Fixed logic [skip ci]

CHANGELOG.md

@@ -1,6 +1,6 @@
 ## 0.6.0 (unreleased)
 
-- Added support for sparse vectors
+- Added support for inline filtering with HNSW
 
 ## 0.5.1 (2023-10-10)
 

Makefile

@@ -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/svector.o src/vector.o
+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/svector.h src/vector.h
+HEADERS = src/vector.h
 
 TESTS = $(wildcard test/sql/*.sql)
 REGRESS = $(patsubst test/sql/%.sql,%,$(TESTS))

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\svector.obj src\vector.obj
+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\svector.h src\vector.h
+HEADERS = 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)

README.md

@@ -315,6 +315,12 @@ 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
@@ -369,26 +375,6 @@ 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.
@@ -732,6 +718,7 @@ Thanks to:
 - [k-means++: The Advantage of Careful Seeding](https://theory.stanford.edu/~sergei/papers/kMeansPP-soda.pdf)
 - [Concept Decompositions for Large Sparse Text Data using Clustering](https://www.cs.utexas.edu/users/inderjit/public_papers/concept_mlj.pdf)
 - [Efficient and Robust Approximate Nearest Neighbor Search using Hierarchical Navigable Small World Graphs](https://arxiv.org/ftp/arxiv/papers/1603/1603.09320.pdf)
+- [HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints](https://arxiv.org/pdf/2207.07940.pdf)
 
 ## History
 

sql/vector--0.5.1--0.6.0.sql

@@ -1,79 +1,10 @@
 -- 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 TYPE svector;
+CREATE FUNCTION hnsw_attribute_distance(integer, integer) RETURNS float8
+	AS 'MODULE_PATHNAME', 'hnsw_int4_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
 
-CREATE FUNCTION svector_in(cstring, oid, integer) RETURNS svector
+CREATE OPERATOR CLASS vector_integer_ops
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+	DEFAULT FOR TYPE integer USING hnsw AS
-
+	OPERATOR 2 = (integer, integer),
-CREATE FUNCTION svector_out(svector) RETURNS cstring
+	FUNCTION 3 hnsw_attribute_distance(integer, integer);
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-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 = '<=>'
-);

sql/vector.sql

@@ -291,91 +291,12 @@ CREATE OPERATOR CLASS vector_cosine_ops
 	FUNCTION 1 vector_negative_inner_product(vector, vector),
 	FUNCTION 2 vector_norm(vector);
 
---- svector type
+-- hnsw attributes
 
-CREATE TYPE svector;
+CREATE FUNCTION hnsw_attribute_distance(integer, integer) RETURNS float8
+	AS 'MODULE_PATHNAME', 'hnsw_int4_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
 
-CREATE FUNCTION svector_in(cstring, oid, integer) RETURNS svector
+CREATE OPERATOR CLASS vector_integer_ops
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+	DEFAULT FOR TYPE integer USING hnsw AS
-
+	OPERATOR 2 = (integer, integer),
-CREATE FUNCTION svector_out(svector) RETURNS cstring
+	FUNCTION 3 hnsw_attribute_distance(integer, integer);
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-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 = '<=>'
-);

src/hnsw.c

@@ -167,7 +167,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 	IndexAmRoutine *amroutine = makeNode(IndexAmRoutine);
 
 	amroutine->amstrategies = 0;
-	amroutine->amsupport = 2;
+	amroutine->amsupport = 3;
 #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 = false;
+	amroutine->amcanmulticol = true;
 	amroutine->amoptionalkey = true;
 	amroutine->amsearcharray = false;
 	amroutine->amsearchnulls = false;
@@ -222,3 +222,17 @@ hnswhandler(PG_FUNCTION_ARGS)
 
 	PG_RETURN_POINTER(amroutine);
 }
+
+/*
+ * Get the distance between two int4 attributes
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(hnsw_int4_attribute_distance);
+Datum
+hnsw_int4_attribute_distance(PG_FUNCTION_ARGS)
+{
+	int32		a = PG_GETARG_INT32(0);
+	int32		b = PG_GETARG_INT32(1);
+	double		distance = ((double) a) - ((double) b);
+
+	PG_RETURN_FLOAT8(distance);
+}

src/hnsw.h

@@ -19,6 +19,7 @@
 /* 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
@@ -59,7 +60,7 @@
 
 #define HNSW_MAX_SIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - sizeof(ItemIdData))
 
-#define HNSW_ELEMENT_TUPLE_SIZE(_dim)	MAXALIGN(offsetof(HnswElementTupleData, vec) + VECTOR_SIZE(_dim))
+#define HNSW_ELEMENT_TUPLE_SIZE(size)	MAXALIGN(offsetof(HnswElementTupleData, data) + (size))
 #define HNSW_NEIGHBOR_TUPLE_SIZE(level, m)	MAXALIGN(offsetof(HnswNeighborTupleData, indextids) + ((level) + 2) * (m) * sizeof(ItemPointerData))
 
 #define HnswPageGetOpaque(page)	((HnswPageOpaque) PageGetSpecialPointer(page))
@@ -103,7 +104,8 @@ typedef struct HnswElementData
 	OffsetNumber offno;
 	OffsetNumber neighborOffno;
 	BlockNumber neighborPage;
-	Vector	   *vec;
+	Datum		value;
+	IndexTuple	itup;
 }			HnswElementData;
 
 typedef HnswElementData * HnswElement;
@@ -112,6 +114,7 @@ typedef struct HnswCandidate
 {
 	HnswElement element;
 	float		distance;
+	bool		matches;
 	bool		closer;
 }			HnswCandidate;
 
@@ -154,17 +157,18 @@ typedef struct HnswBuildState
 	double		reltuples;
 
