mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-22 20:15:46 +08:00
Compare commits
26 Commits
hnsw-adapt
...
ci-alpine
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
9250ddce87 | ||
|
|
bb431d531a | ||
|
|
2821648051 | ||
|
|
e583329be6 | ||
|
|
9d4fbeb7df | ||
|
|
eab825ae21 | ||
|
|
0d2ef735e5 | ||
|
|
1697c9f6d0 | ||
|
|
77814eb0ee | ||
|
|
1a381ffdcd | ||
|
|
250d453f8c | ||
|
|
498c23aa0c | ||
|
|
f09ef49dbf | ||
|
|
544686feb1 | ||
|
|
1a8ebb1129 | ||
|
|
aca89aec73 | ||
|
|
c9875f5150 | ||
|
|
df2c3d301f | ||
|
|
d557f1c9b1 | ||
|
|
3d6dd20469 | ||
|
|
c711da411c | ||
|
|
3975e212cc | ||
|
|
2b741ef068 | ||
|
|
f85a7d3fd0 | ||
|
|
5c25f81789 | ||
|
|
d72ee71f23 |
246
.github/workflows/build.yml
vendored
246
.github/workflows/build.yml
vendored
@@ -1,120 +1,120 @@
|
||||
name: build
|
||||
on: [push, pull_request]
|
||||
jobs:
|
||||
ubuntu:
|
||||
runs-on: ${{ matrix.os }}
|
||||
if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- postgres: 19
|
||||
os: ubuntu-24.04
|
||||
- postgres: 18
|
||||
os: ubuntu-24.04
|
||||
- postgres: 17
|
||||
os: ubuntu-24.04
|
||||
- postgres: 16
|
||||
os: ubuntu-24.04-arm
|
||||
- postgres: 15
|
||||
os: ubuntu-22.04
|
||||
- postgres: 14
|
||||
os: ubuntu-22.04-arm
|
||||
- postgres: 13
|
||||
os: ubuntu-22.04
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- uses: ankane/setup-postgres@v1
|
||||
with:
|
||||
postgres-version: ${{ matrix.postgres }}
|
||||
dev-files: true
|
||||
- run: make
|
||||
env:
|
||||
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare ${{ matrix.postgres >= 18 && '-Wno-missing-field-initializers' || '' }}
|
||||
- run: |
|
||||
export PG_CONFIG=`which pg_config`
|
||||
sudo --preserve-env=PG_CONFIG make install
|
||||
- run: make installcheck
|
||||
- if: ${{ failure() }}
|
||||
run: cat regression.diffs
|
||||
- run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install libipc-run-perl
|
||||
- run: make prove_installcheck
|
||||
mac:
|
||||
runs-on: ${{ matrix.os }}
|
||||
if: ${{ !startsWith(github.ref_name, 'windows') }}
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- postgres: 18
|
||||
os: macos-26
|
||||
- postgres: 14
|
||||
os: macos-15-intel
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- uses: ankane/setup-postgres@v1
|
||||
with:
|
||||
postgres-version: ${{ matrix.postgres }}
|
||||
- run: make
|
||||
env:
|
||||
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-unknown-warning-option ${{ matrix.postgres >= 18 && '-Wno-missing-field-initializers' || '' }}
|
||||
- run: make install
|
||||
- run: make installcheck
|
||||
- if: ${{ failure() }}
|
||||
run: cat regression.diffs
|
||||
# Homebrew Postgres does not enable TAP tests, so need to download
|
||||
- run: |
|
||||
brew install cpanm
|
||||
cpanm --notest IPC::Run
|
||||
wget -q https://github.com/postgres/postgres/archive/refs/tags/$TAG.tar.gz
|
||||
tar xf $TAG.tar.gz
|
||||
mv postgres-$TAG postgres
|
||||
env:
|
||||
TAG: ${{ matrix.postgres == 18 && 'REL_18_0' || 'REL_14_19' }}
|
||||
- run: make prove_installcheck PROVE_FLAGS="-I ./postgres/src/test/perl -I ./test/perl"
|
||||
env:
|
||||
PERL5LIB: /Users/runner/perl5/lib/perl5
|
||||
- run: make clean && $(brew --prefix llvm@$LLVM_VERSION)/bin/scan-build --status-bugs make
|
||||
env:
|
||||
LLVM_VERSION: ${{ matrix.os == 'macos-26' && 20 || 18 }}
|
||||
PG_CFLAGS: -DUSE_ASSERT_CHECKING
|
||||
windows:
|
||||
runs-on: ${{ matrix.os }}
|
||||
if: ${{ !startsWith(github.ref_name, 'mac') }}
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- postgres: 17
|
||||
os: windows-2025
|
||||
- postgres: 14
|
||||
os: windows-2022
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- uses: ankane/setup-postgres@v1
|
||||
with:
|
||||
postgres-version: ${{ matrix.postgres }}
|
||||
- run: |
|
||||
call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvars64.bat" && ^
|
||||
nmake /NOLOGO /F Makefile.win && ^
|
||||
nmake /NOLOGO /F Makefile.win install && ^
|
||||
