Compare commits

..

18 Commits

Author SHA1 Message Date
Andrew Kane
75cf54a1e2 Updated changelog [skip ci] 2024-03-11 19:53:03 -07:00
Andrew Kane
569fd36396 Improved performance of parallel HNSW index builds 2024-03-11 18:32:39 -07:00
Andrew Kane
62350b1589 Added note about IVFFlat results [skip ci] 2024-03-06 00:29:55 -08:00
Andrew Kane
dd57309281 Added section about HNSW results - #480 [skip ci] 2024-03-06 00:27:50 -08:00
Andrew Kane
c6ddf62a29 Version bump to 0.6.1 [skip ci] 2024-03-04 10:27:59 -08:00
Andrew Kane
801be04d8b Updated CI [skip ci] 2024-03-02 17:06:11 -08:00
Andrew Kane
587e9ba97c Added link to bulk loading example [skip ci] 2024-02-29 21:25:11 -08:00
Andrew Kane
d57047a935 Moved COPY example and added FORMAT [skip ci] 2024-02-29 20:35:01 -08:00
oneturkmen
f1db1f17e3 Update README.md (#472) 2024-02-29 20:27:53 -08:00
Andrew Kane
2f48c0fac4 Updated changelog [skip ci] 2024-02-29 18:10:19 -08:00
Andrew Kane
84a8aa8176 Added note about HNSW build time [skip ci] 2024-02-29 16:25:58 -08:00
Andrew Kane
f64ebbef50 Added OPTFLAGS to readme [skip ci] 2024-02-29 16:15:22 -08:00
Andrew Kane
ac8156509b Updated vector operators for <= and >= 2024-02-29 15:43:29 -08:00
Andrew Kane
82bf69b479 Fixed vector subtraction being marked as commutative - fixes #475 2024-02-29 14:36:18 -08:00
Andrew Kane
4be2f57916 Updated license year [skip ci] 2024-02-29 13:44:58 -08:00
Andrew Kane
91e3d2905f Fixed sort function for Postgres 12 2024-02-28 16:26:41 -08:00
Andrew Kane
fe2406564f Replaced pairing heap with array in SelectNeighbors - closes #447
Co-authored-by: Heikki Linnakangas <heikki.linnakangas@iki.fi>
2024-02-28 15:47:26 -08:00
Andrew Kane
fa52511eaa Fixed closer caching for Postgres 12 2024-02-28 15:44:38 -08:00
14 changed files with 91 additions and 53 deletions

View File

@@ -60,7 +60,9 @@ jobs:
wget -q https://github.com/postgres/postgres/archive/refs/tags/REL_14_10.tar.gz
tar xf REL_14_10.tar.gz
- run: make prove_installcheck PROVE_FLAGS="-I ./postgres-REL_14_10/src/test/perl" PERL5LIB="/Users/runner/perl5/lib/perl5"
- run: make clean && /usr/local/opt/llvm@15/bin/scan-build --status-bugs make PG_CFLAGS="-DUSE_ASSERT_CHECKING"
- run: make clean && /usr/local/opt/llvm@15/bin/scan-build --status-bugs make
env:
PG_CFLAGS: -DUSE_ASSERT_CHECKING
windows:
runs-on: windows-latest
if: ${{ !startsWith(github.ref_name, 'mac') }}

View File

@@ -1,7 +1,12 @@
## 0.6.1 (unreleased)
## 0.6.2 (unreleased)
- Reduced lock contention with parallel HNSW index builds
## 0.6.1 (2024-03-04)
- Fixed error with `ANALYZE` and vectors with different dimensions
- Fixed error with `shared_preload_libraries`
- Fixed vector subtraction being marked as commutative
## 0.6.0 (2024-01-29)

View File

@@ -1,4 +1,4 @@
Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
Portions Copyright (c) 1994, The Regents of the University of California