 	/* Support functions */
-	FmgrInfo   *procinfo;
+	FmgrInfo  **procinfos;
 	FmgrInfo   *normprocinfo;
-	Oid			collation;
+	Oid		   *collations;
 
 	/* Variables */
 	List	   *elements;
 	HnswElement entryPoint;
 	double		ml;
 	int			maxLevel;
-	double		maxInMemoryElements;
+	long		memoryLeft;
 	bool		flushed;
+	bool		useIndexTuple;
 	Vector	   *normvec;
 
 	/* Memory */
@@ -204,7 +208,7 @@ typedef struct HnswElementTupleData
 	ItemPointerData heaptids[HNSW_HEAPTIDS];
 	ItemPointerData neighbortid;
 	uint16		unused2;
-	Vector		vec;
+	Vector		data;
 }			HnswElementTupleData;
 
 typedef HnswElementTupleData * HnswElementTuple;
@@ -226,9 +230,9 @@ typedef struct HnswScanOpaqueData
 	MemoryContext tmpCtx;
 
 	/* Support functions */
-	FmgrInfo   *procinfo;
+	FmgrInfo  **procinfos;
 	FmgrInfo   *normprocinfo;
-	Oid			collation;
+	Oid		   *collations;
 }			HnswScanOpaqueData;
 
 typedef HnswScanOpaqueData * HnswScanOpaque;
@@ -246,8 +250,8 @@ typedef struct HnswVacuumState
 	int			efConstruction;
 
 	/* Support functions */
-	FmgrInfo   *procinfo;
+	FmgrInfo  **procinfos;
-	Oid			collation;
+	Oid		   *collations;
 
 	/* Variables */
 	HTAB	   *deleted;
@@ -269,26 +273,27 @@ 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, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
+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);
 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 *procinfo, Oid collation, int m, int efConstruction, bool existing);
+void		HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo **procinfos, Oid *collations, int m, int efConstruction, bool existing, bool inMemory);
-HnswElement HnswFindDuplicate(HnswElement e);
+HnswElement HnswFindDuplicate(HnswElement e, Relation index);
-HnswCandidate *HnswEntryCandidate(HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
+HnswCandidate *HnswEntryCandidate(HnswElement em, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation rel, FmgrInfo **procinfos, Oid *collations, bool loadVec, bool inMemory);
 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 *procinfo, Oid collation, HnswElement e, int m, bool checkExisting);
+void		HnswUpdateNeighborPages(Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement e, int m, bool checkExisting);
-void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
+void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index);
-void		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
+void		HnswLoadElement(HnswElement element, float *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations, bool loadVec);
-void		HnswSetElementTuple(HnswElementTuple etup, HnswElement element);
+void		HnswSetElementTuple(HnswElementTuple etup, HnswElement element, bool useIndexTuple);
-void		HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
+void		HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo **procinfos, Oid *collations, bool inMemory);
 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);
@@ -305,5 +310,6 @@ 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

src/hnswbuild.c

@@ -8,6 +8,7 @@
 #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
@@ -105,8 +106,8 @@ CreateElementPages(HnswBuildState * buildstate)
 {
 	Relation	index = buildstate->index;
 	ForkNumber	forkNum = buildstate->forkNum;
-	int			dimensions = buildstate->dimensions;
+	bool		useIndexTuple = buildstate->useIndexTuple;
-	Size		etupSize;
+	Size		etupAllocSize;
 	Size		maxSize;
 	HnswElementTuple etup;
 	HnswNeighborTuple ntup;
@@ -117,11 +118,11 @@ CreateElementPages(HnswBuildState * buildstate)
 	ListCell   *lc;
 
 	/* Calculate sizes */
+	etupAllocSize = BLCKSZ;
 	maxSize = HNSW_MAX_SIZE;
-	etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);
 
 	/* Allocate once */
-	etup = palloc0(etupSize);
+	etup = palloc0(etupAllocSize);
 	ntup = palloc0(BLCKSZ);
 
 	/* Prepare first page */
@@ -133,15 +134,24 @@ CreateElementPages(HnswBuildState * buildstate)
 	foreach(lc, buildstate->elements)
 	{
 		HnswElement element = lfirst(lc);
+		Size		etupSize;
 		Size		ntupSize;
 		Size		combinedSize;
 
-		HnswSetElementTuple(etup, element);
+		/* Zero memory for each element */
+		MemSet(etup, 0, etupAllocSize);
 
 		/* 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);
@@ -264,13 +274,15 @@ FlushPages(HnswBuildState * buildstate)
  * Insert tuple
  */
 static bool
-InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState * buildstate, HnswElement * dup)
+InsertTuple(Relation index, Datum *values, bool *isnull, HnswElement element, HnswBuildState * buildstate, HnswElement * dup, MemoryContext outerCtx)
 {
-	FmgrInfo   *procinfo = buildstate->procinfo;
+	FmgrInfo  **procinfos = buildstate->procinfos;
-	Oid			collation = buildstate->collation;
+	Oid		   *collations = buildstate->collations;
 	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]));
@@ -278,18 +290,20 @@ InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState *
 	/* Normalize if needed */
 	if (buildstate->normprocinfo != NULL)
 	{
-		if (!HnswNormValue(buildstate->normprocinfo, collation, &value, buildstate->normvec))
+		if (!HnswNormValue(buildstate->normprocinfo, collations[0], &value, buildstate->normvec))
 			return false;
 	}
 
 	/* Copy value to element so accessible outside of memory context */
-	memcpy(element->vec, DatumGetVector(value), VECTOR_SIZE(buildstate->dimensions));
+	oldCtx = MemoryContextSwitchTo(outerCtx);
+	HnswElementSetData(element, index, value, values, isnull);
+	MemoryContextSwitchTo(oldCtx);
 