nmake /NOLOGO /F Makefile.win installcheck ${{ matrix.postgres != 17 && 'PG_REGRESS=$(PGROOT)\bin\pg_regress' || '' }} && ^
|
||||
nmake /NOLOGO /F Makefile.win clean && ^
|
||||
nmake /NOLOGO /F Makefile.win uninstall
|
||||
shell: cmd
|
||||
- if: ${{ failure() }}
|
||||
run: cat regression.diffs
|
||||
# ubuntu:
|
||||
# runs-on: ${{ matrix.os }}
|
||||
# if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
|
||||
# strategy:
|
||||
# fail-fast: false
|
||||
# matrix:
|
||||
# include:
|
||||
# - postgres: 19
|
||||
# os: ubuntu-24.04
|
||||
# - postgres: 18
|
||||
# os: ubuntu-24.04
|
||||
# - postgres: 17
|
||||
# os: ubuntu-24.04
|
||||
# - postgres: 16
|
||||
# os: ubuntu-24.04-arm
|
||||
# - postgres: 15
|
||||
# os: ubuntu-22.04
|
||||
# - postgres: 14
|
||||
# os: ubuntu-22.04-arm
|
||||
# - postgres: 13
|
||||
# os: ubuntu-22.04
|
||||
# steps:
|
||||
# - uses: actions/checkout@v5
|
||||
# - uses: ankane/setup-postgres@v1
|
||||
# with:
|
||||
# postgres-version: ${{ matrix.postgres }}
|
||||
# dev-files: true
|
||||
# - run: make
|
||||
# env:
|
||||
# PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare ${{ matrix.postgres >= 18 && '-Wno-missing-field-initializers' || '' }}
|
||||
# - run: |
|
||||
# export PG_CONFIG=`which pg_config`
|
||||
# sudo --preserve-env=PG_CONFIG make install
|
||||
# - run: make installcheck
|
||||
# - if: ${{ failure() }}
|
||||
# run: cat regression.diffs
|
||||
# - run: |
|
||||
# sudo apt-get update
|
||||
# sudo apt-get install libipc-run-perl
|
||||
# - run: make prove_installcheck
|
||||
# mac:
|
||||
# runs-on: ${{ matrix.os }}
|
||||
# if: ${{ !startsWith(github.ref_name, 'windows') }}
|
||||
# strategy:
|
||||
# fail-fast: false
|
||||
# matrix:
|
||||
# include:
|
||||
# - postgres: 18
|
||||
# os: macos-26
|
||||
# - postgres: 14
|
||||
# os: macos-15-intel
|
||||
# steps:
|
||||
# - uses: actions/checkout@v5
|
||||
# - uses: ankane/setup-postgres@v1
|
||||
# with:
|
||||
# postgres-version: ${{ matrix.postgres }}
|
||||
# - run: make
|
||||
# env:
|
||||
# PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-unknown-warning-option ${{ matrix.postgres >= 18 && '-Wno-missing-field-initializers' || '' }}
|
||||
# - run: make install
|
||||
# - run: make installcheck
|
||||
# - if: ${{ failure() }}
|
||||
# run: cat regression.diffs
|
||||
# # Homebrew Postgres does not enable TAP tests, so need to download
|
||||
# - run: |
|
||||
# brew install cpanm
|
||||
# cpanm --notest IPC::Run
|
||||
# wget -q https://github.com/postgres/postgres/archive/refs/tags/$TAG.tar.gz
|
||||
# tar xf $TAG.tar.gz
|
||||
# mv postgres-$TAG postgres
|
||||
# env:
|
||||
# TAG: ${{ matrix.postgres == 18 && 'REL_18_0' || 'REL_14_19' }}
|
||||
# - run: make prove_installcheck PROVE_FLAGS="-I ./postgres/src/test/perl -I ./test/perl"
|
||||
# env:
|
||||
# PERL5LIB: /Users/runner/perl5/lib/perl5
|
||||
# - run: make clean && $(brew --prefix llvm@$LLVM_VERSION)/bin/scan-build --status-bugs make
|
||||
# env:
|
||||
# LLVM_VERSION: ${{ matrix.os == 'macos-26' && 20 || 18 }}
|
||||
# PG_CFLAGS: -DUSE_ASSERT_CHECKING
|
||||
# windows:
|
||||
# runs-on: ${{ matrix.os }}
|
||||
# if: ${{ !startsWith(github.ref_name, 'mac') }}
|
||||
# strategy:
|
||||
# fail-fast: false
|
||||
# matrix:
|
||||
# include:
|
||||
# - postgres: 17
|
||||
# os: windows-2025
|
||||
# - postgres: 14
|
||||
# os: windows-2022
|
||||
# steps:
|
||||
# - uses: actions/checkout@v5
|
||||
# - uses: ankane/setup-postgres@v1
|
||||
# with:
|
||||
# postgres-version: ${{ matrix.postgres }}
|
||||
# - run: |
|
||||
# call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvars64.bat" && ^
|
||||
# nmake /NOLOGO /F Makefile.win && ^
|
||||
# nmake /NOLOGO /F Makefile.win install && ^
|
||||
# nmake /NOLOGO /F Makefile.win installcheck ${{ matrix.postgres != 17 && 'PG_REGRESS=$(PGROOT)\bin\pg_regress' || '' }} && ^
|
||||
# nmake /NOLOGO /F Makefile.win clean && ^
|
||||
# nmake /NOLOGO /F Makefile.win uninstall
|
||||
# shell: cmd
|
||||
