Added test for explicit zeros [skip ci]

Added todo [skip ci]
Updated version [skip ci]
2026-07-22 12:07:34 +08:00 · 2023-11-06 14:29:52 -08:00 · 2023-11-05 21:26:28 -08:00 · 2023-11-05 18:21:09 -08:00 · 2023-11-05 18:12:19 -08:00
21 changed files with 1286 additions and 594 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,6 @@
 ## 0.6.0 (unreleased)

- Added support for inline filtering with HNSW
+- Added support for sparse vectors

 ## 0.5.1 (2023-10-10)

--- a/4
+++ b/4
@@ -3,8 +3,8 @@ EXTVERSION = 0.5.1

 MODULE_big = vector
 DATA = $(wildcard sql/*--*.sql)
-OBJS = src/hnsw.o src/hnswbuild.o src/hnswinsert.o src/hnswscan.o src/hnswutils.o src/hnswvacuum.o src/ivfbuild.o src/ivfflat.o src/ivfinsert.o src/ivfkmeans.o src/ivfscan.o src/ivfutils.o src/ivfvacuum.o src/vector.o
-HEADERS = src/vector.h
+OBJS = src/hnsw.o src/hnswbuild.o src/hnswinsert.o src/hnswscan.o src/hnswutils.o src/hnswvacuum.o src/ivfbuild.o src/ivfflat.o src/ivfinsert.o src/ivfkmeans.o src/ivfscan.o src/ivfutils.o src/ivfvacuum.o src/svector.o src/vector.o
+HEADERS = src/svector.h src/vector.h

 TESTS = $(wildcard test/sql/*.sql)
 REGRESS = $(patsubst test/sql/%.sql,%,$(TESTS))
--- a/Makefile.win
+++ b/Makefile.win
@@ -1,8 +1,8 @@
 EXTENSION = vector
 EXTVERSION = 0.5.1

-OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\vector.obj
-HEADERS = src\vector.h
+OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\svector.obj src\vector.obj
+HEADERS = src\svector.h src\vector.h

 REGRESS = btree cast copy functions input ivfflat_cosine ivfflat_ip ivfflat_l2 ivfflat_options ivfflat_unlogged
 REGRESS_OPTS = --inputdir=test --load-extension=$(EXTENSION)
--- a/README.md
+++ b/README.md
@@ -315,12 +315,6 @@ Create an index on one [or more](https://www.postgresql.org/docs/current/indexes
 CREATE INDEX ON items (category_id);
 ```

-Or a composite HNSW index for approximate search (added in 0.6.0)
-
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_l2_ops, category_id);
-```
-
 Or a [partial index](https://www.postgresql.org/docs/current/indexes-partial.html) on the vector column for approximate search

 ```sql
@@ -375,6 +369,26 @@ To speed up queries with an IVFFlat index, increase the number of inverted lists
 CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 1000);
 ```

+## Sparse Vectors
+
+Create a sparse vector column with 10 dimensions
+
+```sql
+CREATE TABLE items (id bigserial PRIMARY KEY, embedding svector(10));
+```
+
+Insert vectors
+
+```sql
+INSERT INTO items (embedding) VALUES ('(0,1),(1,2),(2,3)|10|'), ('(0,4),(1,5),(4,6)|10|');
+```
+
+Get the nearest neighbors by L2 distance
+
+```sql
+SELECT * FROM items ORDER BY embedding <-> '(0,3),(1,1),(2,2)|10|' LIMIT 5;
+```
+
 ## Languages

 Use pgvector from any language with a Postgres client. You can even generate and store vectors in one language and query them in another.
@@ -718,7 +732,6 @@ 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

--- a/sql/vector--0.5.1--0.6.0.sql
+++ b/sql/vector--0.5.1--0.6.0.sql
@@ -1,18 +1,79 @@
 -- complain if script is sourced in psql, rather than via CREATE EXTENSION
 \echo Use "ALTER EXTENSION vector UPDATE TO '0.6.0'" 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 TYPE svector;

-CREATE FUNCTION hnsw_attribute_distance(bigint, bigint) RETURNS float8
-	AS 'MODULE_PATHNAME', 'hnsw_int8_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+CREATE FUNCTION svector_in(cstring, oid, integer) RETURNS svector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;

-CREATE OPERATOR CLASS vector_integer_ops
-	DEFAULT FOR TYPE integer USING hnsw AS
-	OPERATOR 2 = (integer, integer),
-	FUNCTION 3 hnsw_attribute_distance(integer, integer);
+CREATE FUNCTION svector_out(svector) RETURNS cstring
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;

-CREATE OPERATOR CLASS vector_bigint_ops
-	DEFAULT FOR TYPE bigint USING hnsw AS
-	OPERATOR 2 = (bigint, bigint),
-	FUNCTION 3 hnsw_attribute_distance(bigint, bigint);
+CREATE FUNCTION svector_typmod_in(cstring[]) RETURNS integer
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION svector_recv(internal, oid, integer) RETURNS svector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION svector_send(svector) RETURNS bytea
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE TYPE svector (
+	INPUT     = svector_in,
+	OUTPUT    = svector_out,
+	TYPMOD_IN = svector_typmod_in,
+	RECEIVE   = svector_recv,
+	SEND      = svector_send,
+	STORAGE   = external
+);
+
+CREATE FUNCTION l2_distance(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME', 'svector_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION inner_product(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME', 'svector_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION cosine_distance(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME', 'svector_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION jaccard_distance(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME', 'svector_jaccard_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION svector_l2_squared_distance(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION svector_negative_inner_product(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION svector(svector, integer, boolean) RETURNS svector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION vector_to_svector(vector, integer, boolean) RETURNS svector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION svector_to_vector(svector, integer, boolean) RETURNS vector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE CAST (svector AS svector)
+	WITH FUNCTION svector(svector, integer, boolean) AS IMPLICIT;
+
+CREATE CAST (svector AS vector)
+	WITH FUNCTION svector_to_vector(svector, integer, boolean) AS IMPLICIT;
+
+CREATE CAST (vector AS svector)
+	WITH FUNCTION vector_to_svector(vector, integer, boolean) AS IMPLICIT;
+
+CREATE OPERATOR <-> (
+	LEFTARG = svector, RIGHTARG = svector, PROCEDURE = l2_distance,
+	COMMUTATOR = '<->'
+);
+
+CREATE OPERATOR <#> (
+	LEFTARG = svector, RIGHTARG = svector, PROCEDURE = svector_negative_inner_product,
+	COMMUTATOR = '<#>'
+);
+
+CREATE OPERATOR <=> (
+	LEFTARG = svector, RIGHTARG = svector, PROCEDURE = cosine_distance,
+	COMMUTATOR = '<=>'
+);
--- a/sql/vector.sql
+++ b/sql/vector.sql
@@ -291,20 +291,91 @@ CREATE OPERATOR CLASS vector_cosine_ops
 	FUNCTION 1 vector_negative_inner_product(vector, vector),
 	FUNCTION 2 vector_norm(vector);

-- hnsw attributes
+--- svector type

-CREATE FUNCTION hnsw_attribute_distance(integer, integer) RETURNS float8
-	AS 'MODULE_PATHNAME', 'hnsw_int4_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+CREATE TYPE svector;

-CREATE FUNCTION hnsw_attribute_distance(bigint, bigint) RETURNS float8
-	AS 'MODULE_PATHNAME', 'hnsw_int8_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+CREATE FUNCTION svector_in(cstring, oid, integer) RETURNS svector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;

-CREATE OPERATOR CLASS vector_integer_ops
-	DEFAULT FOR TYPE integer USING hnsw AS
-	OPERATOR 2 = (integer, integer),
-	FUNCTION 3 hnsw_attribute_distance(integer, integer);
+CREATE FUNCTION svector_out(svector) RETURNS cstring
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;

-CREATE OPERATOR CLASS vector_bigint_ops
-	DEFAULT FOR TYPE bigint USING hnsw AS
-	OPERATOR 2 = (bigint, bigint),
-	FUNCTION 3 hnsw_attribute_distance(bigint, bigint);
+CREATE FUNCTION svector_typmod_in(cstring[]) RETURNS integer
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION svector_recv(internal, oid, integer) RETURNS svector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION svector_send(svector) RETURNS bytea
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE TYPE svector (
+	INPUT     = svector_in,
+	OUTPUT    = svector_out,
+	TYPMOD_IN = svector_typmod_in,
+	RECEIVE   = svector_recv,
+	SEND      = svector_send,
+	STORAGE   = external
+);
+
+-- svector functions
+
+CREATE FUNCTION l2_distance(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME', 'svector_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION inner_product(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME', 'svector_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION cosine_distance(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME', 'svector_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION jaccard_distance(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME', 'svector_jaccard_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+-- svector private functions
+
+CREATE FUNCTION svector_l2_squared_distance(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION svector_negative_inner_product(svector, svector) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+-- svector cast functions
+
+CREATE FUNCTION svector(svector, integer, boolean) RETURNS svector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION vector_to_svector(vector, integer, boolean) RETURNS svector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION svector_to_vector(svector, integer, boolean) RETURNS vector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+-- svector casts
+
+CREATE CAST (svector AS svector)
+	WITH FUNCTION svector(svector, integer, boolean) AS IMPLICIT;
+
+CREATE CAST (svector AS vector)
+	WITH FUNCTION svector_to_vector(svector, integer, boolean) AS IMPLICIT;
+
+CREATE CAST (vector AS svector)
+	WITH FUNCTION vector_to_svector(vector, integer, boolean) AS IMPLICIT;
+
+-- svector operators
+
+CREATE OPERATOR <-> (
+	LEFTARG = svector, RIGHTARG = svector, PROCEDURE = l2_distance,
+	COMMUTATOR = '<->'
+);
+
+CREATE OPERATOR <#> (
+	LEFTARG = svector, RIGHTARG = svector, PROCEDURE = svector_negative_inner_product,
+	COMMUTATOR = '<#>'
+);
+
+CREATE OPERATOR <=> (
+	LEFTARG = svector, RIGHTARG = svector, PROCEDURE = cosine_distance,
+	COMMUTATOR = '<=>'
+);
--- a/src/hnsw.c
+++ b/src/hnsw.c
@@ -167,7 +167,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 	IndexAmRoutine *amroutine = makeNode(IndexAmRoutine);

 	amroutine->amstrategies = 0;
-	amroutine->amsupport = 3;
+	amroutine->amsupport = 2;
 #if PG_VERSION_NUM >= 130000
 	amroutine->amoptsprocnum = 0;
 #endif
@@ -175,7 +175,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 	amroutine->amcanorderbyop = true;
 	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;
@@ -222,31 +222,3 @@ 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);
-}
-
-/*
- * Get the distance between two int8 attributes
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(hnsw_int8_attribute_distance);
-Datum
-hnsw_int8_attribute_distance(PG_FUNCTION_ARGS)
-{
-	int64		a = PG_GETARG_INT64(0);