 	/* Insert element in graph */
-	HnswInsertElement(element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
+	HnswInsertElement(element, entryPoint, index, procinfos, collations, m, efConstruction, false, inMemory);
 
 	/* Look for duplicate */
-	*dup = HnswFindDuplicate(element);
+	*dup = HnswFindDuplicate(element, index);
 
 	/* Update neighbors if needed */
 	if (*dup == NULL)
@@ -300,7 +314,7 @@ InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState *
 			HnswNeighborArray *neighbors = &element->neighbors[lc];
 
 			for (int i = 0; i < neighbors->length; i++)
-				HnswUpdateConnection(element, &neighbors->items[i], lm, lc, NULL, NULL, procinfo, collation);
+				HnswUpdateConnection(element, &neighbors->items[i], lm, lc, NULL, index, procinfos, collations, inMemory);
 		}
 	}
 
@@ -313,6 +327,21 @@ InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState *
 	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
  */
@@ -334,7 +363,7 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 	if (isnull[0])
 		return;
 
-	if (buildstate->indtuples >= buildstate->maxInMemoryElements)
+	if (buildstate->memoryLeft <= 0)
 	{
 		if (!buildstate->flushed)
 		{
@@ -360,13 +389,12 @@ 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, element, buildstate, &dup);
+	inserted = InsertTuple(index, values, isnull, element, buildstate, &dup, oldCtx);
 
 	/* Reset memory context */
 	MemoryContextSwitchTo(oldCtx);
@@ -374,31 +402,21 @@ 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
  */
@@ -414,6 +432,19 @@ 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");
@@ -428,16 +459,17 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->indtuples = 0;
 
 	/* Get support functions */
-	buildstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+	buildstate->procinfos = HnswInitProcinfos(index);
 	buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	buildstate->collation = index->rd_indcollation[0];
+	buildstate->collations = index->rd_indcollation;
 
 	buildstate->elements = NIL;
 	buildstate->entryPoint = NULL;
 	buildstate->ml = HnswGetMl(buildstate->m);
 	buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
-	buildstate->maxInMemoryElements = HnswGetMaxInMemoryElements(buildstate->m, buildstate->ml, buildstate->dimensions);
+	buildstate->memoryLeft = maintenance_work_mem * 1024L;
 	buildstate->flushed = false;
+	buildstate->useIndexTuple = IndexRelationGetNumberOfAttributes(index) > 1;
 
 	/* Reuse for each tuple */
 	buildstate->normvec = InitVector(buildstate->dimensions);
@@ -453,6 +485,7 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 static void
 FreeBuildState(HnswBuildState * buildstate)
 {
+	pfree(buildstate->procinfos);
 	pfree(buildstate->normvec);
 	MemoryContextDelete(buildstate->tmpCtx);
 }

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(dimensions);
+	etupSize = HNSW_ELEMENT_TUPLE_SIZE(useIndexTuple ? IndexTupleSize(e->itup) : VARSIZE_ANY(DatumGetPointer(e->value)));
 	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);
+	HnswSetElementTuple(etup, e, useIndexTuple);
 
 	/* 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 *procinfo, Oid collation, HnswElement e, int m, bool checkExisting)
+HnswUpdateNeighborPages(Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement e, int m, bool checkExisting)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -334,7 +334,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			 */
 
 			/* Select neighbors */
-			HnswUpdateConnection(e, hc, lm, lc, &idx, index, procinfo, collation);
+			HnswUpdateConnection(e, hc, lm, lc, &idx, index, procinfos, collations, false);
 
 			/* New element was not selected as a neighbor */
 			if (idx == -1)
@@ -405,8 +405,9 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	Buffer		buf;
 	Page		page;
 	GenericXLogState *state;
-	Size		etupSize = HNSW_ELEMENT_TUPLE_SIZE(dup->vec->dim);
+	ItemId		itemid;
 	HnswElementTuple etup;
+	Size		etupSize;
 	int			i;
 
 	/* Read page */
@@ -416,7 +417,9 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	page = GenericXLogRegisterBuffer(state, buf, 0);
 
 	/* Find space */
-	etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, dup->offno));
+	itemid = PageGetItemId(page, dup->offno);
+	etup = (HnswElementTuple) PageGetItem(page, itemid);
+	etupSize = ItemIdGetLength(itemid);
 	for (i = 0; i < HNSW_HEAPTIDS; i++)
 	{
 		if (!ItemPointerIsValid(&etup->heaptids[i]))
@@ -449,7 +452,7 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
  * Write changes to disk
  */
 static void
-WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint)
+WriteElement(Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
@@ -468,7 +471,7 @@ WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement elem
 		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false);
+	HnswUpdateNeighborPages(index, procinfos, collations, element, m, false);
 
 	/* Update metapage if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -487,8 +490,8 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	HnswElement element;
 	int			m;
 	int			efConstruction = HnswGetEfConstruction(index);
-	FmgrInfo   *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+	FmgrInfo  **procinfos = HnswInitProcinfos(index);
-	Oid			collation = index->rd_indcollation[0];
+	Oid		   *collations = index->rd_indcollation;
 	HnswElement dup;
 	LOCKMODE	lockmode = ShareLock;
 
@@ -499,7 +502,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
 	if (normprocinfo != NULL)
 	{
-		if (!HnswNormValue(normprocinfo, collation, &value, NULL))
+		if (!HnswNormValue(normprocinfo, collations[0], &value, NULL))
 			return false;
 	}
 
@@ -515,7 +518,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 
 	/* Create an element */
 	element = HnswInitElement(heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m));
-	element->vec = DatumGetVector(value);
+	HnswElementSetData(element, index, value, values, isnull);
 
 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -532,13 +535,13 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	}
 
 	/* Insert element in graph */
-	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, false);
+	HnswInsertElement(element, entryPoint, index, procinfos, collations, m, efConstruction, false, false);
 