# - if: ${{ failure() }}
|
||||
# run: cat regression.diffs
|
||||
i386:
|
||||
if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
|
||||
runs-on: ubuntu-latest
|
||||
container:
|
||||
image: debian:12
|
||||
image: alpine:3.23
|
||||
options: --platform linux/386
|
||||
steps:
|
||||
- run: apt-get update && apt-get install -y build-essential git libipc-run-perl postgresql-15 postgresql-server-dev-15 sudo
|
||||
- run: service postgresql start
|
||||
- run: apk add --update build-base git openrc perl perl-ipc-run perl-test-harness-utils postgresql18 postgresql18-dev
|
||||
- run: mkdir /run/openrc && touch /run/openrc/softlevel && rc-update add postgresql && rc-service postgresql start
|
||||
- run: |
|
||||
git clone https://github.com/${{ github.repository }}.git pgvector
|
||||
cd pgvector
|
||||
@@ -123,21 +123,21 @@ jobs:
|
||||
make
|
||||
make install
|
||||
chown -R postgres .
|
||||
sudo -u postgres make installcheck
|
||||
sudo -u postgres make prove_installcheck
|
||||
su postgres -c "make installcheck"
|
||||
su postgres -c "make prove_installcheck"
|
||||
env:
|
||||
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
|
||||
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare -Wno-missing-field-initializers
|
||||
- if: ${{ failure() }}
|
||||
run: cat pgvector/regression.diffs
|
||||
valgrind:
|
||||
if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- uses: ankane/setup-postgres-valgrind@v1
|
||||
with:
|
||||
postgres-version: 18
|
||||
check-ub: yes
|
||||
- run: make OPTFLAGS=""
|
||||
- run: sudo --preserve-env=PG_CONFIG make install
|
||||
- run: make installcheck
|
||||
# valgrind:
|
||||
# if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
|
||||
# runs-on: ubuntu-latest
|
||||
# steps:
|
||||
# - uses: actions/checkout@v5
|
||||
# - uses: ankane/setup-postgres-valgrind@v1
|
||||
# with:
|
||||
# postgres-version: 18
|
||||
# check-ub: yes
|
||||
# - run: make OPTFLAGS=""
|
||||
# - run: sudo --preserve-env=PG_CONFIG make install
|
||||
# - run: make installcheck
|
||||
|
||||
2
LICENSE
2
LICENSE
@@ -1,4 +1,4 @@
|
||||
Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
|
||||
Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group
|
||||
|
||||
Portions Copyright (c) 1994, The Regents of the University of California
|
||||
|
||||
|
||||
5
Makefile
5
Makefile
@@ -27,6 +27,11 @@ ifneq ($(filter ppc64%, $(shell uname -m)), )
|
||||
OPTFLAGS =
|
||||
endif
|
||||
|
||||
# RISC-V64 doesn't support -march=native
|
||||
ifeq ($(shell uname -m), riscv64)
|
||||
OPTFLAGS =
|
||||
endif
|
||||
|
||||
# For auto-vectorization:
|
||||
# - GCC (needs -ftree-vectorize OR -O3) - https://gcc.gnu.org/projects/tree-ssa/vectorization.html
|
||||
# - Clang (could use pragma instead) - https://llvm.org/docs/Vectorizers.html
|
||||
|
||||
@@ -776,6 +776,7 @@ Algol | [pgvector-algol](https://github.com/pgvector/pgvector-algol)
|
||||
C | [pgvector-c](https://github.com/pgvector/pgvector-c)
|
||||
C++ | [pgvector-cpp](https://github.com/pgvector/pgvector-cpp)
|
||||
C#, F#, Visual Basic | [pgvector-dotnet](https://github.com/pgvector/pgvector-dotnet)
|
||||
COBOL | [pgvector-cobol](https://github.com/pgvector/pgvector-cobol)
|
||||
Crystal | [pgvector-crystal](https://github.com/pgvector/pgvector-crystal)
|
||||
D | [pgvector-d](https://github.com/pgvector/pgvector-d)
|
||||
Dart | [pgvector-dart](https://github.com/pgvector/pgvector-dart)
|
||||
@@ -803,6 +804,7 @@ Raku | [pgvector-raku](https://github.com/pgvector/pgvector-raku)
|
||||
Ruby | [pgvector-ruby](https://github.com/pgvector/pgvector-ruby), [Neighbor](https://github.com/ankane/neighbor)
|
||||
Rust | [pgvector-rust](https://github.com/pgvector/pgvector-rust)
|
||||
Swift | [pgvector-swift](https://github.com/pgvector/pgvector-swift)
|
||||
Tcl | [pgvector-tcl](https://github.com/pgvector/pgvector-tcl)
|
||||
Zig | [pgvector-zig](https://github.com/pgvector/pgvector-zig)
|
||||
|
||||
## Frequently Asked Questions
|
||||
@@ -1282,7 +1284,6 @@ Thanks to:
