andrew Kane	525e3b81e1	Improved HnswUpdateConnection parameters [skip ci]	2024-09-29 19:47:25 -07:00
Andrew Kane	8eb8cdf0f3	Moved insert-specific code to hnswinsert.c	2024-09-29 19:44:11 -07:00
Andrew Kane	4c72f91206	Improved variable name [skip ci]	2024-09-29 19:26:15 -07:00
Andrew Kane	4ac86f62a1	Improved variable names [skip ci]	2024-09-29 19:22:35 -07:00
Andrew Kane	648dd8af78	Moved LoadElementsForInsert to separate function and removed unused code path	2024-09-29 19:12:38 -07:00
Andrew Kane	ee43ee9b16	Use HnswLoadNeighborTids for inserts	2024-09-29 18:52:12 -07:00
Andrew Kane	5ce367e18b	Removed lc from HnswUpdateConnection [skip ci]	2024-09-29 18:18:42 -07:00
Andrew Kane	f371eb119b	Removed lc from SelectNeighbors [skip ci]	2024-09-29 18:14:28 -07:00
Andrew Kane	382a25aefb	Split loading neighbor TIDs into separate function [skip ci]	2024-09-29 17:20:54 -07:00
Andrew Kane	0b6214aad6	Moved HnswLoadNeighbors to hnswinsert.c [skip ci]	2024-09-29 15:49:01 -07:00
Andrew Kane	f2afd11257	Use sc for search candidates [skip ci]	2024-09-29 15:09:54 -07:00
Andrew Kane	cae3458329	Updated distance to use double	2024-09-29 15:06:50 -07:00
Andrew Kane	dc23752618	Fixed uninitialized variable [skip ci]	2024-09-28 19:18:52 -07:00