 	/* Look for duplicate */
-	dup = HnswFindDuplicate(element);
+	dup = HnswFindDuplicate(element, index);
 
 	/* Write to disk */
-	WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint);
+	WriteElement(index, procinfos, collations, element, m, efConstruction, dup, entryPoint);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);

src/hnswscan.c

@@ -15,12 +15,13 @@ GetScanItems(IndexScanDesc scan, Datum q)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 	Relation	index = scan->indexRelation;
-	FmgrInfo   *procinfo = so->procinfo;
+	FmgrInfo  **procinfos = so->procinfos;
-	Oid			collation = so->collation;
+	Oid		   *collations = so->collations;
 	List	   *ep;
 	List	   *w;
 	int			m;
 	HnswElement entryPoint;
+	ScanKeyData *keyData = scan->keyData;
 
 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
@@ -28,15 +29,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	if (entryPoint == NULL)
 		return NIL;
 
-	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, false));
+	ep = list_make1(HnswEntryCandidate(entryPoint, q, NULL, keyData, index, procinfos, collations, false, false));
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
+		w = HnswSearchLayer(q, NULL, keyData, ep, 1, lc, index, procinfos, collations, m, false, NULL, false);
 		ep = w;
 	}
 
-	return HnswSearchLayer(q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
+	return HnswSearchLayer(q, NULL, keyData, ep, hnsw_ef_search, 0, index, procinfos, collations, m, false, NULL, false);
 }
 
 /*
@@ -83,7 +84,7 @@ GetScanValue(IndexScanDesc scan)
 
 		/* Fine if normalization fails */
 		if (so->normprocinfo != NULL)
-			HnswNormValue(so->normprocinfo, so->collation, &value, NULL);
+			HnswNormValue(so->normprocinfo, so->collations[0], &value, NULL);
 	}
 
 	return value;
@@ -107,9 +108,9 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 									   ALLOCSET_DEFAULT_SIZES);
 
 	/* Set support functions */
-	so->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+	so->procinfos = HnswInitProcinfos(index);
 	so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	so->collation = index->rd_indcollation[0];
+	so->collations = index->rd_indcollation;
 
 	scan->opaque = so;
 
@@ -206,6 +207,9 @@ 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;
 	}
@@ -222,6 +226,7 @@ hnswendscan(IndexScanDesc scan)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 
+	pfree(so->procinfos);
 	MemoryContextDelete(so->tmpCtx);
 
 	pfree(so);

src/hnswutils.c

@@ -4,8 +4,13 @@
 
 #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
  */
@@ -46,6 +51,22 @@ 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
  *
@@ -173,6 +194,7 @@ HnswInitElement(ItemPointer heaptid, int m, double ml, int maxLevel)
 
 	element->level = level;
 	element->deleted = 0;
+	element->itup = NULL;
 
 	HnswInitNeighbors(element, m);
 
@@ -187,7 +209,8 @@ HnswFreeElement(HnswElement element)
 {
 	HnswFreeNeighbors(element);
 	list_free_deep(element->heaptids);
-	pfree(element->vec);
+	if (element->itup)
+		pfree(element->itup);
 	pfree(element);
 }
 
@@ -214,7 +237,8 @@ HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno)
 	element->blkno = blkno;
 	element->offno = offno;
 	element->neighbors = NULL;
-	element->vec = NULL;
+	element->value = PointerGetDatum(NULL);
+	element->itup = NULL;
 	return element;
 }
 
@@ -312,7 +336,7 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
  * Set element tuple, except for neighbor info
  */
 void
-HnswSetElementTuple(HnswElementTuple etup, HnswElement element)
+HnswSetElementTuple(HnswElementTuple etup, HnswElement element, bool useIndexTuple)
 {
 	etup->type = HNSW_ELEMENT_TUPLE_TYPE;
 	etup->level = element->level;
@@ -324,7 +348,11 @@ HnswSetElementTuple(HnswElementTuple etup, HnswElement element)
 		else
 			ItemPointerSetInvalid(&etup->heaptids[i]);
 	}
-	memcpy(&etup->vec, element->vec, VECTOR_SIZE(element->vec->dim));
+
+	if (useIndexTuple)
+		memcpy(&etup->data, element->itup, IndexTupleSize(element->itup));
+	else
+		memcpy(&etup->data, DatumGetPointer(element->value), VARSIZE_ANY(DatumGetPointer(element->value)));
 }
 
 /*
@@ -425,7 +453,7 @@ HnswLoadNeighbors(HnswElement element, Relation index, int m)
  * Load an element from a tuple
  */
 void
-HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec)
+HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index)
 {
 	element->level = etup->level;
 	element->deleted = etup->deleted;
@@ -447,16 +475,157 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
 
 	if (loadVec)
 	{
-		element->vec = palloc(VECTOR_SIZE(etup->vec.dim));
+		if (IndexRelationGetNumberOfAttributes(index) > 1)
-		memcpy(element->vec, &etup->vec, VECTOR_SIZE(etup->vec.dim));
+		{
+			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);
+		}
 	}
 }
 
+/*
+ * 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, bool *matches)
+{
+	double		g = DatumGetFloat8(FunctionCall2Coll(procinfos[0], collations[0], q, vec));
+
+	Assert(PointerIsValid(matches));
+	*matches = true;
+
+	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;
+						*matches = false;
+					}
+				}
+				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;
+
+					*matches = false;
+				}
+			}
+
+			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, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
+HnswLoadElement(HnswElement element, float *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations, bool loadVec)
 {
 	Buffer		buf;
 	Page		page;
@@ -472,11 +641,27 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
 	Assert(HnswIsElementTuple(etup));
 
 	/* Load element */
-	HnswLoadElementFromTuple(element, etup, true, loadVec);
+	HnswLoadElementFromTuple(element, etup, true, loadVec, index);
 