View File

@@ -2,7 +2,7 @@
"name": "vector",
"abstract": "Open-source vector similarity search for Postgres",
"description": "Supports L2 distance, inner product, and cosine distance",
"version": "0.6.0",
"version": "0.6.1",
"maintainer": [
"Andrew Kane <andrew@ankane.org>"
],
@@ -20,7 +20,7 @@
"vector": {
"file": "sql/vector.sql",
"docfile": "README.md",
"version": "0.6.0",
"version": "0.6.1",
"abstract": "Open-source vector similarity search for Postgres"
}
},

View File

@@ -1,5 +1,5 @@
EXTENSION = vector
EXTVERSION = 0.6.0
EXTVERSION = 0.6.1
MODULE_big = vector
DATA = $(wildcard sql/*--*.sql)

View File

@@ -1,5 +1,5 @@
EXTENSION = vector
EXTVERSION = 0.6.0
EXTVERSION = 0.6.1
OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\vector.obj
HEADERS = src\vector.h

View File

@@ -20,7 +20,7 @@ Compile and install the extension (supports Postgres 12+)
```sh
cd /tmp
git clone --branch v0.6.0 https://github.com/pgvector/pgvector.git
git clone --branch v0.6.1 https://github.com/pgvector/pgvector.git
cd pgvector
make
make install # may need sudo
@@ -44,7 +44,7 @@ Then use `nmake` to build:
```cmd
set "PGROOT=C:\Program Files\PostgreSQL\16"
git clone --branch v0.6.0 https://github.com/pgvector/pgvector.git
git clone --branch v0.6.1 https://github.com/pgvector/pgvector.git
cd pgvector
nmake /F Makefile.win
nmake /F Makefile.win install
@@ -102,6 +102,12 @@ Insert vectors
INSERT INTO items (embedding) VALUES ('[1,2,3]'), ('[4,5,6]');
```
Or load vectors in bulk using `COPY` ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/bulk_loading.py))
```sql
COPY items (embedding) FROM STDIN WITH (FORMAT BINARY);
```
Upsert vectors
```sql
@@ -264,6 +270,8 @@ HINT: Increase maintenance_work_mem to speed up builds.
Note: Do not set `maintenance_work_mem` so high that it exhausts the memory on the server
Like other index types, its faster to create an index after loading your initial data
Starting with 0.6.0, you can also speed up index creation by increasing the number of parallel workers (2 by default)
```sql
@@ -573,6 +581,10 @@ or choose to store vectors inline:
ALTER TABLE items ALTER COLUMN embedding SET STORAGE PLAIN;
```
#### Why are there less results for a query after adding an HNSW index?
Results are limited by the size of the dynamic candidate list (`hnsw.ef_search`). There may be even less results due to dead tuples or filtering conditions in the query. We recommend setting `hnsw.ef_search` to at least twice the `LIMIT` of the query. If you need more than 500 results, use an IVFFlat index instead.
#### Why are there less results for a query after adding an IVFFlat index?
The index was likely created with too little data for the number of lists. Drop the index until the table has more data.
@@ -581,6 +593,8 @@ The index was likely created with too little data for the number of lists. Drop
DROP INDEX index_name;
```
Results can also be limited by the number of probes (`ivfflat.probes`).
## Reference
### Vector Type
@@ -656,6 +670,14 @@ Note: Replace `16` with your Postgres server version
If compilation fails and the output includes `warning: no such sysroot directory` on Mac, reinstall Xcode Command Line Tools.
### Portability
To compile for portability, use:
```sh
make OPTFLAGS=""
```
## Additional Installation Methods
### Docker
@@ -671,7 +693,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
You can also build the image manually:
```sh
git clone --branch v0.6.0 https://github.com/pgvector/pgvector.git
git clone --branch v0.6.1 https://github.com/pgvector/pgvector.git
cd pgvector
docker build --build-arg PG_MAJOR=16 -t myuser/pgvector .