|
||||
- [k-means++: The Advantage of Careful Seeding](https://theory.stanford.edu/~sergei/papers/kMeansPP-soda.pdf)
|
||||
- [Concept Decompositions for Large Sparse Text Data using Clustering](https://www.cs.utexas.edu/users/inderjit/public_papers/concept_mlj.pdf)
|
||||
- [Efficient and Robust Approximate Nearest Neighbor Search using Hierarchical Navigable Small World Graphs](https://arxiv.org/ftp/arxiv/papers/1603/1603.09320.pdf)
|
||||
- [Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search](https://arxiv.org/pdf/2505.15636)
|
||||
|
||||
## History
|
||||
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
|
||||
#include "bitutils.h"
|
||||
#include "bitvec.h"
|
||||
#include "fmgr.h"
|
||||
#include "utils/varbit.h"
|
||||
#include "vector.h"
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
#include "postgres.h"
|
||||
|
||||
#include <math.h>
|
||||
|
||||
#include "halfutils.h"
|
||||
#include "halfvec.h"
|
||||
|
||||
|
||||
@@ -13,12 +13,20 @@
|
||||
#include "port.h" /* for strtof() */
|
||||
#include "sparsevec.h"
|
||||
#include "utils/array.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/float.h"
|
||||
#include "utils/fmgrprotos.h"
|
||||
#include "utils/lsyscache.h"
|
||||
#include "utils/numeric.h"
|
||||
#include "utils/varbit.h"
|
||||
#include "vector.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
#endif
|
||||
|
||||
#if PG_VERSION_NUM >= 170000
|
||||
#include "parser/scansup.h"
|
||||
#endif
|
||||
|
||||
#define STATE_DIMS(x) (ARR_DIMS(x)[0] - 1)
|
||||
#define CreateStateDatums(dim) palloc(sizeof(Datum) * (dim + 1))
|
||||
|
||||
@@ -129,9 +137,9 @@ InitHalfVector(int dim)
|
||||
return result;
|
||||
}
|
||||
|
||||
/*
|
||||
* Check for whitespace, since array_isspace() is static
|
||||
*/
|
||||
#if PG_VERSION_NUM >= 170000
|
||||
#define halfvec_isspace(ch) scanner_isspace(ch)
|
||||
#else
|
||||
static inline bool
|
||||
halfvec_isspace(char ch)
|
||||
{
|
||||
@@ -144,6 +152,7 @@ halfvec_isspace(char ch)
|
||||
return true;
|
||||
return false;
|
||||
}
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Check state array
|
||||
|
||||
@@ -1,18 +1,24 @@
|
||||
#include "postgres.h"
|
||||
|
||||
#include <float.h>
|
||||
#include <limits.h>
|
||||
#include <math.h>
|
||||
|
||||
#include "access/amapi.h"
|
||||
#include "access/genam.h"
|
||||
#include "access/reloptions.h"
|
||||
#include "commands/progress.h"
|
||||
#include "commands/vacuum.h"
|
||||
#include "fmgr.h"
|
||||
#include "hnsw.h"
|
||||
#include "miscadmin.h"
|
||||
#include "nodes/pg_list.h"
|
||||
#include "utils/float.h"
|
||||
#include "utils/guc.h"
|
||||
#include "utils/relcache.h"
|
||||
#include "utils/selfuncs.h"
|
||||
#include "utils/spccache.h"
|
||||
#include "vector.h"
|
||||
|
||||
#if PG_VERSION_NUM < 150000
|
||||
#define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
|
||||
|
||||
@@ -3,6 +3,8 @@
|
||||
|
||||
#include "postgres.h"
|
||||
|
||||
#include <math.h>
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/parallel.h"
|
||||
#include "lib/pairingheap.h"
|
||||
@@ -12,6 +14,10 @@
|
||||
#include "utils/sampling.h"
|
||||
#include "vector.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 190000
|
||||
typedef Pointer Item;
|
||||
#endif
|
||||
|
||||
#define HNSW_MAX_DIM 2000
|
||||
#define HNSW_MAX_NNZ 1000
|
||||
|
||||
@@ -424,7 +430,7 @@ void *HnswAlloc(HnswAllocator * allocator, Size size);
|
||||
HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
|
||||
HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
|
||||
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing);
|
||||
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, HnswSupport * support, bool loadVec);
|
||||
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec);
|
||||
void HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
|
||||
void HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
|
||||
void HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
|
||||
|
||||
