mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-22 20:15:46 +08:00
Compare commits
3 Commits
hnsw-datum
...
ci6
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
491804d99f | ||
|
|
f43cd0ed98 | ||
|
|
51df640961 |
63
.github/workflows/build.yml
vendored
63
.github/workflows/build.yml
vendored
@@ -29,9 +29,7 @@ jobs:
|
|||||||
- run: make
|
- run: make
|
||||||
env:
|
env:
|
||||||
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
|
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
|
||||||
- run: |
|
- run: sudo make install
|
||||||
export PG_CONFIG=`which pg_config`
|
|
||||||
sudo --preserve-env=PG_CONFIG make install
|
|
||||||
- run: make installcheck
|
- run: make installcheck
|
||||||
- if: ${{ failure() }}
|
- if: ${{ failure() }}
|
||||||
run: cat regression.diffs
|
run: cat regression.diffs
|
||||||
@@ -39,62 +37,3 @@ jobs:
|
|||||||
sudo apt-get update
|
sudo apt-get update
|
||||||
sudo apt-get install libipc-run-perl
|
sudo apt-get install libipc-run-perl
|
||||||
- run: make prove_installcheck
|
- run: make prove_installcheck
|
||||||
mac:
|
|
||||||
runs-on: macos-latest
|
|
||||||
if: ${{ !startsWith(github.ref_name, 'windows') }}
|
|
||||||
steps:
|
|
||||||
- uses: actions/checkout@v4
|
|
||||||
- uses: ankane/setup-postgres@v1
|
|
||||||
with:
|
|
||||||
postgres-version: 14
|
|
||||||
- run: make
|
|
||||||
env:
|
|
||||||
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter
|
|
||||||
- run: make install
|
|
||||||
- run: make installcheck
|
|
||||||
- if: ${{ failure() }}
|
|
||||||
run: cat regression.diffs
|
|
||||||
- run: |
|
|
||||||
brew install cpanm
|
|
||||||
cpanm --notest IPC::Run
|
|
||||||
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"
|
|
||||||
windows:
|
|
||||||
runs-on: windows-latest
|
|
||||||
if: ${{ !startsWith(github.ref_name, 'mac') }}
|
|
||||||
steps:
|
|
||||||
- uses: actions/checkout@v4
|
|
||||||
- uses: ankane/setup-postgres@v1
|
|
||||||
with:
|
|
||||||
postgres-version: 14
|
|
||||||
- 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 && ^
|
|
||||||
nmake /NOLOGO /F Makefile.win clean && ^
|
|
||||||
nmake /NOLOGO /F Makefile.win uninstall
|
|
||||||
shell: cmd
|
|
||||||
i386:
|
|
||||||
if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
|
|
||||||
runs-on: ubuntu-latest
|
|
||||||
container:
|
|
||||||
image: debian:12
|
|
||||||
options: --platform linux/386
|
|
||||||
steps:
|
|
||||||
- run: apt-get update && apt-get install -y build-essential git libipc-run-perl postgresql-15 postgresql-server-dev-15 sudo
|
|
||||||
- run: service postgresql start
|
|
||||||
- run: |
|
|
||||||
git clone https://github.com/${{ github.repository }}.git pgvector
|
|
||||||
cd pgvector
|
|
||||||
git fetch origin ${{ github.ref }}
|
|
||||||
git reset --hard FETCH_HEAD
|
|
||||||
make
|
|
||||||
make install
|
|
||||||
chown -R postgres .
|
|
||||||
sudo -u postgres make installcheck
|
|
||||||
sudo -u postgres make prove_installcheck
|
|
||||||
env:
|
|
||||||
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
|
|
||||||
|
|||||||
17
README.md
17
README.md
@@ -28,7 +28,7 @@ make install # may need sudo
|
|||||||
|
|
||||||
See the [installation notes](#installation-notes) if you run into issues
|
See the [installation notes](#installation-notes) if you run into issues
|
||||||
|
|
||||||
You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres). There are also instructions for [GitHub Actions](https://github.com/pgvector/setup-pgvector).