-	int64		b = PG_GETARG_INT64(1);
-	double		distance = ((double) a) - ((double) b);
-
-	PG_RETURN_FLOAT8(distance);
-}
--- a/src/hnsw.h
+++ b/src/hnsw.h
@@ -19,7 +19,6 @@
 /* Support functions */
 #define HNSW_DISTANCE_PROC 1
 #define HNSW_NORM_PROC 2
-#define HNSW_ATTRIBUTE_DISTANCE_PROC 3

 #define HNSW_VERSION	1
 #define HNSW_MAGIC_NUMBER 0xA953A953
@@ -60,7 +59,7 @@

 #define HNSW_MAX_SIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - sizeof(ItemIdData))

-#define HNSW_ELEMENT_TUPLE_SIZE(size)	MAXALIGN(offsetof(HnswElementTupleData, data) + (size))
+#define HNSW_ELEMENT_TUPLE_SIZE(_dim)	MAXALIGN(offsetof(HnswElementTupleData, vec) + VECTOR_SIZE(_dim))
 #define HNSW_NEIGHBOR_TUPLE_SIZE(level, m)	MAXALIGN(offsetof(HnswNeighborTupleData, indextids) + ((level) + 2) * (m) * sizeof(ItemPointerData))

 #define HnswPageGetOpaque(page)	((HnswPageOpaque) PageGetSpecialPointer(page))
@@ -104,8 +103,7 @@ typedef struct HnswElementData
 	OffsetNumber offno;
 	OffsetNumber neighborOffno;
 	BlockNumber neighborPage;
-	Datum		value;
-	IndexTuple	itup;
+	Vector	   *vec;
 }			HnswElementData;

 typedef HnswElementData * HnswElement;
@@ -156,18 +154,17 @@ typedef struct HnswBuildState
 	double		reltuples;

 	/* Support functions */
-	FmgrInfo  **procinfos;
+	FmgrInfo   *procinfo;
 	FmgrInfo   *normprocinfo;
-	Oid		   *collations;
+	Oid			collation;

 	/* Variables */
 	List	   *elements;
 	HnswElement entryPoint;
 	double		ml;
 	int			maxLevel;
-	long		memoryLeft;
+	double		maxInMemoryElements;
 	bool		flushed;
-	bool		useIndexTuple;
 	Vector	   *normvec;

 	/* Memory */
@@ -207,7 +204,7 @@ typedef struct HnswElementTupleData
 	ItemPointerData heaptids[HNSW_HEAPTIDS];
 	ItemPointerData neighbortid;
 	uint16		unused2;
-	Vector		data;
+	Vector		vec;
 }			HnswElementTupleData;

 typedef HnswElementTupleData * HnswElementTuple;
@@ -229,9 +226,9 @@ typedef struct HnswScanOpaqueData
 	MemoryContext tmpCtx;

 	/* Support functions */
-	FmgrInfo  **procinfos;
+	FmgrInfo   *procinfo;
 	FmgrInfo   *normprocinfo;
-	Oid		   *collations;
+	Oid			collation;
 }			HnswScanOpaqueData;

 typedef HnswScanOpaqueData * HnswScanOpaque;
@@ -249,8 +246,8 @@ typedef struct HnswVacuumState
 	int			efConstruction;

 	/* Support functions */
-	FmgrInfo  **procinfos;
-	Oid		   *collations;
+	FmgrInfo   *procinfo;
+	Oid			collation;

 	/* Variables */
 	HTAB	   *deleted;
@@ -272,27 +269,26 @@ Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
 void		HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state);
 void		HnswInit(void);
-List	   *HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef, int lc, Relation index, FmgrInfo **procinfos, Oid *collations, int m, bool loadVec, HnswElement skipElement, bool inMemory);
+List	   *HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
 HnswElement HnswGetEntryPoint(Relation index);
 void		HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
 HnswElement HnswInitElement(ItemPointer tid, int m, double ml, int maxLevel);
 void		HnswFreeElement(HnswElement element);
 HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
-void		HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo **procinfos, Oid *collations, int m, int efConstruction, bool existing, bool inMemory);
-HnswElement HnswFindDuplicate(HnswElement e, Relation index);
-HnswCandidate *HnswEntryCandidate(HnswElement em, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation rel, FmgrInfo **procinfos, Oid *collations, bool loadVec, bool inMemory);
+void		HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
+HnswElement HnswFindDuplicate(HnswElement e);
+HnswCandidate *HnswEntryCandidate(HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
 void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum);
 void		HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m);
 void		HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
 void		HnswInitNeighbors(HnswElement element, int m);
 bool		HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel);
-void		HnswUpdateNeighborPages(Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement e, int m, bool checkExisting);
-void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index);
-void		HnswLoadElement(HnswElement element, float *distance, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations, bool loadVec);
-void		HnswSetElementTuple(HnswElementTuple etup, HnswElement element, bool useIndexTuple);
-void		HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo **procinfos, Oid *collations, bool inMemory);
+void		HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting);
+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);
+void		HnswSetElementTuple(HnswElementTuple etup, HnswElement element);
+void		HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
 void		HnswLoadNeighbors(HnswElement element, Relation index, int m);
-void		HnswElementSetData(HnswElement element, Relation index, Datum value, Datum *values, bool *isnull);

 /* Index access methods */
 IndexBuildResult *hnswbuild(Relation heap, Relation index, IndexInfo *indexInfo);
@@ -309,6 +305,5 @@ IndexScanDesc hnswbeginscan(Relation index, int nkeys, int norderbys);
 void		hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int norderbys);
 bool		hnswgettuple(IndexScanDesc scan, ScanDirection dir);
 void		hnswendscan(IndexScanDesc scan);
-FmgrInfo  **HnswInitProcinfos(Relation index);

 #endif
--- a/src/hnswbuild.c
+++ b/src/hnswbuild.c
@@ -8,7 +8,6 @@
 #include "lib/pairingheap.h"
 #include "nodes/pg_list.h"
 #include "storage/bufmgr.h"
-#include "utils/datum.h"
 #include "utils/memutils.h"

 #if PG_VERSION_NUM >= 140000
@@ -106,8 +105,8 @@ CreateElementPages(HnswBuildState * buildstate)
 {
 	Relation	index = buildstate->index;
 	ForkNumber	forkNum = buildstate->forkNum;
-	bool		useIndexTuple = buildstate->useIndexTuple;
-	Size		etupAllocSize;
+	int			dimensions = buildstate->dimensions;
+	Size		etupSize;
 	Size		maxSize;
 	HnswElementTuple etup;
 	HnswNeighborTuple ntup;
@@ -118,11 +117,11 @@ CreateElementPages(HnswBuildState * buildstate)
 	ListCell   *lc;

 	/* Calculate sizes */
-	etupAllocSize = BLCKSZ;
 	maxSize = HNSW_MAX_SIZE;
+	etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);

 	/* Allocate once */
-	etup = palloc0(etupAllocSize);
+	etup = palloc0(etupSize);
 	ntup = palloc0(BLCKSZ);

 	/* Prepare first page */
@@ -134,24 +133,15 @@ CreateElementPages(HnswBuildState * buildstate)
 	foreach(lc, buildstate->elements)
 	{
 		HnswElement element = lfirst(lc);
-		Size		etupSize;
 		Size		ntupSize;
 		Size		combinedSize;

-		/* Zero memory for each element */
-		MemSet(etup, 0, etupAllocSize);
+		HnswSetElementTuple(etup, element);

 		/* Calculate sizes */
-		etupSize = HNSW_ELEMENT_TUPLE_SIZE(useIndexTuple ? IndexTupleSize(element->itup) : VARSIZE_ANY(DatumGetPointer(element->value)));
 		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, buildstate->m);
 		combinedSize = etupSize + ntupSize + sizeof(ItemIdData);

-		/* Initial size check */
-		if (etupSize > etupAllocSize)
-			elog(ERROR, "index tuple too large");
-
-		HnswSetElementTuple(etup, element, useIndexTuple);
-
 		/* Keep element and neighbors on the same page if possible */
 		if (PageGetFreeSpace(page) < etupSize || (combinedSize <= maxSize && PageGetFreeSpace(page) < combinedSize))
 			HnswBuildAppendPage(index, &buf, &page, &state, forkNum);
@@ -274,15 +264,13 @@ FlushPages(HnswBuildState * buildstate)
 * Insert tuple
 */
 static bool
-InsertTuple(Relation index, Datum *values, bool *isnull, HnswElement element, HnswBuildState * buildstate, HnswElement * dup, MemoryContext outerCtx)
+InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState * buildstate, HnswElement * dup)
 {
-	FmgrInfo  **procinfos = buildstate->procinfos;
-	Oid		   *collations = buildstate->collations;
+	FmgrInfo   *procinfo = buildstate->procinfo;
+	Oid			collation = buildstate->collation;
 	HnswElement entryPoint = buildstate->entryPoint;
 	int			efConstruction = buildstate->efConstruction;
 	int			m = buildstate->m;
-	bool		inMemory = true;
-	MemoryContext oldCtx;

 	/* Detoast once for all calls */
 	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -290,20 +278,18 @@ InsertTuple(Relation index, Datum *values, bool *isnull, HnswElement element, Hn
 	/* Normalize if needed */
 	if (buildstate->normprocinfo != NULL)
 	{
-		if (!HnswNormValue(buildstate->normprocinfo, collations[0], &value, buildstate->normvec))
+		if (!HnswNormValue(buildstate->normprocinfo, collation, &value, buildstate->normvec))
 			return false;
 	}

 	/* Copy value to element so accessible outside of memory context */
-	oldCtx = MemoryContextSwitchTo(outerCtx);
-	HnswElementSetData(element, index, value, values, isnull);
-	MemoryContextSwitchTo(oldCtx);
+	memcpy(element->vec, DatumGetVector(value), VECTOR_SIZE(buildstate->dimensions));

 	/* Insert element in graph */
-	HnswInsertElement(element, entryPoint, index, procinfos, collations, m, efConstruction, false, inMemory);
+	HnswInsertElement(element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);

 	/* Look for duplicate */
-	*dup = HnswFindDuplicate(element, index);
+	*dup = HnswFindDuplicate(element);

 	/* Update neighbors if needed */
 	if (*dup == NULL)
@@ -314,7 +300,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, HnswElement element, Hn
 			HnswNeighborArray *neighbors = &element->neighbors[lc];

 			for (int i = 0; i < neighbors->length; i++)
-				HnswUpdateConnection(element, &neighbors->items[i], lm, lc, NULL, index, procinfos, collations, inMemory);
+				HnswUpdateConnection(element, &neighbors->items[i], lm, lc, NULL, NULL, procinfo, collation);
 		}
 	}

@@ -327,21 +313,6 @@ InsertTuple(Relation index, Datum *values, bool *isnull, HnswElement element, Hn
 	return *dup == NULL;
 }

-/*
- * Get the memory used by an element
- */
-static long
-HnswElementMemory(HnswElement e, int m)
-{
-	long		elementSize = sizeof(HnswElementData);
-
-	elementSize += sizeof(HnswNeighborArray) * (e->level + 1);
-	elementSize += sizeof(HnswCandidate) * (m * (e->level + 2));
-	elementSize += sizeof(ItemPointerData);
-	elementSize += IndexTupleSize(e->itup);
-	return elementSize;
-}
-
 /*
 * Callback for table_index_build_scan
 */
@@ -363,7 +334,7 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 	if (isnull[0])
 		return;

-	if (buildstate->memoryLeft <= 0)
+	if (buildstate->indtuples >= buildstate->maxInMemoryElements)
 	{
 		if (!buildstate->flushed)
 		{
@@ -389,12 +360,13 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,

 	/* Allocate necessary memory outside of memory context */