@@ -36,11 +36,12 @@
|
||||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include <math.h>
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/parallel.h"
|
||||
#include "access/relscan.h"
|
||||
#include "access/table.h"
|
||||
#include "access/tableam.h"
|
||||
#include "access/tupdesc.h"
|
||||
#include "access/xact.h"
|
||||
#include "access/xloginsert.h"
|
||||
#include "catalog/index.h"
|
||||
@@ -48,11 +49,14 @@
|
||||
#include "commands/progress.h"
|
||||
#include "hnsw.h"
|
||||
#include "miscadmin.h"
|
||||
#include "nodes/execnodes.h"
|
||||
#include "optimizer/optimizer.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "tcop/tcopprot.h"
|
||||
#include "utils/datum.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/rel.h"
|
||||
#include "utils/snapmgr.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
@@ -549,7 +553,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
|
||||
|
||||
/* Copy the datum */
|
||||
memcpy(valuePtr, DatumGetPointer(value), valueSize);
|
||||
HnswPtrStore(base, element->value, valuePtr);
|
||||
HnswPtrStore(base, element->value, (char *) valuePtr);
|
||||
|
||||
/* Create a lock for the element */
|
||||
LWLockInitialize(&element->lock, hnsw_lock_tranche_id);
|
||||
|
||||
@@ -1,13 +1,14 @@
|
||||
#include "postgres.h"
|
||||
|
||||
#include <math.h>
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/generic_xlog.h"
|
||||
#include "hnsw.h"
|
||||
#include "nodes/execnodes.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/lmgr.h"
|
||||
#include "utils/datum.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/rel.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
@@ -712,7 +713,7 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
|
||||
|
||||
/* Create an element */
|
||||
element = HnswInitElement(base, heaptid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
|
||||
HnswPtrStore(base, element->value, DatumGetPointer(value));
|
||||
HnswPtrStore(base, element->value, (char *) DatumGetPointer(value));
|
||||
|
||||
/* Prevent concurrent inserts when likely updating entry point */
|
||||
if (entryPoint == NULL || element->level > entryPoint->level)
|
||||
|
||||
@@ -1,12 +1,21 @@
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/relscan.h"
|
||||
#include "hnsw.h"
|
||||
#include "lib/pairingheap.h"
|
||||
#include "miscadmin.h"
|
||||
#include "nodes/pg_list.h"
|
||||
#include "pgstat.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/lmgr.h"
|
||||
#include "utils/float.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/relcache.h"
|
||||
#include "utils/snapmgr.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Algorithm 5 from paper
|
||||
|
||||
@@ -2,18 +2,20 @@
|
||||
|
||||
#include <math.h>
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/generic_xlog.h"
|
||||
#include "catalog/pg_type.h"
|
||||
#include "catalog/pg_type_d.h"
|
||||
#include "common/hashfn.h"
|
||||
#include "fmgr.h"
|
||||
#include "hnsw.h"
|
||||
#include "lib/pairingheap.h"
|
||||
#include "nodes/pg_list.h"
|
||||
#include "port/atomics.h"
|
||||
#include "sparsevec.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "utils/datum.h"
|
||||
#include "utils/memdebug.h"
|
||||
#include "utils/rel.h"
|
||||
#include "vector.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
@@ -260,7 +262,7 @@ HnswInitElement(char *base, ItemPointer heaptid, int m, double ml, int maxLevel,
|
||||
|
||||
HnswInitNeighbors(base, element, m, allocator);
|
||||
|
||||
HnswPtrStore(base, element->value, (Pointer) NULL);
|
||||
HnswPtrStore(base, element->value, (char *) NULL);
|
||||
|
||||
return element;
|
||||
}
|
||||
@@ -286,7 +288,7 @@ HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno)
|
||||
element->blkno = blkno;
|
||||
element->offno = offno;
|
||||
HnswPtrStore(base, element->neighbors, (HnswNeighborArrayPtr *) NULL);
|
||||
HnswPtrStore(base, element->value, (Pointer) NULL);
|
||||
HnswPtrStore(base, element->value, (char *) NULL);
|
||||
return element;
|
||||