|
You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), [pkg](#pkg), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres). There are also instructions for [GitHub Actions](https://github.com/pgvector/setup-pgvector).
|
||||||
|
|
||||||
### Windows
|
### Windows
|
||||||
|
|
||||||
@@ -716,6 +716,21 @@ sudo dnf install pgvector_16
|
|||||||
|
|
||||||
Note: Replace `16` with your Postgres server version
|
Note: Replace `16` with your Postgres server version
|
||||||
|
|
||||||
|
### pkg
|
||||||
|
|
||||||
|
Install the FreeBSD package with:
|
||||||
|
|
||||||
|
```sh
|
||||||
|
pkg install postgresql15-pg_vector
|
||||||
|
```
|
||||||
|
|
||||||
|
or the port with:
|
||||||
|
|
||||||
|
```sh
|
||||||
|
cd /usr/ports/databases/pg_vector
|
||||||
|
make install
|
||||||
|
```
|
||||||
|
|
||||||
### conda-forge
|
### conda-forge
|
||||||
|
|
||||||
With Conda Postgres, install from [conda-forge](https://anaconda.org/conda-forge/pgvector) with:
|
With Conda Postgres, install from [conda-forge](https://anaconda.org/conda-forge/pgvector) with:
|
||||||
|
|||||||
@@ -176,7 +176,7 @@ CreateGraphPages(HnswBuildState * buildstate)
|
|||||||
Size etupSize;
|
Size etupSize;
|
||||||
Size ntupSize;
|
Size ntupSize;
|
||||||
Size combinedSize;
|
Size combinedSize;
|
||||||
void *valuePtr = HnswPtrAccess(base, element->value);
|
Pointer valuePtr = HnswPtrAccess(base, element->value);
|
||||||
|
|
||||||
/* Update iterator */
|
/* Update iterator */
|
||||||
iter = element->next;
|
iter = element->next;
|
||||||
@@ -669,6 +669,10 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
|
|||||||
buildstate->efConstruction = HnswGetEfConstruction(index);
|
buildstate->efConstruction = HnswGetEfConstruction(index);
|
||||||
buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
|
buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
|
||||||
|
|
||||||
|
/* Require column to have dimensions to be indexed */
|
||||||
|
if (buildstate->dimensions < 0)
|
||||||
|
elog(ERROR, "column does not have dimensions");
|
||||||
|
|
||||||
if (buildstate->dimensions > HNSW_MAX_DIM)
|
if (buildstate->dimensions > HNSW_MAX_DIM)
|
||||||
elog(ERROR, "column cannot have more than %d dimensions for hnsw index", HNSW_MAX_DIM);
|
elog(ERROR, "column cannot have more than %d dimensions for hnsw index", HNSW_MAX_DIM);
|
||||||
|
|
||||||
|
|||||||
@@ -1,113 +0,0 @@
|
|||||||
use strict;
|
|
||||||
use warnings;
|
|
||||||
use PostgresNode;
|
|
||||||
use TestLib;
|
|
||||||
use Test::More;
|
|
||||||
|
|
||||||
my $node;
|
|
||||||
my @queries = ();
|
|
||||||
my @expected;
|
|
||||||
my $limit = 20;
|
|
||||||
|
|
||||||
sub test_recall
|
|
||||||
{
|
|
||||||
my ($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 ORDER BY v $operator '$queries[0]' LIMIT $limit;
|
|
||||||
));
|
|
||||||
like($explain, qr/Index Scan/);
|
|
||||||
|
|
||||||
for my $i (0 .. $#queries)
|
|
||||||
{
|
|
||||||
my $actual = $node->safe_psql("postgres", qq(
|
|
||||||
SET enable_seqscan = off;
|
|