 	element = HnswInitElement(tid, buildstate->m, buildstate->ml, buildstate->maxLevel);
+	element->vec = palloc(VECTOR_SIZE(buildstate->dimensions));

 	/* Use memory context since detoast can allocate */
 	oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);

 	/* Insert tuple */
-	inserted = InsertTuple(index, values, isnull, element, buildstate, &dup, oldCtx);
+	inserted = InsertTuple(index, values, element, buildstate, &dup);

 	/* Reset memory context */
 	MemoryContextSwitchTo(oldCtx);
@@ -402,21 +374,31 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,

 	/* Add outside memory context */
 	if (dup != NULL)
-	{
 		HnswAddHeapTid(dup, tid);
-		buildstate->memoryLeft -= sizeof(ItemPointerData);
-	}

 	/* Add to buildstate or free */
 	if (inserted)
-	{
 		buildstate->elements = lappend(buildstate->elements, element);
-		buildstate->memoryLeft -= HnswElementMemory(element, buildstate->m);
-	}
 	else
 		HnswFreeElement(element);
 }

+/*
+ * Get the max number of elements that fit into maintenance_work_mem
+ */
+static double
+HnswGetMaxInMemoryElements(int m, double ml, int dimensions)
+{
+	Size		elementSize = sizeof(HnswElementData);
+	double		avgLevel = -log(0.5) * ml;
+
+	elementSize += sizeof(HnswNeighborArray) * (avgLevel + 1);
+	elementSize += sizeof(HnswCandidate) * (m * (avgLevel + 2));
+	elementSize += sizeof(ItemPointerData);
+	elementSize += VECTOR_SIZE(dimensions);
+	return (maintenance_work_mem * 1024L) / elementSize;
+}
+
 /*
 * Initialize the build state
 */
@@ -432,19 +414,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->efConstruction = HnswGetEfConstruction(index);
 	buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;

-	/* 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)
 		elog(ERROR, "column does not have dimensions");
@@ -459,17 +428,16 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->indtuples = 0;

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

 	buildstate->elements = NIL;
 	buildstate->entryPoint = NULL;
 	buildstate->ml = HnswGetMl(buildstate->m);
 	buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
-	buildstate->memoryLeft = maintenance_work_mem * 1024L;
+	buildstate->maxInMemoryElements = HnswGetMaxInMemoryElements(buildstate->m, buildstate->ml, buildstate->dimensions);
 	buildstate->flushed = false;
-	buildstate->useIndexTuple = IndexRelationGetNumberOfAttributes(index) > 1;

 	/* Reuse for each tuple */
 	buildstate->normvec = InitVector(buildstate->dimensions);
@@ -485,7 +453,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 static void
 FreeBuildState(HnswBuildState * buildstate)
 {
-	pfree(buildstate->procinfos);
 	pfree(buildstate->normvec);
 	MemoryContextDelete(buildstate->tmpCtx);
 }
--- a/src/hnswinsert.c
+++ b/src/hnswinsert.c
@@ -123,16 +123,16 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	Size		minCombinedSize;
 	HnswElementTuple etup;
 	BlockNumber currentPage = insertPage;
+	int			dimensions = e->vec->dim;
 	HnswNeighborTuple ntup;
 	Buffer		nbuf;
 	Page		npage;
 	OffsetNumber freeOffno = InvalidOffsetNumber;
 	OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
 	BlockNumber newInsertPage = InvalidBlockNumber;
-	bool		useIndexTuple = IndexRelationGetNumberOfAttributes(index) > 1;

 	/* Calculate sizes */
-	etupSize = HNSW_ELEMENT_TUPLE_SIZE(useIndexTuple ? IndexTupleSize(e->itup) : VARSIZE_ANY(DatumGetPointer(e->value)));
+	etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);
 	ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 	combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 	maxSize = HNSW_MAX_SIZE;
@@ -140,7 +140,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag

 	/* Prepare element tuple */
 	etup = palloc0(etupSize);
-	HnswSetElementTuple(etup, e, useIndexTuple);
+	HnswSetElementTuple(etup, e);

 	/* Prepare neighbor tuple */
 	ntup = palloc0(ntupSize);
@@ -302,7 +302,7 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
 * Update neighbors
 */
 void
-HnswUpdateNeighborPages(Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement e, int m, bool checkExisting)
+HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -334,7 +334,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo **procinfos, Oid *collations, H
 			 */

 			/* Select neighbors */
-			HnswUpdateConnection(e, hc, lm, lc, &idx, index, procinfos, collations, false);
+			HnswUpdateConnection(e, hc, lm, lc, &idx, index, procinfo, collation);

 			/* New element was not selected as a neighbor */
 			if (idx == -1)
@@ -405,9 +405,8 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	Buffer		buf;
 	Page		page;
 	GenericXLogState *state;
-	ItemId		itemid;
+	Size		etupSize = HNSW_ELEMENT_TUPLE_SIZE(dup->vec->dim);
 	HnswElementTuple etup;
-	Size		etupSize;
 	int			i;

 	/* Read page */
@@ -417,9 +416,7 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	page = GenericXLogRegisterBuffer(state, buf, 0);

 	/* Find space */
-	itemid = PageGetItemId(page, dup->offno);
-	etup = (HnswElementTuple) PageGetItem(page, itemid);
-	etupSize = ItemIdGetLength(itemid);
+	etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, dup->offno));
 	for (i = 0; i < HNSW_HEAPTIDS; i++)
 	{
 		if (!ItemPointerIsValid(&etup->heaptids[i]))
@@ -452,7 +449,7 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 * Write changes to disk
 */
 static void
-WriteElement(Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint)
+WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;

@@ -471,7 +468,7 @@ WriteElement(Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement
 		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM);

 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfos, collations, element, m, false);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false);

 	/* Update metapage if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -490,8 +487,8 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	HnswElement element;
 	int			m;
 	int			efConstruction = HnswGetEfConstruction(index);
-	FmgrInfo  **procinfos = HnswInitProcinfos(index);
-	Oid		   *collations = index->rd_indcollation;
+	FmgrInfo   *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+	Oid			collation = index->rd_indcollation[0];
 	HnswElement dup;
 	LOCKMODE	lockmode = ShareLock;

@@ -502,7 +499,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
 	if (normprocinfo != NULL)
 	{
-		if (!HnswNormValue(normprocinfo, collations[0], &value, NULL))
+		if (!HnswNormValue(normprocinfo, collation, &value, NULL))
 			return false;
 	}

@@ -518,7 +515,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti

 	/* Create an element */
 	element = HnswInitElement(heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m));
-	HnswElementSetData(element, index, value, values, isnull);
+	element->vec = DatumGetVector(value);

 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -535,13 +532,13 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	}

 	/* Insert element in graph */
-	HnswInsertElement(element, entryPoint, index, procinfos, collations, m, efConstruction, false, false);
+	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, false);

 	/* Look for duplicate */
-	dup = HnswFindDuplicate(element, index);
+	dup = HnswFindDuplicate(element);

 	/* Write to disk */
-	WriteElement(index, procinfos, collations, element, m, efConstruction, dup, entryPoint);
+	WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint);

 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
--- a/src/hnswscan.c
+++ b/src/hnswscan.c
@@ -15,13 +15,12 @@ GetScanItems(IndexScanDesc scan, Datum q)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 	Relation	index = scan->indexRelation;
-	FmgrInfo  **procinfos = so->procinfos;
-	Oid		   *collations = so->collations;
+	FmgrInfo   *procinfo = so->procinfo;
+	Oid			collation = so->collation;
 	List	   *ep;
 	List	   *w;
 	int			m;
 	HnswElement entryPoint;
-	ScanKeyData *keyData = scan->keyData;

 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
@@ -29,15 +28,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	if (entryPoint == NULL)
 		return NIL;

-	ep = list_make1(HnswEntryCandidate(entryPoint, q, NULL, keyData, index, procinfos, collations, false, false));
+	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, false));

 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(q, NULL, keyData, ep, 1, lc, index, procinfos, collations, m, false, NULL, false);
+		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
 		ep = w;
 	}

-	return HnswSearchLayer(q, NULL, keyData, ep, hnsw_ef_search, 0, index, procinfos, collations, m, false, NULL, false);
+	return HnswSearchLayer(q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
 }

 /*
@@ -84,7 +83,7 @@ GetScanValue(IndexScanDesc scan)

 		/* Fine if normalization fails */
 		if (so->normprocinfo != NULL)
-			HnswNormValue(so->normprocinfo, so->collations[0], &value, NULL);
+			HnswNormValue(so->normprocinfo, so->collation, &value, NULL);
 	}

 	return value;
@@ -108,9 +107,9 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 									   ALLOCSET_DEFAULT_SIZES);

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

 	scan->opaque = so;

@@ -207,9 +206,6 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		scan->xs_ctup.t_self = *heaptid;
 #endif

-		/* TODO Check during scan */
-		scan->xs_recheck = scan->numberOfKeys > 0;
-
 		scan->xs_recheckorderby = false;
 		return true;
 	}
@@ -226,7 +222,6 @@ hnswendscan(IndexScanDesc scan)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;

-	pfree(so->procinfos);
 	MemoryContextDelete(so->tmpCtx);

 	pfree(so);
--- a/src/hnswutils.c
+++ b/src/hnswutils.c
@@ -4,13 +4,8 @@

 #include "hnsw.h"
 #include "storage/bufmgr.h"
-#include "utils/datum.h"
 #include "vector.h"

-#if PG_VERSION_NUM < 130000
-#define TYPSTORAGE_PLAIN 'p'
-#endif
-
 /*
 * Get the max number of connections in an upper layer for each element in the index
 */
@@ -51,22 +46,6 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
 	return index_getprocinfo(index, 1, procnum);
 }

-/*
- * Init procs
- */
-FmgrInfo  **
-HnswInitProcinfos(Relation index)
-{
-	int			keyAttributes = IndexRelationGetNumberOfKeyAttributes(index);
-	FmgrInfo  **procinfos = palloc(keyAttributes * sizeof(FmgrInfo *));
-
-	procinfos[0] = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-	for (int i = 1; i < keyAttributes; i++)
-		procinfos[i] = index_getprocinfo(index, i + 1, HNSW_ATTRIBUTE_DISTANCE_PROC);
-
-	return procinfos;
-}
-
 /*
 * Divide by the norm
 *
@@ -194,7 +173,6 @@ HnswInitElement(ItemPointer heaptid, int m, double ml, int maxLevel)

 	element->level = level;
 	element->deleted = 0;
-	element->itup = NULL;