}
|
||||
|
||||
@@ -512,7 +514,7 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
|
||||
char *base = NULL;
|
||||
Datum value = datumCopy(PointerGetDatum(&etup->data), false, -1);
|
||||
|
||||
HnswPtrStore(base, element->value, DatumGetPointer(value));
|
||||
HnswPtrStore(base, element->value, (char *) DatumGetPointer(value));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -829,7 +831,6 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
||||
HnswUnvisited *unvisited = palloc(lm * sizeof(HnswUnvisited));
|
||||
int unvisitedLength;
|
||||
bool inMemory = index == NULL;
|
||||
double lambda = 0.12;
|
||||
|
||||
if (v == NULL)
|
||||
{
|
||||
@@ -885,7 +886,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
||||
HnswSearchCandidate *f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
|
||||
HnswElement cElement;
|
||||
|
||||
if (c->distance > f->distance * (1 + lambda))
|
||||
if (c->distance > f->distance)
|
||||
break;
|
||||
|
||||
cElement = HnswPtrAccess(base, c->element);
|
||||
@@ -905,10 +906,8 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
||||
HnswSearchCandidate *e;
|
||||
double eDistance;
|
||||
bool alwaysAdd = wlen < ef;
|
||||
double fDistance;
|
||||
|
||||
f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
|
||||
fDistance = f->distance * (1 + lambda);
|
||||
|
||||
if (inMemory)
|
||||
{
|
||||
@@ -923,13 +922,13 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
||||
|
||||
/* Avoid any allocations if not adding */
|
||||
eElement = NULL;
|
||||
HnswLoadElementImpl(blkno, offno, &eDistance, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &fDistance, &eElement);
|
||||
HnswLoadElementImpl(blkno, offno, &eDistance, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
|
||||
|
||||
if (eElement == NULL)
|
||||
continue;
|
||||
}
|
||||
|
||||
if (eElement == NULL || !(eDistance < fDistance || alwaysAdd))
|
||||
if (!(eDistance < f->distance || alwaysAdd))
|
||||
{
|
||||
if (discarded != NULL)
|
||||
{
|
||||
|
||||
@@ -1,13 +1,14 @@
|
||||
#include "postgres.h"
|
||||
|
||||
#include <math.h>
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/generic_xlog.h"
|
||||
#include "commands/vacuum.h"
|
||||
#include "hnsw.h"
|
||||
#include "nodes/pg_list.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/lmgr.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/rel.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
@@ -178,7 +179,12 @@ NeedsUpdated(HnswVacuumState * vacuumstate, HnswElement element)
|
||||
/* Also update if layer 0 is not full */
|
||||
/* This could indicate too many candidates being deleted during insert */
|
||||
if (!needsUpdated)
|
||||
{
|
||||
/* Keep clang-tidy happy */
|
||||
Assert(ntup->count > 0);
|
||||
|
||||
needsUpdated = !ItemPointerIsValid(&ntup->indextids[ntup->count - 1]);
|
||||
}
|
||||
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
@@ -528,8 +534,9 @@ MarkDeleted(HnswVacuumState * vacuumstate)
|
||||
ntup = (HnswNeighborTuple) PageGetItem(npage, PageGetItemId(npage, neighborOffno));
|
||||
|
||||
/* Overwrite element */
|
||||
/* Use memset instead of MemSet to keep clang-tidy happy */
|
||||
etup->deleted = 1;
|
||||
MemSet(&etup->data, 0, VARSIZE_ANY(&etup->data));
|
||||
memset(&etup->data, 0, VARSIZE_ANY(&etup->data));
|
||||
|
||||
/* Overwrite neighbors */
|
||||
for (int i = 0; i < ntup->count; i++)
|
||||
|
||||
@@ -2,23 +2,32 @@
|
||||
|
||||
#include <float.h>
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/generic_xlog.h"
|
||||
#include "access/itup.h"
|
||||
#include "access/relscan.h"
|
||||
#include "access/table.h"
|
||||
#include "access/tableam.h"
|
||||
#include "access/tupdesc.h"
|
||||
#include "access/parallel.h"
|
||||
#include "access/xact.h"
|
||||
#include "bitvec.h"
|
||||
#include "access/xloginsert.h"
|
||||
#include "catalog/index.h"
|
||||
#include "catalog/pg_operator_d.h"
|
||||
#include "catalog/pg_type_d.h"
|
||||
#include "commands/progress.h"
|
||||
#include "halfvec.h"
|
||||