 	/* Calculate distance */
 	if (distance != NULL)
-		*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->vec)));
+	{
+		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, matches);
+	}
 
 	UnlockReleaseBuffer(buf);
 }
@@ -485,24 +670,24 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
  * Get the distance for a candidate
  */
 static float
-GetCandidateDistance(HnswCandidate * hc, Datum q, FmgrInfo *procinfo, Oid collation)
+GetCandidateDistance(HnswCandidate * hc, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations)
 {
-	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, PointerGetDatum(hc->element->vec)));
+	return GetDistance(hc->element->itup, hc->element->value, q, qtup, keyData, index, procinfos, collations, &hc->matches);
 }
 
 /*
  * Create a candidate for the entry point
  */
 HnswCandidate *
-HnswEntryCandidate(HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
+HnswEntryCandidate(HnswElement entryPoint, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations, bool loadVec, bool inMemory)
 {
 	HnswCandidate *hc = palloc(sizeof(HnswCandidate));
 
 	hc->element = entryPoint;
-	if (index == NULL)
+	if (inMemory)
-		hc->distance = GetCandidateDistance(hc, q, procinfo, collation);
+		hc->distance = GetCandidateDistance(hc, q, qtup, keyData, index, procinfos, collations);
 	else
-		HnswLoadElement(hc->element, &hc->distance, &q, index, procinfo, collation, loadVec);
+		HnswLoadElement(hc->element, &hc->distance, &hc->matches, &q, qtup, keyData, index, procinfos, collations, loadVec);
 	return hc;
 }
 
@@ -552,9 +737,9 @@ CreatePairingHeapNode(HnswCandidate * c)
  * Add to visited
  */
 static inline void
-AddToVisited(HTAB *v, HnswCandidate * hc, Relation index, bool *found)
+AddToVisited(HTAB *v, HnswCandidate * hc, bool inMemory, bool *found)
 {
-	if (index == NULL)
+	if (inMemory)
 		hash_search(v, &hc->element, HASH_ENTER, found);
 	else
 	{
@@ -569,7 +754,7 @@ AddToVisited(HTAB *v, HnswCandidate * hc, Relation index, bool *found)
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
+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)
 {
 	ListCell   *lc2;
 
@@ -577,11 +762,13 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 	pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
 	pairingheap *W = pairingheap_allocate(CompareFurthestCandidates, NULL);
 	int			wlen = 0;
+	uint64		additional = 0;
+	uint64		maxAdditional = keyData ? 4 * ef : 0;
 	HASHCTL		hash_ctl;
 	HTAB	   *v;
 
 	/* Create hash table */
-	if (index == NULL)
+	if (inMemory)
 	{
 		hash_ctl.keysize = sizeof(HnswElement *);
 		hash_ctl.entrysize = sizeof(HnswElement *);
@@ -600,11 +787,18 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 	{
 		HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
 
-		AddToVisited(v, hc, index, NULL);
+		AddToVisited(v, hc, inMemory, NULL);
 
 		pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node));
 		pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node));
 
+		/* Do not count elements that do not match filter towards ef */
+		if (!hc->matches)
+		{
+			if ((++additional) <= maxAdditional)
+				continue;
+		}
+
 		/*
 		 * Do not count elements being deleted towards ef when vacuuming. It
 		 * would be ideal to do this for inserts as well, but this could
@@ -634,7 +828,7 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 			HnswCandidate *e = &neighborhood->items[i];
 			bool		visited;
 
-			AddToVisited(v, e, index, &visited);
+			AddToVisited(v, e, inMemory, &visited);
 
 			if (!visited)
 			{
@@ -642,10 +836,10 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 
 				f = ((HnswPairingHeapNode *) pairingheap_first(W))->inner;
 
-				if (index == NULL)
+				if (inMemory)
-					eDistance = GetCandidateDistance(e, q, procinfo, collation);
+					eDistance = GetCandidateDistance(e, q, qtup, keyData, index, procinfos, collations);
 				else
-					HnswLoadElement(e->element, &eDistance, &q, index, procinfo, collation, inserting);
+					HnswLoadElement(e->element, &eDistance, &e->matches, &q, qtup, keyData, index, procinfos, collations, loadVec);
 
 				Assert(!e->element->deleted);
 
@@ -671,6 +865,16 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 					 */
 					if (skipElement == NULL || list_length(e->element->heaptids) != 0)
 					{
+						/*
+						 * Do not count elements that do not match filter
+						 * towards ef
+						 */
+						if (!e->matches)
+						{
+							if ((++additional) <= maxAdditional)
+								continue;
+						}
+
 						wlen++;
 
 						/* No need to decrement wlen */
@@ -725,8 +929,10 @@ CompareCandidateDistances(const void *a, const void *b)
  * Calculate the distance between elements
  */
 static float
-HnswGetDistance(HnswElement a, HnswElement b, int lc, FmgrInfo *procinfo, Oid collation)
+HnswGetCachedDistance(HnswElement a, HnswElement b, int lc, Relation index, FmgrInfo **procinfos, Oid *collations)
 {
+	bool		matches;
+
 	/* Look for cached distance */
 	if (a->neighbors != NULL)
 	{
@@ -750,21 +956,21 @@ HnswGetDistance(HnswElement a, HnswElement b, int lc, FmgrInfo *procinfo, Oid co
 		}
 	}
 
-	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(a->vec), PointerGetDatum(b->vec)));
+	return GetDistance(a->itup, a->value, b->value, b->itup, NULL, index, procinfos, collations, &matches);
 }
 