 	HnswInitNeighbors(element, m);

@@ -209,8 +187,7 @@ HnswFreeElement(HnswElement element)
 {
 	HnswFreeNeighbors(element);
 	list_free_deep(element->heaptids);
-	if (element->itup)
-		pfree(element->itup);
+	pfree(element->vec);
 	pfree(element);
 }

@@ -237,8 +214,7 @@ HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno)
 	element->blkno = blkno;
 	element->offno = offno;
 	element->neighbors = NULL;
-	element->value = PointerGetDatum(NULL);
-	element->itup = NULL;
+	element->vec = NULL;
 	return element;
 }

@@ -336,7 +312,7 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
 * Set element tuple, except for neighbor info
 */
 void
-HnswSetElementTuple(HnswElementTuple etup, HnswElement element, bool useIndexTuple)
+HnswSetElementTuple(HnswElementTuple etup, HnswElement element)
 {
 	etup->type = HNSW_ELEMENT_TUPLE_TYPE;
 	etup->level = element->level;
@@ -348,11 +324,7 @@ HnswSetElementTuple(HnswElementTuple etup, HnswElement element, bool useIndexTup
 		else
 			ItemPointerSetInvalid(&etup->heaptids[i]);
 	}
-
-	if (useIndexTuple)
-		memcpy(&etup->data, element->itup, IndexTupleSize(element->itup));
-	else
-		memcpy(&etup->data, DatumGetPointer(element->value), VARSIZE_ANY(DatumGetPointer(element->value)));
+	memcpy(&etup->vec, element->vec, VECTOR_SIZE(element->vec->dim));
 }

 /*
@@ -453,7 +425,7 @@ HnswLoadNeighbors(HnswElement element, Relation index, 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;
@@ -475,149 +447,16 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe

 	if (loadVec)
 	{
-		if (IndexRelationGetNumberOfAttributes(index) > 1)
-		{
-			TupleDesc	tupdesc = RelationGetDescr(index);
-			bool		unused;
-
-			element->itup = CopyIndexTuple((IndexTuple) &etup->data);
-			element->value = index_getattr(element->itup, 1, tupdesc, &unused);
-		}
-		else
-		{
-			Vector	   *vec = palloc(VARSIZE_ANY(&etup->data));
-
-			memcpy(vec, &etup->data, VARSIZE_ANY(&etup->data));
-			element->value = PointerGetDatum(vec);
-		}
+		element->vec = palloc(VECTOR_SIZE(etup->vec.dim));
+		memcpy(element->vec, &etup->vec, VECTOR_SIZE(etup->vec.dim));
 	}
 }

-/*
- * Get the tuple descriptor
- */
-static TupleDesc
-HnswTupleDesc(Relation index)
-{
-	TupleDesc	tupdesc = CreateTupleDescCopyConstr(RelationGetDescr(index));
-
-	/* Prevent compression */
-	TupleDescAttr(tupdesc, 0)->attstorage = TYPSTORAGE_PLAIN;
-
-	return tupdesc;
-}
-
-/*
- * Set element data
- */
-void
-HnswElementSetData(HnswElement element, Relation index, Datum value, Datum *values, bool *isnull)
-{
-	/* TODO Create once per index build */
-	TupleDesc	tupdesc = HnswTupleDesc(index);
-	bool		unused;
-	Datum		tmp;
-
-	tmp = values[0];
-	values[0] = value;
-	element->itup = index_form_tuple(tupdesc, values, isnull);
-	values[0] = tmp;
-
-	element->value = index_getattr(element->itup, 1, tupdesc, &unused);
-
-	FreeTupleDesc(tupdesc);
-}
-
-/*
- * 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;
-}
-
-/*
- * Get the distance
- */
-static double
-GetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations)
-{
-	double		g = DatumGetFloat8(FunctionCall2Coll(procinfos[0], collations[0], q, vec));
-
-	if (IndexRelationGetNumberOfKeyAttributes(index) > 1)
-	{
-		double		w = 0.25;
-		double		e = 0.0;
-		TupleDesc	tupdesc = RelationGetDescr(index);
-
-		if (keyData)
-		{
-			/* TODO need to pass length of key data */
-			int			keyCount = 1;
-
-			for (int i = 0; i < keyCount; i++)
-			{
-				ScanKey		key = &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;
-				}
-				else if (!DatumGetBool(FunctionCall2Coll(&key->sk_func, key->sk_collation, value, key->sk_argument)))
-				{
-					double		ei = fabs(DatumGetFloat8(FunctionCall2Coll(procinfos[key->sk_attno - 1], collations[key->sk_attno - 1], value, key->sk_argument)));
-
-					if (ei > 0)
-						e += ei;
-					else
-						/* Distance is zero for inequality */
-						e += 1000;
-				}
-			}
-
-			return w * g + AttributeDistance(e);
-		}
-		else if (qtup)
-		{
-			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(qtup, i + 2, tupdesc, &attnull);
-
-				if (isnull || attnull)
-				{
-					if (isnull != attnull)
-						e += 1000;
-				}
-				else
-					e += fabs(DatumGetFloat8(FunctionCall2Coll(procinfos[i + 1], collations[i + 1], value, value2)));
-			}
-
-			return w * g + AttributeDistance(e);
-		}
-	}
-
-	return g;
-}
-
 /*
 * Load an element and optionally get its distance from q
 */
 void
-HnswLoadElement(HnswElement element, float *distance, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations, bool loadVec)
+HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
 {
 	Buffer		buf;
 	Page		page;
@@ -633,27 +472,11 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, IndexTuple qtup,
 	Assert(HnswIsElementTuple(etup));

 	/* Load element */
-	HnswLoadElementFromTuple(element, etup, true, loadVec, index);
+	HnswLoadElementFromTuple(element, etup, true, loadVec);

 	/* Calculate distance */
 	if (distance != NULL)
-	{
-		IndexTuple	itup = NULL;
-		Datum		value;
-
-		if (IndexRelationGetNumberOfAttributes(index) > 1)
-		{
-			TupleDesc	tupdesc = RelationGetDescr(index);
-			bool		unused;
-
-			itup = (IndexTuple) &etup->data;
-			value = index_getattr(itup, 1, tupdesc, &unused);
-		}
-		else
-			value = PointerGetDatum(&etup->data);
-
-		*distance = GetDistance(itup, value, *q, qtup, keyData, index, procinfos, collations);
-	}
+		*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->vec)));

 	UnlockReleaseBuffer(buf);
 }
@@ -662,24 +485,24 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, IndexTuple qtup,
 * Get the distance for a candidate
 */
 static float
-GetCandidateDistance(HnswCandidate * hc, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations)
+GetCandidateDistance(HnswCandidate * hc, Datum q, FmgrInfo *procinfo, Oid collation)
 {
-	return GetDistance(hc->element->itup, hc->element->value, q, qtup, keyData, index, procinfos, collations);
+	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, PointerGetDatum(hc->element->vec)));
 }

 /*
 * Create a candidate for the entry point
 */
 HnswCandidate *
-HnswEntryCandidate(HnswElement entryPoint, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations, bool loadVec, bool inMemory)
+HnswEntryCandidate(HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
 {
 	HnswCandidate *hc = palloc(sizeof(HnswCandidate));

 	hc->element = entryPoint;
-	if (inMemory)
-		hc->distance = GetCandidateDistance(hc, q, qtup, keyData, index, procinfos, collations);
+	if (index == NULL)
+		hc->distance = GetCandidateDistance(hc, q, procinfo, collation);
 	else
-		HnswLoadElement(hc->element, &hc->distance, &q, qtup, keyData, index, procinfos, collations, loadVec);
+		HnswLoadElement(hc->element, &hc->distance, &q, index, procinfo, collation, loadVec);
 	return hc;
 }

@@ -729,9 +552,9 @@ CreatePairingHeapNode(HnswCandidate * c)
 * Add to visited
 */
 static inline void
-AddToVisited(HTAB *v, HnswCandidate * hc, bool inMemory, bool *found)
+AddToVisited(HTAB *v, HnswCandidate * hc, Relation index, bool *found)
 {
-	if (inMemory)
+	if (index == NULL)
 		hash_search(v, &hc->element, HASH_ENTER, found);
 	else
 	{
@@ -746,7 +569,7 @@ AddToVisited(HTAB *v, HnswCandidate * hc, bool inMemory, bool *found)
 * Algorithm 2 from paper
 */
 List *
-HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef, int lc, Relation index, FmgrInfo **procinfos, Oid *collations, int m, bool loadVec, HnswElement skipElement, bool inMemory)
+HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
 {
 	ListCell   *lc2;

@@ -758,7 +581,7 @@ HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef
 	HTAB	   *v;

 	/* Create hash table */
-	if (inMemory)
+	if (index == NULL)
 	{
 		hash_ctl.keysize = sizeof(HnswElement *);
 		hash_ctl.entrysize = sizeof(HnswElement *);
@@ -777,7 +600,7 @@ HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef
 	{
 		HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);

-		AddToVisited(v, hc, inMemory, NULL);
+		AddToVisited(v, hc, index, NULL);

 		pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node));
 		pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node));
@@ -811,7 +634,7 @@ HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef
 			HnswCandidate *e = &neighborhood->items[i];
 			bool		visited;

-			AddToVisited(v, e, inMemory, &visited);
+			AddToVisited(v, e, index, &visited);

 			if (!visited)
 			{
@@ -819,10 +642,10 @@ HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef

 				f = ((HnswPairingHeapNode *) pairingheap_first(W))->inner;

-				if (inMemory)
-					eDistance = GetCandidateDistance(e, q, qtup, keyData, index, procinfos, collations);
+				if (index == NULL)
+					eDistance = GetCandidateDistance(e, q, procinfo, collation);
 				else
-					HnswLoadElement(e->element, &eDistance, &q, qtup, keyData, index, procinfos, collations, loadVec);
+					HnswLoadElement(e->element, &eDistance, &q, index, procinfo, collation, inserting);

 				Assert(!e->element->deleted);

@@ -902,7 +725,7 @@ CompareCandidateDistances(const void *a, const void *b)
 * Calculate the distance between elements
 */
 static float
-HnswGetCachedDistance(HnswElement a, HnswElement b, int lc, Relation index, FmgrInfo **procinfos, Oid *collations)
+HnswGetDistance(HnswElement a, HnswElement b, int lc, FmgrInfo *procinfo, Oid collation)
 {
 	/* Look for cached distance */
 	if (a->neighbors != NULL)
@@ -927,21 +750,21 @@ HnswGetCachedDistance(HnswElement a, HnswElement b, int lc, Relation index, Fmgr
 		}
 	}

-	return GetDistance(a->itup, a->value, b->value, b->itup, NULL, index, procinfos, collations);
+	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(a->vec), PointerGetDatum(b->vec)));
 }

 /*
 * Check if an element is closer to q than any element from R
 */
 static bool
-CheckElementCloser(HnswCandidate * e, List *r, int lc, Relation index, FmgrInfo **procinfos, Oid *collations)
+CheckElementCloser(HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid collation)
 {
 	ListCell   *lc2;

 	foreach(lc2, r)
 	{
 		HnswCandidate *ri = lfirst(lc2);
-		float		distance = HnswGetCachedDistance(e->element, ri->element, lc, index, procinfos, collations);
+		float		distance = HnswGetDistance(e->element, ri->element, lc, procinfo, collation);

 		if (distance <= e->distance)
 			return false;
@@ -954,7 +777,7 @@ CheckElementCloser(HnswCandidate * e, List *r, int lc, Relation index, FmgrInfo
 * Algorithm 4 from paper
 */
 static List *
-SelectNeighbors(List *c, int m, int lc, Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
+SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
 {
 	List	   *r = NIL;