#include "fmgr.h"
|
||||
#include "ivfflat.h"
|
||||
#include "miscadmin.h"
|
||||
#include "nodes/execnodes.h"
|
||||
#include "optimizer/optimizer.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "tcop/tcopprot.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "vector.h"
|
||||
#include "utils/rel.h"
|
||||
#include "utils/sampling.h"
|
||||
#include "utils/snapmgr.h"
|
||||
#include "utils/tuplesort.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
|
||||
@@ -3,14 +3,19 @@
|
||||
#include <float.h>
|
||||
|
||||
#include "access/amapi.h"
|
||||
#include "access/genam.h"
|
||||
#include "access/reloptions.h"
|
||||
#include "commands/progress.h"
|
||||
#include "commands/vacuum.h"
|
||||
#include "fmgr.h"
|
||||
#include "ivfflat.h"
|
||||
#include "nodes/pg_list.h"
|
||||
#include "utils/float.h"
|
||||
#include "utils/guc.h"
|
||||
#include "utils/relcache.h"
|
||||
#include "utils/selfuncs.h"
|
||||
#include "utils/spccache.h"
|
||||
#include "vector.h"
|
||||
|
||||
#if PG_VERSION_NUM < 150000
|
||||
#define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
|
||||
|
||||
@@ -25,6 +25,10 @@
|
||||
#include "portability/instr_time.h"
|
||||
#endif
|
||||
|
||||
#if PG_VERSION_NUM >= 190000
|
||||
typedef Pointer Item;
|
||||
#endif
|
||||
|
||||
#define IVFFLAT_MAX_DIM 2000
|
||||
|
||||
/* Support functions */
|
||||
|
||||
@@ -2,11 +2,16 @@
|
||||
|
||||
#include <float.h>
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/generic_xlog.h"
|
||||
#include "access/itup.h"
|
||||
#include "fmgr.h"
|
||||
#include "ivfflat.h"
|
||||
#include "nodes/execnodes.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/lmgr.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/rel.h"
|
||||
|
||||
/*
|
||||
* Find the list that minimizes the distance function
|
||||
|
||||
@@ -1,17 +1,15 @@
|
||||
#include "postgres.h"
|
||||
|
||||
#include <float.h>
|
||||
#include <limits.h>
|
||||
#include <math.h>
|
||||
|
||||
#include "bitvec.h"
|
||||
#include "halfutils.h"
|
||||
#include "halfvec.h"
|
||||
#include "access/genam.h"
|
||||
#include "fmgr.h"
|
||||
#include "ivfflat.h"
|
||||
#include "miscadmin.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/datum.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "vector.h"
|
||||
#include "utils/relcache.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
|
||||
@@ -2,15 +2,26 @@
|
||||
|
||||
#include <float.h>
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/itup.h"
|
||||
#include "access/relscan.h"
|
||||
#include "access/tupdesc.h"
|
||||
#include "catalog/pg_operator_d.h"
|
||||
#include "catalog/pg_type_d.h"
|
||||
#include "fmgr.h"
|
||||
#include "lib/pairingheap.h"
|
||||
#include "ivfflat.h"
|
||||
#include "miscadmin.h"
|
||||
#include "pgstat.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "utils/memutils.h"
|
||||
#include "utils/rel.h"
|
||||
#include "utils/snapmgr.h"
|
||||
#include "utils/tuplesort.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
#endif
|
||||
|
||||
#define GetScanList(ptr) pairingheap_container(IvfflatScanList, ph_node, ptr)
|
||||
#define GetScanListConst(ptr) pairingheap_const_container(IvfflatScanList, ph_node, ptr)
|
||||
|
||||
@@ -1,13 +1,19 @@
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/generic_xlog.h"
|
||||
#include "bitvec.h"
|
||||
#include "catalog/pg_type.h"
|
||||
#include "fmgr.h"
|
||||
#include "halfutils.h"
|
||||
#include "halfvec.h"
|
||||
#include "ivfflat.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "utils/relcache.h"
|
||||
#include "utils/varbit.h"
|
||||
#include "vector.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Allocate a vector array
|
||||
|
||||
@@ -1,9 +1,12 @@
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/generic_xlog.h"
|
||||
#include "access/itup.h"
|
||||
#include "commands/vacuum.h"
|
||||
#include "ivfflat.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "utils/relcache.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 180000
|