```

View File

@@ -0,0 +1,16 @@
-- complain if script is sourced in psql, rather than via CREATE EXTENSION
\echo Use "ALTER EXTENSION vector UPDATE TO '0.6.1'" to load this file. \quit
DROP OPERATOR - (vector, vector);
CREATE OPERATOR - (
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_sub
);
ALTER OPERATOR <= (vector, vector) SET (
RESTRICT = scalarlesel, JOIN = scalarlejoinsel
);
ALTER OPERATOR >= (vector, vector) SET (
RESTRICT = scalargesel, JOIN = scalargejoinsel
);

View File

@@ -180,8 +180,7 @@ CREATE OPERATOR + (
);
CREATE OPERATOR - (
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_sub,
COMMUTATOR = -
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_sub
);
CREATE OPERATOR * (
@@ -195,11 +194,10 @@ CREATE OPERATOR < (
RESTRICT = scalarltsel, JOIN = scalarltjoinsel
);
-- should use scalarlesel and scalarlejoinsel, but not supported in Postgres < 11
CREATE OPERATOR <= (
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_le,
COMMUTATOR = >= , NEGATOR = > ,
RESTRICT = scalarltsel, JOIN = scalarltjoinsel
RESTRICT = scalarlesel, JOIN = scalarlejoinsel
);
CREATE OPERATOR = (
@@ -214,11 +212,10 @@ CREATE OPERATOR <> (
RESTRICT = eqsel, JOIN = eqjoinsel
);
-- should use scalargesel and scalargejoinsel, but not supported in Postgres < 11
CREATE OPERATOR >= (
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_ge,
COMMUTATOR = <= , NEGATOR = < ,
RESTRICT = scalargtsel, JOIN = scalargtjoinsel
RESTRICT = scalargesel, JOIN = scalargejoinsel
);
CREATE OPERATOR > (

View File

@@ -80,7 +80,7 @@
#if PG_VERSION_NUM < 130000
#define list_delete_last(list) list_truncate(list, list_length(list) - 1)
#define list_sort(list, cmp) list_qsort(list, cmp)
#define list_sort(list, cmp) ((list) = list_qsort(list, cmp))
#endif
#define HnswIsElementTuple(tup) ((tup)->type == HNSW_ELEMENT_TUPLE_TYPE)
@@ -185,6 +185,7 @@ typedef struct HnswGraph
/* Entry state */
LWLock entryLock;
LWLock entryWaitLock;
HnswElementPtr entryPoint;
/* Allocations state */

View File

@@ -431,10 +431,15 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
HnswGraph *graph = buildstate->graph;
HnswElement entryPoint;
LWLock *entryLock = &graph->entryLock;
LWLock *entryWaitLock = &graph->entryWaitLock;
int efConstruction = buildstate->efConstruction;
int m = buildstate->m;
char *base = buildstate->hnswarea;
/* Wait if another process needs exclusive lock */
LWLockAcquire(entryWaitLock, LW_EXCLUSIVE);
LWLockRelease(entryWaitLock);
/* Get entry point */
LWLockAcquire(entryLock, LW_SHARED);
entryPoint = HnswPtrAccess(base, graph->entryPoint);
@@ -446,7 +451,9 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
LWLockRelease(entryLock);
/* Get exclusive lock */
LWLockAcquire(entryWaitLock, LW_EXCLUSIVE);
LWLockAcquire(entryLock, LW_EXCLUSIVE);
LWLockRelease(entryWaitLock);
/* Get latest entry point after lock is acquired */
entryPoint = HnswPtrAccess(base, graph->entryPoint);
@@ -612,6 +619,7 @@ InitGraph(HnswGraph * graph, char *base, long memoryTotal)
graph->indtuples = 0;
SpinLockInit(&graph->lock);
LWLockInitialize(&graph->entryLock, hnsw_lock_tranche_id);
LWLockInitialize(&graph->entryWaitLock, hnsw_lock_tranche_id);
LWLockInitialize(&graph->allocatorLock, hnsw_lock_tranche_id);
LWLockInitialize(&graph->flushLock, hnsw_lock_tranche_id);
}

View File

@@ -860,12 +860,15 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
static int
#if PG_VERSION_NUM >= 130000
CompareCandidateDistances(const ListCell *a, const ListCell *b)
{
HnswCandidate *hca = lfirst(a);
HnswCandidate *hcb = lfirst(b);
#else