 	List	   *w = list_copy(c);
@@ -981,7 +804,7 @@ SelectNeighbors(List *c, int m, int lc, Relation index, FmgrInfo **procinfos, Oi

 		/* Use previous state of r and wd to skip work when possible */
 		if (mustCalculate)
-			e->closer = CheckElementCloser(e, r, lc, index, procinfos, collations);
+			e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
 		else if (list_length(added) > 0)
 		{
 			/*
@@ -990,7 +813,7 @@ SelectNeighbors(List *c, int m, int lc, Relation index, FmgrInfo **procinfos, Oi
 			 */
 			if (e->closer)
 			{
-				e->closer = CheckElementCloser(e, added, lc, index, procinfos, collations);
+				e->closer = CheckElementCloser(e, added, lc, procinfo, collation);

 				if (!e->closer)
 					removedAny = true;
@@ -1003,7 +826,7 @@ SelectNeighbors(List *c, int m, int lc, Relation index, FmgrInfo **procinfos, Oi
 				 */
 				if (removedAny)
 				{
-					e->closer = CheckElementCloser(e, r, lc, index, procinfos, collations);
+					e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
 					if (e->closer)
 						added = lappend(added, e);
 				}
@@ -1011,7 +834,7 @@ SelectNeighbors(List *c, int m, int lc, Relation index, FmgrInfo **procinfos, Oi
 		}
 		else if (e == newCandidate)
 		{
-			e->closer = CheckElementCloser(e, r, lc, index, procinfos, collations);
+			e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
 			if (e->closer)
 				added = lappend(added, e);
 		}
@@ -1045,20 +868,16 @@ SelectNeighbors(List *c, int m, int lc, Relation index, FmgrInfo **procinfos, Oi
 * Find duplicate element
 */
 HnswElement
-HnswFindDuplicate(HnswElement e, Relation index)
+HnswFindDuplicate(HnswElement e)
 {
 	HnswNeighborArray *neighbors = &e->neighbors[0];

-	/* TODO Implement */
-	if (IndexRelationGetNumberOfAttributes(index) > 1)
-		return NULL;
-
 	for (int i = 0; i < neighbors->length; i++)
 	{
 		HnswCandidate *neighbor = &neighbors->items[i];

 		/* Exit early since ordered by distance */
-		if (!datumIsEqual(e->value, neighbor->element->value, false, -1))
+		if (vector_cmp_internal(e->vec, neighbor->element->vec) != 0)
 			break;

 		/* Check for space */
@@ -1086,7 +905,7 @@ AddConnections(HnswElement element, List *neighbors, int m, int lc)
 * Update connections
 */
 void
-HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo **procinfos, Oid *collations, bool inMemory)
+HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation)
 {
 	HnswNeighborArray *currentNeighbors = &hc->element->neighbors[lc];

@@ -1109,20 +928,18 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 		HnswCandidate *pruned = NULL;

 		/* Load elements on insert */
-		if (!inMemory)
+		if (index != NULL)
 		{
-			Datum		q = hc->element->value;
-			IndexTuple	qtup = hc->element->itup;
-			ScanKeyData *keyData = NULL;
+			Datum		q = PointerGetDatum(hc->element->vec);

 			for (int i = 0; i < currentNeighbors->length; i++)
 			{
 				HnswCandidate *hc3 = &currentNeighbors->items[i];

-				if (DatumGetPointer(hc3->element->value) == NULL)
-					HnswLoadElement(hc3->element, &hc3->distance, &q, qtup, keyData, index, procinfos, collations, true);
+				if (hc3->element->vec == NULL)
+					HnswLoadElement(hc3->element, &hc3->distance, &q, index, procinfo, collation, true);
 				else
-					hc3->distance = GetCandidateDistance(hc3, q, qtup, keyData, index, procinfos, collations);
+					hc3->distance = GetCandidateDistance(hc3, q, procinfo, collation);

 				/* Prune element if being deleted */
 				if (list_length(hc3->element->heaptids) == 0)
@@ -1142,7 +959,7 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 				c = lappend(c, &currentNeighbors->items[i]);
 			c = lappend(c, &hc2);

-			SelectNeighbors(c, m, lc, index, procinfos, collations, hc->element, &hc2, &pruned, true);
+			SelectNeighbors(c, m, lc, procinfo, collation, hc->element, &hc2, &pruned, true);

 			/* Should not happen */
 			if (pruned == NULL)
@@ -1194,15 +1011,13 @@ RemoveElements(List *w, HnswElement skipElement)
 * Algorithm 1 from paper
 */
 void
-HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo **procinfos, Oid *collations, int m, int efConstruction, bool existing, bool inMemory)
+HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing)
 {
 	List	   *ep;
 	List	   *w;
 	int			level = element->level;
 	int			entryLevel;
-	Datum		q = element->value;
-	IndexTuple	qtup = element->itup;
-	ScanKeyData *keyData = NULL;
+	Datum		q = PointerGetDatum(element->vec);
 	HnswElement skipElement = existing ? element : NULL;

 	/* No neighbors if no entry point */
@@ -1210,13 +1025,13 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		return;

 	/* Get entry point and level */
-	ep = list_make1(HnswEntryCandidate(entryPoint, q, qtup, keyData, index, procinfos, collations, true, inMemory));
+	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, true));
 	entryLevel = entryPoint->level;

 	/* 1st phase: greedy search to insert level */
 	for (int lc = entryLevel; lc >= level + 1; lc--)
 	{
-		w = HnswSearchLayer(q, qtup, keyData, ep, 1, lc, index, procinfos, collations, m, true, skipElement, inMemory);
+		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
 		ep = w;
 	}

@@ -1234,11 +1049,11 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		List	   *neighbors;
 		List	   *lw;

-		w = HnswSearchLayer(q, qtup, keyData, ep, efConstruction, lc, index, procinfos, collations, m, true, skipElement, inMemory);
+		w = HnswSearchLayer(q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);

 		/* Elements being deleted or skipped can help with search */
 		/* but should be removed before selecting neighbors */
-		if (!inMemory)
+		if (index != NULL)
 			lw = RemoveElements(w, skipElement);
 		else
 			lw = w;
@@ -1248,7 +1063,7 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		 * sortCandidates to true for in-memory builds to enable closer
 		 * caching, but there does not seem to be a difference in performance.
 		 */
-		neighbors = SelectNeighbors(lw, lm, lc, index, procinfos, collations, element, NULL, NULL, false);
+		neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, element, NULL, NULL, false);

 		AddConnections(element, neighbors, lm, lc);

--- a/src/hnswvacuum.c
+++ b/src/hnswvacuum.c
@@ -62,8 +62,7 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 		/* Iterate over nodes */
 		for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 		{
-			ItemId		itemid = PageGetItemId(page, offno);
-			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, itemid);
+			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, offno));
 			int			idx = 0;
 			bool		itemUpdated = false;

@@ -94,7 +93,7 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)

 				if (itemUpdated)
 				{
-					Size		etupSize = ItemIdGetLength(itemid);
+					Size		etupSize = HNSW_ELEMENT_TUPLE_SIZE(etup->vec.dim);

 					/* Mark rest as invalid */
 					for (int i = idx; i < HNSW_HEAPTIDS; i++)
@@ -195,8 +194,8 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	GenericXLogState *state;
 	int			m = vacuumstate->m;
 	int			efConstruction = vacuumstate->efConstruction;
-	FmgrInfo  **procinfos = vacuumstate->procinfos;
-	Oid		   *collations = vacuumstate->collations;
+	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);
@@ -210,7 +209,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	element->heaptids = NIL;

 	/* Add element to graph, skipping itself */
-	HnswInsertElement(element, entryPoint, index, procinfos, collations, m, efConstruction, true, false);
+	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, true);

 	/* Update neighbor tuple */
 	/* Do this before getting page to minimize locking */
@@ -231,7 +230,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);

 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfos, collations, element, m, true);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true);
 }

 /*
@@ -258,7 +257,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 		LockPage(index, HNSW_UPDATE_LOCK, ShareLock);

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

 		/* Repair if needed */
 		if (NeedsUpdated(vacuumstate, highestPoint))
@@ -296,7 +295,7 @@ 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, NULL, index, vacuumstate->procinfos, vacuumstate->collations, true);
+			HnswLoadElement(entryPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);

 			if (NeedsUpdated(vacuumstate, entryPoint))
 			{
@@ -372,7 +371,7 @@ 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);
 		}
@@ -442,7 +441,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	BlockNumber insertPage = InvalidBlockNumber;
 	Relation	index = vacuumstate->index;
 	BufferAccessStrategy bas = vacuumstate->bas;
-	bool		useIndexTuple = IndexRelationGetNumberOfAttributes(index);

 	/*
 	 * Wait for index scans to complete. Scans before this point may contain
@@ -479,8 +477,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 		/* Update element and neighbors together */
 		for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 		{
-			ItemId		itemid = PageGetItemId(page, offno);
-			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, itemid);
+			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, offno));
 			HnswNeighborTuple ntup;
 			Size		etupSize;
 			Size		ntupSize;
@@ -508,7 +505,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 				continue;

 			/* Calculate sizes */
-			etupSize = ItemIdGetLength(itemid);
+			etupSize = HNSW_ELEMENT_TUPLE_SIZE(etup->vec.dim);
 			ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(etup->level, vacuumstate->m);

 			/* Get neighbor page */
@@ -531,18 +528,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)

 			/* Overwrite element */
 			etup->deleted = 1;
-			if (useIndexTuple)
-			{
-				IndexTuple	itup = (IndexTuple) &etup->data;
-
-				MemSet(itup, 0, IndexTupleSize(itup));
-			}
-			else
-			{
-				Vector	   *vec = (Vector *) (&etup->data);
-
-				MemSet(vec, 0, VARSIZE_ANY(vec));
-			}
+			MemSet(&etup->vec.x, 0, etup->vec.dim * sizeof(float));

 			/* Overwrite neighbors */
 			for (int i = 0; i < ntup->count; i++)
@@ -598,8 +584,8 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	vacuumstate->callback_state = callback_state;
 	vacuumstate->efConstruction = HnswGetEfConstruction(index);
 	vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
-	vacuumstate->procinfos = HnswInitProcinfos(index);
-	vacuumstate->collations = index->rd_indcollation;
+	vacuumstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+	vacuumstate->collation = index->rd_indcollation[0];
 	vacuumstate->ntup = palloc0(BLCKSZ);
 	vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
 												"Hnsw vacuum temporary context",