||||
#define vacuum_delay_point() vacuum_delay_point(false)
|
||||
|
||||
@@ -5,18 +5,27 @@
|
||||
|
||||
#include "catalog/pg_type.h"
|
||||
#include "common/shortest_dec.h"
|
||||
#include "common/string.h"
|
||||
#include "fmgr.h"
|
||||
#include "halfutils.h"
|
||||
#include "halfvec.h"
|
||||
#include "lib/stringinfo.h"
|
||||
#include "libpq/pqformat.h"
|
||||
#include "sparsevec.h"
|
||||
#include "utils/array.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/float.h"
|
||||
#include "utils/fmgrprotos.h"
|
||||
#include "utils/lsyscache.h"
|
||||
#include "vector.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
#endif
|
||||
|
||||
#if PG_VERSION_NUM >= 170000
|
||||
#include "parser/scansup.h"
|
||||
#endif
|
||||
|
||||
typedef struct SparseInputElement
|
||||
{
|
||||
int32 index;
|
||||
@@ -150,9 +159,9 @@ InitSparseVector(int dim, int nnz)
|
||||
return result;
|
||||
}
|
||||
|
||||
/*
|
||||
* Check for whitespace, since array_isspace() is static
|
||||
*/
|
||||
#if PG_VERSION_NUM >= 170000
|
||||
#define sparsevec_isspace(ch) scanner_isspace(ch)
|
||||
#else
|
||||
static inline bool
|
||||
sparsevec_isspace(char ch)
|
||||
{
|
||||
@@ -165,6 +174,7 @@ sparsevec_isspace(char ch)
|
||||
return true;
|
||||
return false;
|
||||
}
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Compare indices
|
||||
|
||||
15
src/vector.c
15
src/vector.c
@@ -16,16 +16,20 @@
|
||||
#include "port.h" /* for strtof() */
|
||||
#include "sparsevec.h"
|
||||
#include "utils/array.h"
|
||||
#include "utils/builtins.h"
|
||||
#include "utils/float.h"
|
||||
#include "utils/fmgrprotos.h"
|
||||
#include "utils/lsyscache.h"
|
||||
#include "utils/numeric.h"
|
||||
#include "utils/varbit.h"
|
||||
#include "vector.h"
|
||||
|
||||
#if PG_VERSION_NUM >= 160000
|
||||
#include "varatt.h"
|
||||
#endif
|
||||
|
||||
#if PG_VERSION_NUM >= 170000
|
||||
#include "parser/scansup.h"
|
||||
#endif
|
||||
|
||||
#define STATE_DIMS(x) (ARR_DIMS(x)[0] - 1)
|
||||
#define CreateStateDatums(dim) palloc(sizeof(Datum) * (dim + 1))
|
||||
|
||||
@@ -129,9 +133,9 @@ InitVector(int dim)
|
||||
return result;
|
||||
}
|
||||
|
||||
/*
|
||||
* Check for whitespace, since array_isspace() is static
|
||||
*/
|
||||
#if PG_VERSION_NUM >= 170000
|
||||
#define vector_isspace(ch) scanner_isspace(ch)
|
||||
#else
|
||||
static inline bool
|
||||
vector_isspace(char ch)
|
||||
{
|
||||
@@ -144,6 +148,7 @@ vector_isspace(char ch)
|
||||
return true;
|
||||
return false;
|
||||
}
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Check state array
|
||||
|
||||
@@ -16,29 +16,19 @@ $node->safe_psql("postgres",
|
||||
"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 100000) i;"
|
||||
);
|
||||
|
||||
# Check each index type
|
||||
my @operators = ("<->", "<#>", "<=>");
|
||||
my @opclasses = ("vector_l2_ops", "vector_ip_ops", "vector_cosine_ops");
|
||||
# Add index
|
||||
$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
|
||||
|
||||
for my $i (0 .. $#operators)
|
||||
# Test 100% recall
|
||||
for (1 .. 20)
|
||||
{
|
||||
my $operator = $operators[$i];
|
||||
my $opclass = $opclasses[$i];
|
||||
|
||||
# Add index
|
||||
$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v $opclass);");
|
||||
|
||||
# Test 100% recall
|
||||
for (1 .. 20)
|
||||
{
|
||||
my $id = int(rand() * 100000);
|
||||
my $query = $node->safe_psql("postgres", "SELECT v FROM tst WHERE i = $id;");
|
||||
my $res = $node->safe_psql("postgres", qq(
|
||||
SET enable_seqscan = off;
|
||||
SELECT v FROM tst ORDER BY v <-> '$query' LIMIT 1;
|
||||
));
|
||||
is($res, $query);
|
||||
}
|
||||
my $id = int(rand() * 100000);
|
||||
my $query = $node->safe_psql("postgres", "SELECT v FROM tst WHERE i = $id;");
|
||||
my $res = $node->safe_psql("postgres", qq(
|
||||
SET enable_seqscan = off;
|
||||
SELECT v FROM tst ORDER BY v <-> '$query' LIMIT 1;
|
||||
));
|
||||
is($res, $query);
|
||||
}
|
||||
|
||||
done_testing();
|
||||
|
||||
Reference in New Issue
Block a user