Version bump to 0.7.1 [skip ci]

CHANGELOG.md

@@ -1,5 +1,6 @@
-## 0.7.1 (unreleased)
+## 0.7.1 (2024-06-03)
 
+- Improved performance of on-disk HNSW index builds
 - Fixed `undefined symbol` error with GCC 8
 - Fixed compilation error with universal binaries on Mac
 - Fixed compilation warning with Clang < 14

META.json

@@ -2,7 +2,7 @@
 	"name": "vector",
 	"abstract": "Open-source vector similarity search for Postgres",
 	"description": "Supports L2 distance, inner product, and cosine distance",
-	"version": "0.7.0",
+	"version": "0.7.1",
 	"maintainer": [
 		"Andrew Kane <andrew@ankane.org>"
 	],
@@ -20,7 +20,7 @@
 		"vector": {
 			"file": "sql/vector.sql",
 			"docfile": "README.md",
-			"version": "0.7.0",
+			"version": "0.7.1",
 			"abstract": "Open-source vector similarity search for Postgres"
 		}
 	},

Makefile

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.7.0
+EXTVERSION = 0.7.1
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*.sql)

Makefile.win

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.7.0
+EXTVERSION = 0.7.1
 
 OBJS = src\bitutils.obj src\bitvec.obj src\halfutils.obj src\halfvec.obj 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\sparsevec.obj src\vector.obj
 HEADERS = src\halfvec.h src\sparsevec.h src\vector.h

README.md

@@ -21,7 +21,7 @@ Compile and install the extension (supports Postgres 12+)
 
 ```sh
 cd /tmp
-git clone --branch v0.7.0 https://github.com/pgvector/pgvector.git
+git clone --branch v0.7.1 https://github.com/pgvector/pgvector.git
 cd pgvector
 make
 make install # may need sudo
@@ -46,7 +46,7 @@ Then use `nmake` to build:
 ```cmd
 set "PGROOT=C:\Program Files\PostgreSQL\16"
 cd %TEMP%
-git clone --branch v0.7.0 https://github.com/pgvector/pgvector.git
+git clone --branch v0.7.1 https://github.com/pgvector/pgvector.git
 cd pgvector
 nmake /F Makefile.win
 nmake /F Makefile.win install
@@ -1051,7 +1051,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
 You can also build the image manually:
 
 ```sh
-git clone --branch v0.7.0 https://github.com/pgvector/pgvector.git
+git clone --branch v0.7.1 https://github.com/pgvector/pgvector.git
 cd pgvector
 docker build --pull --build-arg PG_MAJOR=16 -t myuser/pgvector .
 ```

sql/vector--0.7.0--0.7.1.sql

@@ -0,0 +1,2 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "ALTER EXTENSION vector UPDATE TO '0.7.1'" to load this file. \quit

src/hnsw.h

@@ -393,7 +393,7 @@ void		HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator *
 bool		HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
 void		HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
 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		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, float *maxDistance);
 void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
 void		HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
 void		HnswLoadNeighbors(HnswElement element, Relation index, int m);

src/hnswutils.c

@@ -545,7 +545,7 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
  * 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, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, float *maxDistance)
 {
 	Buffer		buf;
 	Page		page;
@@ -560,9 +560,6 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
 
 	Assert(HnswIsElementTuple(etup));
 
-	/* Load element */
-	HnswLoadElementFromTuple(element, etup, true, loadVec);
-
 	/* Calculate distance */
 	if (distance != NULL)
 	{
@@ -572,6 +569,10 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
 			*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->data)));
 	}
 
+	/* Load element */
+	if (distance == NULL || maxDistance == NULL || *distance < *maxDistance)
+		HnswLoadElementFromTuple(element, etup, true, loadVec);
+
 	UnlockReleaseBuffer(buf);
 }
 
@@ -599,7 +600,7 @@ HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index,
 	if (index == NULL)
 		hc->distance = GetCandidateDistance(base, hc, q, procinfo, collation);
 	else
-		HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec);
+		HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec, NULL);
 	return hc;
 }
 
@@ -801,19 +802,20 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 				if (index == NULL)
 					eDistance = GetCandidateDistance(base, e, q, procinfo, collation);
 				else
-					HnswLoadElement(eElement, &eDistance, &q, index, procinfo, collation, inserting);
-
-				Assert(!eElement->deleted);
-
-				/* Make robust to issues */
-				if (eElement->level < lc)
-					continue;
+					HnswLoadElement(eElement, &eDistance, &q, index, procinfo, collation, inserting, wlen >= ef ? &f->distance : NULL);
 
 				if (eDistance < f->distance || wlen < ef)
 				{
-					/* Copy e */
-					HnswCandidate *ec = palloc(sizeof(HnswCandidate));
+					HnswCandidate *ec;
 
+					Assert(!eElement->deleted);
+
+					/* Make robust to issues */
+					if (eElement->level < lc)
+						continue;
+
+					/* Copy e */
+					ec = palloc(sizeof(HnswCandidate));
 					HnswPtrStore(base, ec->element, eElement);
 					ec->distance = eDistance;
 
@@ -1102,7 +1104,7 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm
 				HnswElement hc3Element = HnswPtrAccess(base, hc3->element);
 
 				if (HnswPtrIsNull(base, hc3Element->value))
-					HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true);
+					HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true, NULL);
 				else
 					hc3->distance = GetCandidateDistance(base, hc3, q, procinfo, collation);
 

src/hnswvacuum.c

@@ -256,7 +256,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 		LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
 
 		/* Load element */
-		HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
+		HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL);
 
 		/* Repair if needed */
 		if (NeedsUpdated(vacuumstate, highestPoint))
@@ -294,7 +294,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 			 * is outdated, this can remove connections at higher levels in
 			 * the graph until they are repaired, but this should be fine.
 			 */
-			HnswLoadElement(entryPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
+			HnswLoadElement(entryPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL);
 
 			if (NeedsUpdated(vacuumstate, entryPoint))
 			{

vector.control

@@ -1,4 +1,4 @@
 comment = 'vector data type and ivfflat and hnsw access methods'
-default_version = '0.7.0'
+default_version = '0.7.1'
 module_pathname = '$libdir/vector'
 relocatable = true