@@ -623,7 +609,6 @@ FreeVacuumState(HnswVacuumState * vacuumstate)
 {
 	hash_destroy(vacuumstate->deleted);
 	FreeAccessStrategy(vacuumstate->bas);
-	pfree(vacuumstate->procinfos);
 	pfree(vacuumstate->ntup);
 	MemoryContextDelete(vacuumstate->tmpCtx);
 }
--- a/src/svector.c
+++ b/src/svector.c
@@ -0,0 +1,705 @@
+#include "postgres.h"
+
+#include <math.h>
+
+#include "fmgr.h"
+#include "libpq/pqformat.h"
+#include "svector.h"
+#include "utils/array.h"
+#include "vector.h"
+
+#if PG_VERSION_NUM >= 120000
+#include "common/shortest_dec.h"
+#include "utils/float.h"
+#else
+#include <float.h>
+#include "utils/builtins.h"
+#endif
+
+/*
+ * Ensure same dimensions
+ */
+static inline void
+CheckDims(SVector * a, SVector * b)
+{
+	if (a->dim != b->dim)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_EXCEPTION),
+				 errmsg("different svector dimensions %d and %d", a->dim, b->dim)));
+}
+
+/*
+ * Ensure expected dimensions
+ */
+static inline void
+CheckExpectedDim(int32 typmod, int dim)
+{
+	if (typmod != -1 && typmod != dim)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_EXCEPTION),
+				 errmsg("expected %d dimensions, not %d", typmod, dim)));
+}
+
+/*
+ * Ensure valid dimensions
+ */
+static inline void
+CheckDim(int dim)
+{
+	if (dim < 1)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_EXCEPTION),
+				 errmsg("svector must have at least 1 dimension")));
+
+	if (dim > SVECTOR_MAX_DIM)
+		ereport(ERROR,
+				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
+				 errmsg("svector cannot have more than %d dimensions", SVECTOR_MAX_DIM)));
+}
+
+/*
+ * Ensure valid nnz
+ */
+static inline void
+CheckNnz(int nnz, int dim)
+{
+	if (nnz < 0)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_EXCEPTION),
+				 errmsg("svector must have at least one element")));
+
+	if (nnz > dim)
+		ereport(ERROR,
+				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
+				 errmsg("svector cannot have more elements than dimensions")));
+}
+
+/*
+ * Ensure valid index
+ */
+static inline void
+CheckIndex(int32 *indices, int i, int dim)
+{
+	int32		index = indices[i];
+
+	if (index < 0)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_EXCEPTION),
+				 errmsg("index must not be negative")));
+
+	if (index >= dim)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_EXCEPTION),
+				 errmsg("index must be less than dimensions")));
+
+	if (i > 0)
+	{
+		if (index < indices[i - 1])
+			ereport(ERROR,
+					(errcode(ERRCODE_DATA_EXCEPTION),
+					 errmsg("indexes must be in ascending order")));
+
+		if (index == indices[i - 1])
+			ereport(ERROR,
+					(errcode(ERRCODE_DATA_EXCEPTION),
+					 errmsg("indexes must not contain duplicates")));
+	}
+}
+
+/*
+ * Ensure finite element
+ */
+static inline void
+CheckElement(float value)
+{
+	if (isnan(value))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_EXCEPTION),
+				 errmsg("NaN not allowed in svector")));
+
+	if (isinf(value))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_EXCEPTION),
+				 errmsg("infinite value not allowed in svector")));
+}
+
+/*
+ * Allocate and initialize a new sparse vector
+ */
+SVector *
+InitSVector(int dim, int nnz)
+{
+	SVector    *result;
+	int			size;
+
+	size = SVECTOR_SIZE(nnz);
+	result = (SVector *) palloc0(size);
+	SET_VARSIZE(result, size);
+	result->dim = dim;
+	result->nnz = nnz;
+
+	return result;
+}
+
+/*
+ * Convert textual representation to internal representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_in);
+Datum
+svector_in(PG_FUNCTION_ARGS)
+{
+	char	   *str = PG_GETARG_CSTRING(0);
+	int32		typmod = PG_GETARG_INT32(2);
+	int			dim;
+	char	   *pt;
+	SVector    *result;
+	float	   *rvalues;
+	char	   *lit = pstrdup(str);
+	int			n;
+	int32	   *indices;
+	float	   *values;
+	int			index;
+	float		value;
+	int			maxNnz;
+	int			nnz = 0;
+
+	/* TODO Improve code and checks after deciding on format */
+
+	maxNnz = 1;
+	pt = str;
+	while (*pt != '\0')
+	{
+		if (*pt == ',')
+			maxNnz++;
+
+		pt++;
+	}
+	maxNnz /= 2;
+
+	indices = palloc(maxNnz * sizeof(int32));
+	values = palloc(maxNnz * sizeof(float));
+
+	while (sscanf(str, "(%d,%f)%n", &index, &value, &n) == 2)
+	{
+		/* TODO Better error */
+		if (nnz == maxNnz)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("ran out of buffer: \"%s\"", lit)));
+
+		/* TODO Decide whether to store zero values */
+		indices[nnz] = index;
+		values[nnz] = value;
+		nnz++;
+
+		str += n;
+
+		if (*str == ',')
+			str++;
+		else if (*str == '|')
+			break;
+		else
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed svector literal: \"%s\"", lit)));
+	}
+
+	if (sscanf(str, "|%d|%n", &dim, &n) != 1)
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed svector literal: \"%s\"", lit)));
+
+	str += n;
+
+	if (*str != '\0')
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed svector literal: \"%s\"", lit),
+				 errdetail("Junk after closing pipe.")));
+
+	pfree(lit);
+
+	CheckDim(dim);
+	CheckExpectedDim(typmod, dim);
+
+	result = InitSVector(dim, nnz);
+	rvalues = SVECTOR_VALUES(result);
+	for (int i = 0; i < nnz; i++)
+	{
+		result->indices[i] = indices[i];
+		rvalues[i] = values[i];
+
+		CheckIndex(result->indices, i, dim);
+		CheckElement(rvalues[i]);
+	}
+
+	PG_RETURN_POINTER(result);
+}
+
+/*
+ * Convert internal representation to textual representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_out);
+Datum
+svector_out(PG_FUNCTION_ARGS)
+{
+	SVector    *svector = PG_GETARG_SVECTOR_P(0);
+	float	   *values = SVECTOR_VALUES(svector);
+	char	   *buf;
+	char	   *ptr;
+	int			n;
+
+	/* TODO Improve code after deciding on format */
+
+#if PG_VERSION_NUM < 120000
+	int			ndig = FLT_DIG + extra_float_digits;
+
+	if (ndig < 1)
+		ndig = 1;
+
+#define FLOAT_SHORTEST_DECIMAL_LEN (ndig + 10)
+#endif
+
+	/* TODO Move */
+#define APPEND_CHAR(ptr, ch) (*(ptr)++ = (ch))
+
+	/* TODO Improve */
+	buf = (char *) palloc((FLOAT_SHORTEST_DECIMAL_LEN + 20) * svector->nnz + 20);
+	ptr = buf;
+
+	for (int i = 0; i < svector->nnz; i++)
+	{
+		if (i > 0)
+			APPEND_CHAR(ptr, ',');
+
+		n = sprintf(ptr, "(%d,", svector->indices[i]);
+		ptr += n;
+
+#if PG_VERSION_NUM >= 120000
+		n = float_to_shortest_decimal_bufn(values[i], ptr);
+#else
+		n = sprintf(ptr, "%.*g", ndig, values[i]);
+#endif
+		ptr += n;
+
+		APPEND_CHAR(ptr, ')');
+	}
+
+	n = sprintf(ptr, "|%d|", svector->dim);
+	ptr += n;
+
+	APPEND_CHAR(ptr, '\0');
+
+	PG_FREE_IF_COPY(svector, 0);
+	PG_RETURN_CSTRING(buf);
+}
+
+/*
+ * Convert type modifier
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_typmod_in);
+Datum
+svector_typmod_in(PG_FUNCTION_ARGS)
+{
+	ArrayType  *ta = PG_GETARG_ARRAYTYPE_P(0);
+	int32	   *tl;
+	int			n;
+
+	tl = ArrayGetIntegerTypmods(ta, &n);
+
+	if (n != 1)
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				 errmsg("invalid type modifier")));
+
+	if (*tl < 1)
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				 errmsg("dimensions for type svector must be at least 1")));
+
+	if (*tl > SVECTOR_MAX_DIM)
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				 errmsg("dimensions for type svector cannot exceed %d", SVECTOR_MAX_DIM)));
+
+	PG_RETURN_INT32(*tl);
+}
+
+/*
+ * Convert external binary representation to internal representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_recv);
+Datum
+svector_recv(PG_FUNCTION_ARGS)
+{
+	StringInfo	buf = (StringInfo) PG_GETARG_POINTER(0);
+	int32		typmod = PG_GETARG_INT32(2);
+	SVector    *result;
+	int32		dim;
+	int32		nnz;
+	int32		unused;
+	float	   *values;
+
+	dim = pq_getmsgint(buf, sizeof(int32));
+	nnz = pq_getmsgint(buf, sizeof(int32));
+	unused = pq_getmsgint(buf, sizeof(int32));
+
+	CheckDim(dim);
+	CheckNnz(nnz, dim);
+	CheckExpectedDim(typmod, dim);
+
+	if (unused != 0)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_EXCEPTION),
+				 errmsg("expected unused to be 0, not %d", unused)));
+
+	result = InitSVector(dim, nnz);
+	values = SVECTOR_VALUES(result);
+
+	for (int i = 0; i < nnz; i++)
+	{
+		result->indices[i] = pq_getmsgint(buf, sizeof(int32));
+		CheckIndex(result->indices, i, dim);
+	}
+
+	for (int i = 0; i < nnz; i++)
+	{
+		values[i] = pq_getmsgfloat4(buf);
+		CheckElement(values[i]);
+	}
+
+	PG_RETURN_POINTER(result);
+}
+
+/*
+ * Convert internal representation to the external binary representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_send);
+Datum
+svector_send(PG_FUNCTION_ARGS)
+{
+	SVector    *svec = PG_GETARG_SVECTOR_P(0);
+	float	   *values = SVECTOR_VALUES(svec);
+	StringInfoData buf;
+
+	pq_begintypsend(&buf);
+	pq_sendint(&buf, svec->dim, sizeof(int32));
+	pq_sendint(&buf, svec->nnz, sizeof(int32));
+	pq_sendint(&buf, svec->unused, sizeof(int32));
+	for (int i = 0; i < svec->nnz; i++)
+		pq_sendint(&buf, svec->indices[i], sizeof(int32));
+	for (int i = 0; i < svec->nnz; i++)
+		pq_sendfloat4(&buf, values[i]);
+
+	PG_RETURN_BYTEA_P(pq_endtypsend(&buf));
+}
+
+/*
+ * Convert sparse vector to sparse vector
+ * This is needed to check the type modifier
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector);
+Datum
+svector(PG_FUNCTION_ARGS)
+{
+	SVector    *svec = PG_GETARG_SVECTOR_P(0);
+	int32		typmod = PG_GETARG_INT32(1);
+
+	CheckExpectedDim(typmod, svec->dim);
+
+	PG_RETURN_POINTER(svec);
+}
+
+/*
+ * Convert dense vector to sparse vector
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_to_svector);
+Datum
+vector_to_svector(PG_FUNCTION_ARGS)
+{
+	Vector	   *vec = PG_GETARG_VECTOR_P(0);
+	int32		typmod = PG_GETARG_INT32(1);
+	SVector    *result;
+	int			dim = vec->dim;
+	int			nnz = 0;
+	float	   *values;
+	int			j = 0;
+
+	CheckDim(dim);
+	CheckExpectedDim(typmod, dim);
+
+	for (int i = 0; i < dim; i++)
+	{
+		if (vec->x[i] != 0)
+			nnz++;
+	}
+
+	result = InitSVector(dim, nnz);
+	values = SVECTOR_VALUES(result);
+	for (int i = 0; i < dim; i++)
+	{
+		if (vec->x[i] != 0)
+		{
+			/* Safety check */
+			if (j == nnz)
+				elog(ERROR, "safety check failed");
+
+			result->indices[j] = i;
+			values[j] = vec->x[i];
+			j++;
+		}
+	}
+
+	PG_RETURN_POINTER(result);
+}
+
+/*
+ *  Get the L2 squared distance between sparse vectors
+ */
+static double
+l2_distance_squared_internal(SVector * a, SVector * b)
+{
+	float	   *ax = SVECTOR_VALUES(a);
+	float	   *bx = SVECTOR_VALUES(b);
+	double		distance = 0.0;
+	int			bpos = 0;
+
+	for (int i = 0; i < a->nnz; i++)
+	{
+		int			ai = a->indices[i];
+		int			bi = -1;
+
+		for (int j = bpos; j < b->nnz; j++)
+		{
+			bi = b->indices[j];
+
+			if (ai == bi)
+			{
+				double		diff = ax[i] - bx[j];
+
+				distance += diff * diff;
+			}
+			else if (ai > bi)
+				distance += bx[j] * bx[j];
+
+			/* Update start for next iteration */