 /*
  * Check if an element is closer to q than any element from R
  */
 static bool
-CheckElementCloser(HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid collation)
+CheckElementCloser(HnswCandidate * e, List *r, int lc, Relation index, FmgrInfo **procinfos, Oid *collations)
 {
 	ListCell   *lc2;
 
 	foreach(lc2, r)
 	{
 		HnswCandidate *ri = lfirst(lc2);
-		float		distance = HnswGetDistance(e->element, ri->element, lc, procinfo, collation);
+		float		distance = HnswGetCachedDistance(e->element, ri->element, lc, index, procinfos, collations);
 
 		if (distance <= e->distance)
 			return false;
@@ -777,7 +983,7 @@ CheckElementCloser(HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid c
  * Algorithm 4 from paper
  */
 static List *
-SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
+SelectNeighbors(List *c, int m, int lc, Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
 {
 	List	   *r = NIL;
 	List	   *w = list_copy(c);
@@ -804,7 +1010,7 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswE
 
 		/* Use previous state of r and wd to skip work when possible */
 		if (mustCalculate)
-			e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
+			e->closer = CheckElementCloser(e, r, lc, index, procinfos, collations);
 		else if (list_length(added) > 0)
 		{
 			/*
@@ -813,7 +1019,7 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswE
 			 */
 			if (e->closer)
 			{
-				e->closer = CheckElementCloser(e, added, lc, procinfo, collation);
+				e->closer = CheckElementCloser(e, added, lc, index, procinfos, collations);
 
 				if (!e->closer)
 					removedAny = true;
@@ -826,7 +1032,7 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswE
 				 */
 				if (removedAny)
 				{
-					e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
+					e->closer = CheckElementCloser(e, r, lc, index, procinfos, collations);
 					if (e->closer)
 						added = lappend(added, e);
 				}
@@ -834,7 +1040,7 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswE
 		}
 		else if (e == newCandidate)
 		{
-			e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
+			e->closer = CheckElementCloser(e, r, lc, index, procinfos, collations);
 			if (e->closer)
 				added = lappend(added, e);
 		}
@@ -868,16 +1074,20 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswE
  * Find duplicate element
  */
 HnswElement
-HnswFindDuplicate(HnswElement e)
+HnswFindDuplicate(HnswElement e, Relation index)
 {
 	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 (vector_cmp_internal(e->vec, neighbor->element->vec) != 0)
+		if (!datumIsEqual(e->value, neighbor->element->value, false, -1))
 			break;
 
 		/* Check for space */
@@ -905,7 +1115,7 @@ 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 *procinfo, Oid collation)
+HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo **procinfos, Oid *collations, bool inMemory)
 {
 	HnswNeighborArray *currentNeighbors = &hc->element->neighbors[lc];
 
@@ -928,18 +1138,20 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 		HnswCandidate *pruned = NULL;
 
 		/* Load elements on insert */
-		if (index != NULL)
+		if (!inMemory)
 		{
-			Datum		q = PointerGetDatum(hc->element->vec);
+			Datum		q = hc->element->value;
+			IndexTuple	qtup = hc->element->itup;
+			ScanKeyData *keyData = NULL;
 
 			for (int i = 0; i < currentNeighbors->length; i++)
 			{
 				HnswCandidate *hc3 = &currentNeighbors->items[i];
 
-				if (hc3->element->vec == NULL)
+				if (DatumGetPointer(hc3->element->value) == NULL)
-					HnswLoadElement(hc3->element, &hc3->distance, &q, index, procinfo, collation, true);
+					HnswLoadElement(hc3->element, &hc3->distance, &hc3->matches, &q, qtup, keyData, index, procinfos, collations, true);
 				else
-					hc3->distance = GetCandidateDistance(hc3, q, procinfo, collation);
+					hc3->distance = GetCandidateDistance(hc3, q, qtup, keyData, index, procinfos, collations);
 
 				/* Prune element if being deleted */
 				if (list_length(hc3->element->heaptids) == 0)
@@ -959,7 +1171,7 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 				c = lappend(c, &currentNeighbors->items[i]);
 			c = lappend(c, &hc2);
 
-			SelectNeighbors(c, m, lc, procinfo, collation, hc->element, &hc2, &pruned, true);
+			SelectNeighbors(c, m, lc, index, procinfos, collations, hc->element, &hc2, &pruned, true);
 
 			/* Should not happen */
 			if (pruned == NULL)
@@ -1011,13 +1223,15 @@ RemoveElements(List *w, HnswElement skipElement)
  * Algorithm 1 from paper
  */
 void
-HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing)
+HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo **procinfos, Oid *collations, int m, int efConstruction, bool existing, bool inMemory)
 {
 	List	   *ep;
 	List	   *w;
 	int			level = element->level;
 	int			entryLevel;
-	Datum		q = PointerGetDatum(element->vec);
+	Datum		q = element->value;
+	IndexTuple	qtup = element->itup;
+	ScanKeyData *keyData = NULL;
 	HnswElement skipElement = existing ? element : NULL;
 
 	/* No neighbors if no entry point */
@@ -1025,13 +1239,13 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		return;
 
 	/* Get entry point and level */
-	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, true));
+	ep = list_make1(HnswEntryCandidate(entryPoint, q, qtup, keyData, index, procinfos, collations, true, inMemory));
 	entryLevel = entryPoint->level;
 
 	/* 1st phase: greedy search to insert level */
 	for (int lc = entryLevel; lc >= level + 1; lc--)
 	{
-		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
+		w = HnswSearchLayer(q, qtup, keyData, ep, 1, lc, index, procinfos, collations, m, true, skipElement, inMemory);
 		ep = w;
 	}
 
@@ -1049,11 +1263,11 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		List	   *neighbors;
 		List	   *lw;
 
-		w = HnswSearchLayer(q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
+		w = HnswSearchLayer(q, qtup, keyData, ep, efConstruction, lc, index, procinfos, collations, m, true, skipElement, inMemory);
 