||||||
SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit;
|
|
||||||
));
|
|
||||||
my @actual_ids = split("\n", $actual);
|
|
||||||
my %actual_set = map { $_ => 1 } @actual_ids;
|
|
||||||
|
|
||||||
my @expected_ids = split("\n", $expected[$i]);
|
|
||||||
|
|
||||||
foreach (@expected_ids)
|
|
||||||
{
|
|
||||||
if (exists($actual_set{$_}))
|
|
||||||
{
|
|
||||||
$correct++;
|
|
||||||
}
|
|
||||||
$total++;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
cmp_ok($correct / $total, ">=", $min, $operator);
|
|
||||||
}
|
|
||||||
|
|
||||||
# Initialize node
|
|
||||||
$node = get_new_node('node');
|
|
||||||
$node->init;
|
|
||||||
$node->start;
|
|
||||||
|
|
||||||
# Create table
|
|
||||||
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
|
|
||||||
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v float4[3]);");
|
|
||||||
$node->safe_psql("postgres",
|
|
||||||
"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 10000) i;"
|
|
||||||
);
|
|
||||||
|
|
||||||
$node->safe_psql("postgres", qq(
|
|
||||||
CREATE FUNCTION float4_l2_distance(float4[], float4[]) RETURNS float8
|
|
||||||
AS 'BEGIN RETURN l2_distance(\$1::vector, \$2::vector); END;'
|
|
||||||
LANGUAGE plpgsql IMMUTABLE STRICT PARALLEL SAFE;
|
|
||||||
|
|
||||||
CREATE FUNCTION float4_l2_squared_distance(float4[], float4[]) RETURNS float8
|
|
||||||
AS 'BEGIN RETURN vector_l2_squared_distance(\$1::vector, \$2::vector); END;'
|
|
||||||
LANGUAGE plpgsql IMMUTABLE STRICT PARALLEL SAFE;
|
|
||||||
|
|
||||||
CREATE OPERATOR <-> (
|
|
||||||
LEFTARG = float4[], RIGHTARG = float4[], PROCEDURE = float4_l2_distance,
|
|
||||||
COMMUTATOR = '<->'
|
|
||||||
);
|
|
||||||
|
|
||||||
CREATE OPERATOR CLASS float4_l2_ops
|
|
||||||
FOR TYPE float4[] USING hnsw AS
|
|
||||||
OPERATOR 1 <-> (float4[], float4[]) FOR ORDER BY float_ops,
|
|
||||||
FUNCTION 1 float4_l2_squared_distance(float4[], float4[]);
|
|
||||||
));
|
|
||||||
|
|
||||||
# Generate queries
|
|
||||||
for (1 .. 20)
|
|
||||||
{
|
|
||||||
my $r1 = rand();
|
|
||||||
my $r2 = rand();
|
|
||||||
my $r3 = rand();
|
|
||||||
push(@queries, "{$r1,$r2,$r3}");
|
|
||||||
}
|
|
||||||
|
|
||||||
# Check each index type
|
|
||||||
my @operators = ("<->");
|
|
||||||
my @opclasses = ("float4_l2_ops");
|
|
||||||
|
|
||||||
for my $i (0 .. $#operators)
|
|
||||||
{
|
|
||||||
my $operator = $operators[$i];
|
|
||||||
my $opclass = $opclasses[$i];
|
|
||||||
|
|
||||||
# Get exact results
|
|
||||||
@expected = ();
|
|
||||||
foreach (@queries)
|
|
||||||
{
|
|
||||||
my $res = $node->safe_psql("postgres", "SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;");
|
|
||||||
push(@expected, $res);
|
|
||||||
}
|
|
||||||
|
|
||||||
# Add index
|
|
||||||
$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v $opclass);");
|
|
||||||
|
|
||||||
my $min = $operator eq "<#>" ? 0.80 : 0.99;
|
|
||||||
test_recall($min, $operator);
|
|
||||||
}
|
|
||||||
|
|
||||||
done_testing();
|
|
||||||
Reference in New Issue
Block a user