+			if (ai >= bi)
+				bpos = j + 1;
+
+			/* Found or passed it */
+			if (bi >= ai)
+				break;
+		}
+
+		if (ai != bi)
+			distance += ax[i] * ax[i];
+	}
+
+	for (int j = bpos; j < b->nnz; j++)
+		distance += bx[j] * bx[j];
+
+	return distance;
+}
+
+/*
+ * Get the L2 distance between sparse vectors
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_l2_distance);
+Datum
+svector_l2_distance(PG_FUNCTION_ARGS)
+{
+	SVector    *a = PG_GETARG_SVECTOR_P(0);
+	SVector    *b = PG_GETARG_SVECTOR_P(1);
+
+	CheckDims(a, b);
+
+	PG_RETURN_FLOAT8(sqrt(l2_distance_squared_internal(a, b)));
+}
+
+/*
+ * Get the L2 squared distance between sparse vectors
+ * This saves a sqrt calculation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_l2_squared_distance);
+Datum
+svector_l2_squared_distance(PG_FUNCTION_ARGS)
+{
+	SVector    *a = PG_GETARG_SVECTOR_P(0);
+	SVector    *b = PG_GETARG_SVECTOR_P(1);
+
+	CheckDims(a, b);
+
+	PG_RETURN_FLOAT8(l2_distance_squared_internal(a, b));
+}
+
+/*
+ * Get the inner product of two sparse vectors
+ */
+static double
+inner_product_internal(SVector * a, SVector * b)
+{
+	float	   *ax = SVECTOR_VALUES(a);
+	float	   *bx = SVECTOR_VALUES(b);
+	double		distance = 0.0;
+	int			bpos = 0;
+
+	for (int i = 0; i < a->nnz; i++)
+	{
+		int			ai = a->indices[i];
+
+		for (int j = bpos; j < b->nnz; j++)
+		{
+			int			bi = b->indices[j];
+
+			/* Only update when the same index */
+			if (ai == bi)
+				distance += ax[i] * bx[j];
+
+			/* Update start for next iteration */
+			if (ai >= bi)
+				bpos = j + 1;
+
+			/* Found or passed it */
+			if (bi >= ai)
+				break;
+		}
+	}
+
+	return distance;
+}
+
+/*
+ * Get the inner product of two sparse vectors
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_inner_product);
+Datum
+svector_inner_product(PG_FUNCTION_ARGS)
+{
+	SVector    *a = PG_GETARG_SVECTOR_P(0);
+	SVector    *b = PG_GETARG_SVECTOR_P(1);
+
+	CheckDims(a, b);
+
+	PG_RETURN_FLOAT8(inner_product_internal(a, b));
+}
+
+/*
+ * Get the negative inner product of two sparse vectors
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_negative_inner_product);
+Datum
+svector_negative_inner_product(PG_FUNCTION_ARGS)
+{
+	SVector    *a = PG_GETARG_SVECTOR_P(0);
+	SVector    *b = PG_GETARG_SVECTOR_P(1);
+
+	CheckDims(a, b);
+
+	PG_RETURN_FLOAT8(-inner_product_internal(a, b));
+}
+
+/*
+ * Get the cosine distance between two sparse vectors
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_cosine_distance);
+Datum
+svector_cosine_distance(PG_FUNCTION_ARGS)
+{
+	SVector    *a = PG_GETARG_SVECTOR_P(0);
+	SVector    *b = PG_GETARG_SVECTOR_P(1);
+	float	   *ax = SVECTOR_VALUES(a);
+	float	   *bx = SVECTOR_VALUES(b);
+	float		norma = 0.0;
+	float		normb = 0.0;
+	double		similarity;
+
+	CheckDims(a, b);
+
+	similarity = inner_product_internal(a, b);
+
+	/* Auto-vectorized */
+	for (int i = 0; i < a->nnz; i++)
+		norma += ax[i] * ax[i];
+
+	/* Auto-vectorized */
+	for (int i = 0; i < b->nnz; i++)
+		normb += bx[i] * bx[i];
+
+	/* Use sqrt(a * b) over sqrt(a) * sqrt(b) */
+	similarity /= sqrt((double) norma * (double) normb);
+
+#ifdef _MSC_VER
+	/* /fp:fast may not propagate NaN */
+	if (isnan(similarity))
+		PG_RETURN_FLOAT8(NAN);
+#endif
+
+	/* Keep in range */
+	if (similarity > 1)
+		similarity = 1.0;
+	else if (similarity < -1)
+		similarity = -1.0;
+
+	PG_RETURN_FLOAT8(1.0 - similarity);
+}
+
+/*
+ * Get the weighted Jaccard distance between two sparse vectors
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_jaccard_distance);
+Datum
+svector_jaccard_distance(PG_FUNCTION_ARGS)
+{
+	SVector    *a = PG_GETARG_SVECTOR_P(0);
+	SVector    *b = PG_GETARG_SVECTOR_P(1);
+	float	   *ax = SVECTOR_VALUES(a);
+	float	   *bx = SVECTOR_VALUES(b);
+	double		num = 0.0;
+	double		denom = 0.0;
+	int			bpos = 0;
+
+	CheckDims(a, b);
+
+	/*
+	 * Weighted Jaccard distance is not defined for vectors with negative
+	 * values. Could check and return NaN if minimal impact on performance.
+	 */
+
+	for (int i = 0; i < a->nnz; i++)
+	{
+		int			ai = a->indices[i];
+		int			bi = -1;
+
+		for (int j = bpos; j < b->nnz; j++)
+		{
+			bi = b->indices[j];
+
+			if (ai == bi)
+			{
+				num += ax[i] < bx[j] ? ax[i] : bx[j];
+				denom += ax[i] > bx[j] ? ax[i] : bx[j];
+			}
+			else if (ai > bi)
+				denom += bx[j];
+
+			/* Update start for next iteration */
+			if (ai >= bi)
+				bpos = j + 1;
+
+			/* Found or passed it */
+			if (bi >= ai)
+				break;
+		}
+
+		if (ai != bi)
+			denom += ax[i];
+	}
+
+	for (int j = bpos; j < b->nnz; j++)
+		denom += bx[j];
+
+	if (denom > 0)
+		PG_RETURN_FLOAT8(1.0 - (num / denom));
+	else
+		PG_RETURN_FLOAT8(NAN);
+}
--- a/src/svector.h
+++ b/src/svector.h
@@ -0,0 +1,23 @@
+#ifndef SVECTOR_H
+#define SVECTOR_H
+
+#define SVECTOR_MAX_DIM 100000
+
+#define SVECTOR_SIZE(_nnz)		(offsetof(SVector, indices) + (_nnz) * sizeof(int32) + (_nnz * sizeof(float)))
+#define SVECTOR_VALUES(x)		((float *) (((char *) (x)) + offsetof(SVector, indices) + (x)->nnz * sizeof(int32)))
+#define DatumGetSVector(x)		((SVector *) PG_DETOAST_DATUM(x))
+#define PG_GETARG_SVECTOR_P(x)	DatumGetSVector(PG_GETARG_DATUM(x))
+#define PG_RETURN_SVECTOR_P(x)	PG_RETURN_POINTER(x)
+
+typedef struct SVector
+{
+	int32		vl_len_;		/* varlena header (do not touch directly!) */
+	int32		dim;			/* number of dimensions */
+	int32		nnz;
+	int32		unused;
+	int32		indices[FLEXIBLE_ARRAY_MEMBER];
+}			SVector;
+
+SVector    *InitSVector(int dim, int nnz);
+
+#endif
--- a/src/vector.c
+++ b/src/vector.c
@@ -9,6 +9,7 @@
 #include "lib/stringinfo.h"
 #include "libpq/pqformat.h"
 #include "port.h"				/* for strtof() */
+#include "svector.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/lsyscache.h"
@@ -1151,3 +1152,26 @@ vector_avg(PG_FUNCTION_ARGS)

 	PG_RETURN_POINTER(result);
 }
+
+/*
+ * Convert sparse vector to dense vector
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(svector_to_vector);
+Datum
+svector_to_vector(PG_FUNCTION_ARGS)
+{
+	SVector    *svec = PG_GETARG_SVECTOR_P(0);
+	int32		typmod = PG_GETARG_INT32(1);
+	Vector	   *result;
+	int			dim = svec->dim;
+	float	   *values = SVECTOR_VALUES(svec);
+
+	CheckDim(dim);
+	CheckExpectedDim(typmod, dim);
+
+	result = InitVector(dim);
+	for (int i = 0; i < svec->nnz; i++)
+		result->x[svec->indices[i]] = values[i];
+
+	PG_RETURN_POINTER(result);
+}
--- a/test/expected/functions.out
+++ b/test/expected/functions.out
@@ -54,85 +54,85 @@ SELECT vector_norm('[3e37,4e37]')::real;
       5e+37
 (1 row)

-SELECT l2_distance('[0,0]', '[3,4]');
+SELECT l2_distance('[0,0]'::vector, '[3,4]');
 l2_distance 
 -------------
           5
 (1 row)

-SELECT l2_distance('[0,0]', '[0,1]');
+SELECT l2_distance('[0,0]'::vector, '[0,1]');
 l2_distance 
 -------------
           1
 (1 row)

-SELECT l2_distance('[1,2]', '[3]');
+SELECT l2_distance('[1,2]'::vector, '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT l2_distance('[3e38]', '[-3e38]');
+SELECT l2_distance('[3e38]'::vector, '[-3e38]');
 l2_distance 
 -------------
    Infinity
 (1 row)

-SELECT inner_product('[1,2]', '[3,4]');
+SELECT inner_product('[1,2]'::vector, '[3,4]');
 inner_product 
 ---------------
            11
 (1 row)

-SELECT inner_product('[1,2]', '[3]');
+SELECT inner_product('[1,2]'::vector, '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT inner_product('[3e38]', '[3e38]');
+SELECT inner_product('[3e38]'::vector, '[3e38]');
 inner_product 
 ---------------
      Infinity
 (1 row)

-SELECT cosine_distance('[1,2]', '[2,4]');
+SELECT cosine_distance('[1,2]'::vector, '[2,4]');
 cosine_distance 
 -----------------
               0
 (1 row)

-SELECT cosine_distance('[1,2]', '[0,0]');
+SELECT cosine_distance('[1,2]'::vector, '[0,0]');
 cosine_distance 
 -----------------
             NaN
 (1 row)

-SELECT cosine_distance('[1,1]', '[1,1]');
+SELECT cosine_distance('[1,1]'::vector, '[1,1]');
 cosine_distance 
 -----------------
               0
 (1 row)

-SELECT cosine_distance('[1,0]', '[0,2]');
+SELECT cosine_distance('[1,0]'::vector, '[0,2]');
 cosine_distance 
 -----------------
               1
 (1 row)

-SELECT cosine_distance('[1,1]', '[-1,-1]');
+SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
 cosine_distance 
 -----------------
               2
 (1 row)

-SELECT cosine_distance('[1,2]', '[3]');
+SELECT cosine_distance('[1,2]'::vector, '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT cosine_distance('[1,1]', '[1.1,1.1]');
+SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
 cosine_distance 
 -----------------
               0
 (1 row)

-SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
+SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
 cosine_distance 
 -----------------
               2
 (1 row)

-SELECT cosine_distance('[3e38]', '[3e38]');
+SELECT cosine_distance('[3e38]'::vector, '[3e38]');
 cosine_distance 
 -----------------
             NaN
--- a/test/expected/svector.out
+++ b/test/expected/svector.out
@@ -0,0 +1,140 @@
+SELECT '(0,1.5),(2,3.5)|5|'::svector;
+      svector       
+--------------------
+ (0,1.5),(2,3.5)|5|
+(1 row)
+
+SELECT '(0,1.5),(2,3.5)|5|'::svector::vector;
+     vector      
+-----------------
+ [1.5,0,3.5,0,0]
+(1 row)
+
+SELECT '(0,1.5),(2,3.5)|5|'::svector::vector(5);
+     vector      
+-----------------
+ [1.5,0,3.5,0,0]
+(1 row)
+
+SELECT '(0,1.5),(2,3.5)|5|'::svector::vector(4);
+ERROR:  expected 4 dimensions, not 5
+SELECT '[0,1.5,0,3.5,0]'::vector::svector;
+      svector       
+--------------------
+ (1,1.5),(3,3.5)|5|
+(1 row)
+
+SELECT '(0,0),(1,1),(2,0)|3|'::svector;
+       svector        
+----------------------
+ (0,0),(1,1),(2,0)|3|
+(1 row)
+
+SELECT '|5|'::svector;
+ svector 
+---------
+ |5|
+(1 row)
+
+SELECT '|-1|'::svector;
+ERROR:  svector must have at least 1 dimension
+LINE 1: SELECT '|-1|'::svector;
+               ^
+SELECT '|100001|'::svector;
+ERROR:  svector cannot have more than 100000 dimensions
+LINE 1: SELECT '|100001|'::svector;
+               ^
+SELECT '|16001|'::svector::vector;
+ERROR:  vector cannot have more than 16000 dimensions
+SELECT '(-1,1)|1|'::svector;
+ERROR:  index must not be negative
+LINE 1: SELECT '(-1,1)|1|'::svector;
+               ^
+SELECT '(1,1)|1|'::svector;
+ERROR:  index must be less than dimensions
+LINE 1: SELECT '(1,1)|1|'::svector;
+               ^
+SELECT '|1|'::svector(2);
+ERROR:  expected 2 dimensions, not 1
+SELECT l2_distance('|2|'::svector, '(0,3),(1,4)|2|');
+ l2_distance 
+-------------
+           5
+(1 row)
+
+SELECT l2_distance('|2|'::svector, '(1,1)|2|');
+ l2_distance 
+-------------
+           1
+(1 row)
+
+SELECT '|2|'::svector <-> '(0,3),(1,4)|2|';
+ ?column? 