 		/* Elements being deleted or skipped can help with search */
 		/* but should be removed before selecting neighbors */
-		if (index != NULL)
+		if (!inMemory)
 			lw = RemoveElements(w, skipElement);
 		else
 			lw = w;
@@ -1063,7 +1277,7 @@ 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, procinfo, collation, element, NULL, NULL, false);
+		neighbors = SelectNeighbors(lw, lm, lc, index, procinfos, collations, element, NULL, NULL, false);
 
 		AddConnections(element, neighbors, lm, lc);
 

src/hnswvacuum.c

@@ -62,7 +62,8 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 		/* Iterate over nodes */
 		for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 		{
-			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, offno));
+			ItemId		itemid = PageGetItemId(page, offno);
+			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, itemid);
 			int			idx = 0;
 			bool		itemUpdated = false;
 
@@ -93,7 +94,7 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 
 				if (itemUpdated)
 				{
-					Size		etupSize = HNSW_ELEMENT_TUPLE_SIZE(etup->vec.dim);
+					Size		etupSize = ItemIdGetLength(itemid);
 
 					/* Mark rest as invalid */
 					for (int i = idx; i < HNSW_HEAPTIDS; i++)
@@ -194,8 +195,8 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	GenericXLogState *state;
 	int			m = vacuumstate->m;
 	int			efConstruction = vacuumstate->efConstruction;
-	FmgrInfo   *procinfo = vacuumstate->procinfo;
+	FmgrInfo  **procinfos = vacuumstate->procinfos;
-	Oid			collation = vacuumstate->collation;
+	Oid		   *collations = vacuumstate->collations;
 	BufferAccessStrategy bas = vacuumstate->bas;
 	HnswNeighborTuple ntup = vacuumstate->ntup;
 	Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
@@ -209,7 +210,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	element->heaptids = NIL;
 
 	/* Add element to graph, skipping itself */
-	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, true);
+	HnswInsertElement(element, entryPoint, index, procinfos, collations, m, efConstruction, true, false);
 
 	/* Update neighbor tuple */
 	/* Do this before getting page to minimize locking */
@@ -230,7 +231,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true);
+	HnswUpdateNeighborPages(index, procinfos, collations, element, m, true);
 }
 
 /*
@@ -257,7 +258,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 		LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
 
 		/* Load element */
-		HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
+		HnswLoadElement(highestPoint, NULL, NULL, NULL, NULL, NULL, index, vacuumstate->procinfos, vacuumstate->collations, true);
 
 		/* Repair if needed */
 		if (NeedsUpdated(vacuumstate, highestPoint))
@@ -295,7 +296,7 @@ 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);
+			HnswLoadElement(entryPoint, NULL, NULL, NULL, NULL, NULL, index, vacuumstate->procinfos, vacuumstate->collations, true);
 
 			if (NeedsUpdated(vacuumstate, entryPoint))
 			{
@@ -371,7 +372,7 @@ RepairGraph(HnswVacuumState * vacuumstate)
 
 			/* Create an element */
 			element = HnswInitElementFromBlock(blkno, offno);
-			HnswLoadElementFromTuple(element, etup, false, true);
+			HnswLoadElementFromTuple(element, etup, false, true, index);
 
 			elements = lappend(elements, element);
 		}
@@ -441,6 +442,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	BlockNumber insertPage = InvalidBlockNumber;
 	Relation	index = vacuumstate->index;
 	BufferAccessStrategy bas = vacuumstate->bas;
+	bool		useIndexTuple = IndexRelationGetNumberOfAttributes(index) > 1;
 
 	/*
 	 * Wait for index scans to complete. Scans before this point may contain
@@ -477,7 +479,8 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 		/* Update element and neighbors together */
 		for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 		{
-			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, offno));
+			ItemId		itemid = PageGetItemId(page, offno);
+			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, itemid);
 			HnswNeighborTuple ntup;
 			Size		etupSize;
 			Size		ntupSize;
@@ -505,7 +508,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 				continue;
 
 			/* Calculate sizes */
-			etupSize = HNSW_ELEMENT_TUPLE_SIZE(etup->vec.dim);
+			etupSize = ItemIdGetLength(itemid);
 			ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(etup->level, vacuumstate->m);
 
 			/* Get neighbor page */
@@ -528,7 +531,18 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 
 			/* Overwrite element */
 			etup->deleted = 1;
-			MemSet(&etup->vec.x, 0, etup->vec.dim * sizeof(float));
+			if (useIndexTuple)
+			{
+				IndexTuple	itup = (IndexTuple) &etup->data;
+
+				MemSet(itup, 0, IndexTupleSize(itup));
+			}
+			else
+			{
+				Vector	   *vec = (Vector *) (&etup->data);
+
+				MemSet(vec, 0, VARSIZE_ANY(vec));
+			}
 
 			/* Overwrite neighbors */
 			for (int i = 0; i < ntup->count; i++)
@@ -584,8 +598,8 @@ 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->procinfos = HnswInitProcinfos(index);
-	vacuumstate->collation = index->rd_indcollation[0];
+	vacuumstate->collations = index->rd_indcollation;
 	vacuumstate->ntup = palloc0(BLCKSZ);
 	vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
 												"Hnsw vacuum temporary context",
@@ -609,6 +623,7 @@ FreeVacuumState(HnswVacuumState * vacuumstate)
 {
 	hash_destroy(vacuumstate->deleted);
 	FreeAccessStrategy(vacuumstate->bas);
+	pfree(vacuumstate->procinfos);
 	pfree(vacuumstate->ntup);
 	MemoryContextDelete(vacuumstate->tmpCtx);
 }

src/svector.c

@@ -1,705 +0,0 @@
-#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);
-}

src/svector.h

@@ -1,23 +0,0 @@
-#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

src/vector.c

@@ -9,7 +9,6 @@
 #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"
@@ -1152,26 +1151,3 @@ 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);
-}

test/expected/functions.out

@@ -54,85 +54,85 @@ SELECT vector_norm('[3e37,4e37]')::real;
        5e+37
 (1 row)
 