CompareCandidateDistances(const void *a, const void *b)
#endif
{
HnswCandidate *hca = lfirst((ListCell *) a);
HnswCandidate *hcb = lfirst((ListCell *) b);
HnswCandidate *hca = lfirst(*(ListCell **) a);
HnswCandidate *hcb = lfirst(*(ListCell **) b);
#endif
if (hca->distance < hcb->distance)
return 1;
@@ -888,12 +891,15 @@ CompareCandidateDistances(const void *a, const void *b)
static int
#if PG_VERSION_NUM >= 130000
CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
{
HnswCandidate *hca = lfirst(a);
HnswCandidate *hcb = lfirst(b);
#else
CompareCandidateDistancesOffset(const void *a, const void *b)
#endif
{
HnswCandidate *hca = lfirst((ListCell *) a);
HnswCandidate *hcb = lfirst((ListCell *) b);
HnswCandidate *hca = lfirst(*(ListCell **) a);
HnswCandidate *hcb = lfirst(*(ListCell **) b);
#endif
if (hca->distance < hcb->distance)
return 1;
@@ -952,7 +958,9 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
{
List *r = NIL;
List *w = list_copy(c);
pairingheap *wd;
HnswCandidate **wd;
int wdlen = 0;
int wdoff = 0;
HnswNeighborArray *neighbors = HnswGetNeighbors(base, e2, lc);
bool mustCalculate = !neighbors->closerSet;
List *added = NIL;
@@ -961,7 +969,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
if (list_length(w) <= lm)
return w;
wd = pairingheap_allocate(CompareNearestCandidates, NULL);
wd = palloc(sizeof(HnswCandidate *) * list_length(w));
/* Ensure order of candidates is deterministic for closer caching */
if (sortCandidates)
@@ -1027,21 +1035,21 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
if (e->closer)
r = lappend(r, e);
else
pairingheap_add(wd, &(CreatePairingHeapNode(e)->ph_node));
wd[wdlen++] = e;
}
/* Cached value can only be used in future if sorted deterministically */
neighbors->closerSet = sortCandidates;
/* Keep pruned connections */
while (!pairingheap_is_empty(wd) && list_length(r) < lm)
r = lappend(r, ((HnswPairingHeapNode *) pairingheap_remove_first(wd))->inner);
while (wdoff < wdlen && list_length(r) < lm)
r = lappend(r, wd[wdoff++]);
/* Return pruned for update connections */
if (pruned != NULL)
{
if (!pairingheap_is_empty(wd))
*pruned = ((HnswPairingHeapNode *) pairingheap_first(wd))->inner;
if (wdoff < wdlen)
*pruned = wd[wdoff];
else
*pruned = linitial(w);
}

View File

@@ -904,27 +904,6 @@ IvfflatBeginParallel(IvfflatBuildState * buildstate, bool isconcurrent, int requ
WaitForParallelWorkersToAttach(pcxt);
}
/*
* Compute parallel workers
*/
static int
ComputeParallelWorkers(Relation heap, Relation index)
{
int parallel_workers;
/* Make sure it's safe to use parallel workers */
parallel_workers = plan_create_index_workers(RelationGetRelid(heap), RelationGetRelid(index));
if (parallel_workers == 0)
return 0;
/* Use parallel_workers storage parameter on table if set */
parallel_workers = RelationGetParallelWorkers(heap, -1);
if (parallel_workers != -1)
return Min(parallel_workers, max_parallel_maintenance_workers);
return max_parallel_maintenance_workers;
}
/*
* Scan table for tuples to index
*/
@@ -944,7 +923,7 @@ AssignTuples(IvfflatBuildState * buildstate)
/* Calculate parallel workers */
if (buildstate->heap != NULL)
parallel_workers = ComputeParallelWorkers(buildstate->heap, buildstate->index);
parallel_workers = plan_create_index_workers(RelationGetRelid(buildstate->heap), RelationGetRelid(buildstate->index));
/* Attempt to launch parallel worker scan when required */
if (parallel_workers > 0)

View File

@@ -1,4 +1,4 @@
comment = 'vector data type and ivfflat and hnsw access methods'
default_version = '0.6.0'
default_version = '0.6.1'
module_pathname = '$libdir/vector'
relocatable = true