+----------
+        5
+(1 row)
+
+SELECT inner_product('(0,1),(1,2)|2|'::svector, '(0,2),(1,4)|2|');
+ inner_product 
+---------------
+            10
+(1 row)
+
+SELECT svector_negative_inner_product('(0,1),(1,2)|2|', '(0,2),(1,4)|2|');
+ svector_negative_inner_product 
+--------------------------------
+                            -10
+(1 row)
+
+SELECT cosine_distance('(0,1),(1,2)|2|'::svector, '(0,2),(1,4)|2|');
+ cosine_distance 
+-----------------
+               0
+(1 row)
+
+SELECT cosine_distance('(0,1),(1,2)|2|'::svector, '|2|');
+ cosine_distance 
+-----------------
+             NaN
+(1 row)
+
+SELECT cosine_distance('(0,1),(1,1)|2|'::svector, '(0,-1),(1,-1)|2|');
+ cosine_distance 
+-----------------
+               2
+(1 row)
+
+SELECT cosine_distance('(0,1)|2|'::svector, '(1,2)|2|');
+ cosine_distance 
+-----------------
+               1
+(1 row)
+
+SELECT cosine_distance('|1|'::svector, '|1|');
+ cosine_distance 
+-----------------
+             NaN
+(1 row)
+
+SELECT cosine_distance('(0,1)|2|'::svector, '(0,1)|3|');
+ERROR:  different svector dimensions 2 and 3
+SELECT jaccard_distance('(0,1)|2|', '(0,1)|2|');
+ jaccard_distance 
+------------------
+                0
+(1 row)
+
+SELECT jaccard_distance('(0,1)|2|', '(1,1)|2|');
+ jaccard_distance 
+------------------
+                1
+(1 row)
+
+SELECT jaccard_distance('|1|', '|1|');
+ jaccard_distance 
+------------------
+              NaN
+(1 row)
+
+SELECT jaccard_distance('(0,1)|2|', '(0,1)|3|');
+ERROR:  different svector dimensions 2 and 3
--- a/test/sql/functions.sql
+++ b/test/sql/functions.sql
@@ -13,24 +13,24 @@ SELECT vector_norm('[3,4]');
 SELECT vector_norm('[0,1]');
 SELECT vector_norm('[3e37,4e37]')::real;

-SELECT l2_distance('[0,0]', '[3,4]');
-SELECT l2_distance('[0,0]', '[0,1]');
-SELECT l2_distance('[1,2]', '[3]');
-SELECT l2_distance('[3e38]', '[-3e38]');
+SELECT l2_distance('[0,0]'::vector, '[3,4]');
+SELECT l2_distance('[0,0]'::vector, '[0,1]');
+SELECT l2_distance('[1,2]'::vector, '[3]');
+SELECT l2_distance('[3e38]'::vector, '[-3e38]');

-SELECT inner_product('[1,2]', '[3,4]');
-SELECT inner_product('[1,2]', '[3]');
-SELECT inner_product('[3e38]', '[3e38]');
+SELECT inner_product('[1,2]'::vector, '[3,4]');
+SELECT inner_product('[1,2]'::vector, '[3]');
+SELECT inner_product('[3e38]'::vector, '[3e38]');

-SELECT cosine_distance('[1,2]', '[2,4]');
-SELECT cosine_distance('[1,2]', '[0,0]');
-SELECT cosine_distance('[1,1]', '[1,1]');
-SELECT cosine_distance('[1,0]', '[0,2]');
-SELECT cosine_distance('[1,1]', '[-1,-1]');
-SELECT cosine_distance('[1,2]', '[3]');
-SELECT cosine_distance('[1,1]', '[1.1,1.1]');
-SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
-SELECT cosine_distance('[3e38]', '[3e38]');
+SELECT cosine_distance('[1,2]'::vector, '[2,4]');
+SELECT cosine_distance('[1,2]'::vector, '[0,0]');
+SELECT cosine_distance('[1,1]'::vector, '[1,1]');
+SELECT cosine_distance('[1,0]'::vector, '[0,2]');
+SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
+SELECT cosine_distance('[1,2]'::vector, '[3]');
+SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
+SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
+SELECT cosine_distance('[3e38]'::vector, '[3e38]');

 SELECT l1_distance('[0,0]', '[3,4]');
 SELECT l1_distance('[0,0]', '[0,1]');
--- a/test/sql/svector.sql
+++ b/test/sql/svector.sql
@@ -0,0 +1,36 @@
+SELECT '(0,1.5),(2,3.5)|5|'::svector;
+SELECT '(0,1.5),(2,3.5)|5|'::svector::vector;
+SELECT '(0,1.5),(2,3.5)|5|'::svector::vector(5);
+SELECT '(0,1.5),(2,3.5)|5|'::svector::vector(4);
+SELECT '[0,1.5,0,3.5,0]'::vector::svector;
+
+SELECT '(0,0),(1,1),(2,0)|3|'::svector;
+
+SELECT '|5|'::svector;
+SELECT '|-1|'::svector;
+SELECT '|100001|'::svector;
+SELECT '|16001|'::svector::vector;
+
+SELECT '(-1,1)|1|'::svector;
+SELECT '(1,1)|1|'::svector;
+
+SELECT '|1|'::svector(2);
+
+SELECT l2_distance('|2|'::svector, '(0,3),(1,4)|2|');
+SELECT l2_distance('|2|'::svector, '(1,1)|2|');
+SELECT '|2|'::svector <-> '(0,3),(1,4)|2|';
+
+SELECT inner_product('(0,1),(1,2)|2|'::svector, '(0,2),(1,4)|2|');
+SELECT svector_negative_inner_product('(0,1),(1,2)|2|', '(0,2),(1,4)|2|');
+
+SELECT cosine_distance('(0,1),(1,2)|2|'::svector, '(0,2),(1,4)|2|');
+SELECT cosine_distance('(0,1),(1,2)|2|'::svector, '|2|');
+SELECT cosine_distance('(0,1),(1,1)|2|'::svector, '(0,-1),(1,-1)|2|');
+SELECT cosine_distance('(0,1)|2|'::svector, '(1,2)|2|');
+SELECT cosine_distance('|1|'::svector, '|1|');
+SELECT cosine_distance('(0,1)|2|'::svector, '(0,1)|3|');
+
+SELECT jaccard_distance('(0,1)|2|', '(0,1)|2|');
+SELECT jaccard_distance('(0,1)|2|', '(1,1)|2|');
+SELECT jaccard_distance('|1|', '|1|');
+SELECT jaccard_distance('(0,1)|2|', '(0,1)|3|');
--- a/test/t/019_hnsw_filtering.pl
+++ b/test/t/019_hnsw_filtering.pl
@@ -1,107 +0,0 @@
-use strict;
-use warnings;
-use PostgresNode;
-use TestLib;
-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 $nc = 50;
-
-sub test_recall
-{
-	my ($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;
-
-		my @expected_ids = split("\n", $expected[$i]);
-
-		foreach (@expected_ids)
-		{
-			if (exists($actual_set{$_}))
-			{
-				$correct++;
-			}
-			$total++;
-		}
-	}
-
-	cmp_ok($correct / $total, ">=", $min, $operator);
-}
-
-# Initialize node
-$node = get_new_node('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c int8);");
-$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", "CREATE INDEX ON tst USING hnsw (v vector_l2_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) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c, v vector_l2_ops);");
-like($stderr, qr/first column must be a vector/);
-
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, c, c);");
-like($stderr, qr/index cannot have more than two columns/);
-
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, v vector_l2_ops);");
-like($stderr, qr/column 2 cannot be a vector/);
-
-done_testing();
Author	SHA1	Message	Date
Andrew Kane	f90d52d562	Added test for explicit zeros [skip ci]	2023-11-06 14:29:52 -08:00
Andrew Kane	22a1b06924	Added todo [skip ci]	2023-11-05 21:26:28 -08:00
Andrew Kane	b17b9c1ca2	Updated version [skip ci]	2023-11-05 18:21:09 -08:00
Andrew Kane	492ae1225c	Added support for sparse vectors	2023-11-05 18:12:19 -08:00