-SELECT l2_distance('[0,0]'::vector, '[3,4]');
+SELECT l2_distance('[0,0]', '[3,4]');
  l2_distance 
 -------------
            5
 (1 row)
 
-SELECT l2_distance('[0,0]'::vector, '[0,1]');
+SELECT l2_distance('[0,0]', '[0,1]');
  l2_distance 
 -------------
            1
 (1 row)
 
-SELECT l2_distance('[1,2]'::vector, '[3]');
+SELECT l2_distance('[1,2]', '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT l2_distance('[3e38]'::vector, '[-3e38]');
+SELECT l2_distance('[3e38]', '[-3e38]');
  l2_distance 
 -------------
     Infinity
 (1 row)
 
-SELECT inner_product('[1,2]'::vector, '[3,4]');
+SELECT inner_product('[1,2]', '[3,4]');
  inner_product 
 ---------------
             11
 (1 row)
 
-SELECT inner_product('[1,2]'::vector, '[3]');
+SELECT inner_product('[1,2]', '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT inner_product('[3e38]'::vector, '[3e38]');
+SELECT inner_product('[3e38]', '[3e38]');
  inner_product 
 ---------------
       Infinity
 (1 row)
 
-SELECT cosine_distance('[1,2]'::vector, '[2,4]');
+SELECT cosine_distance('[1,2]', '[2,4]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,2]'::vector, '[0,0]');
+SELECT cosine_distance('[1,2]', '[0,0]');
  cosine_distance 
 -----------------
              NaN
 (1 row)
 
-SELECT cosine_distance('[1,1]'::vector, '[1,1]');
+SELECT cosine_distance('[1,1]', '[1,1]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,0]'::vector, '[0,2]');
+SELECT cosine_distance('[1,0]', '[0,2]');
  cosine_distance 
 -----------------
                1
 (1 row)
 
-SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
+SELECT cosine_distance('[1,1]', '[-1,-1]');
  cosine_distance 
 -----------------
                2
 (1 row)
 
-SELECT cosine_distance('[1,2]'::vector, '[3]');
+SELECT cosine_distance('[1,2]', '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
+SELECT cosine_distance('[1,1]', '[1.1,1.1]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
+SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
  cosine_distance 
 -----------------
                2
 (1 row)
 
-SELECT cosine_distance('[3e38]'::vector, '[3e38]');
+SELECT cosine_distance('[3e38]', '[3e38]');
  cosine_distance 
 -----------------
              NaN

test/expected/svector.out

@@ -1,140 +0,0 @@
-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

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]'::vector, '[3,4]');
+SELECT l2_distance('[0,0]', '[3,4]');
-SELECT l2_distance('[0,0]'::vector, '[0,1]');
+SELECT l2_distance('[0,0]', '[0,1]');
-SELECT l2_distance('[1,2]'::vector, '[3]');
+SELECT l2_distance('[1,2]', '[3]');
-SELECT l2_distance('[3e38]'::vector, '[-3e38]');
+SELECT l2_distance('[3e38]', '[-3e38]');
 
-SELECT inner_product('[1,2]'::vector, '[3,4]');
+SELECT inner_product('[1,2]', '[3,4]');
-SELECT inner_product('[1,2]'::vector, '[3]');
+SELECT inner_product('[1,2]', '[3]');
-SELECT inner_product('[3e38]'::vector, '[3e38]');
+SELECT inner_product('[3e38]', '[3e38]');
 
-SELECT cosine_distance('[1,2]'::vector, '[2,4]');
+SELECT cosine_distance('[1,2]', '[2,4]');
-SELECT cosine_distance('[1,2]'::vector, '[0,0]');
+SELECT cosine_distance('[1,2]', '[0,0]');
-SELECT cosine_distance('[1,1]'::vector, '[1,1]');
+SELECT cosine_distance('[1,1]', '[1,1]');
-SELECT cosine_distance('[1,0]'::vector, '[0,2]');
+SELECT cosine_distance('[1,0]', '[0,2]');
-SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
+SELECT cosine_distance('[1,1]', '[-1,-1]');
-SELECT cosine_distance('[1,2]'::vector, '[3]');
+SELECT cosine_distance('[1,2]', '[3]');
-SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
+SELECT cosine_distance('[1,1]', '[1.1,1.1]');
-SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
+SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
-SELECT cosine_distance('[3e38]'::vector, '[3e38]');
+SELECT cosine_distance('[3e38]', '[3e38]');
 
 SELECT l1_distance('[0,0]', '[3,4]');
 SELECT l1_distance('[0,0]', '[0,1]');

test/sql/svector.sql

@@ -1,36 +0,0 @@
-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|');

test/t/019_hnsw_filtering.pl

@@ -0,0 +1,109 @@
+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;
+
+		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 = 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($dim), c int4);");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc FROM generate_series(1, 20000) i;"
+);
+
+# Generate queries
+for (1 .. 20)
+{
+	my @r = ();
+	for (1 .. $dim)
+	{
+		push(@r, rand());
+	}
+	push(@queries, "[" . join(",", @r) . "]");
+	push(@cs, int(rand() * $nc));
+}
+
+# Get exact results
+@expected = ();
+for my $i (0 .. $#queries)
+{
+	my $res = $node->safe_psql("postgres", "SELECT i FROM tst WHERE c = $cs[$i] ORDER BY v <-> '$queries[$i]' LIMIT $limit;");
+	push(@expected, $res);
+}
+
+# Add index
+$node->safe_psql("postgres", "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();