mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-22 20:15:46 +08:00
Compare commits
6 Commits
v0.6.0
...
hnsw-datum
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c8e4bf1c3c | ||
|
|
2716a223a6 | ||
|
|
3697043898 | ||
|
|
c22740962c | ||
|
|
a55ecf3281 | ||
|
|
fecdd5794e |
@@ -1,10 +1,14 @@
|
||||
## 0.6.1 (unreleased)
|
||||
|
||||
- Fixed error with `ANALYZE` and vectors with different dimensions
|
||||
|
||||
## 0.6.0 (2024-01-29)
|
||||
|
||||
If upgrading with Postgres 12 or Docker, see [these notes](https://github.com/pgvector/pgvector#060).
|
||||
|
||||
- Changed storage for vector from `extended` to `external`
|
||||
- Added support for parallel index builds for HNSW
|
||||
- Added validation for GUC parameters
|
||||
- Changed storage for vector from `extended` to `external`
|
||||
- Improved performance of HNSW
|
||||
- Reduced memory usage for HNSW index builds
|
||||
- Reduced WAL generation for HNSW index builds
|
||||
|
||||
13
README.md
13
README.md
@@ -16,7 +16,7 @@ Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recove
|
||||
|
||||
### Linux and Mac
|
||||
|
||||
Compile and install the extension (supports Postgres 11+)
|
||||
Compile and install the extension (supports Postgres 12+)
|
||||
|
||||
```sh
|
||||
cd /tmp
|
||||
@@ -430,6 +430,15 @@ 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);
|
||||
```
|
||||
|
||||
## Vacuuming
|
||||
|
||||
Vacuuming can take a while for HNSW indexes. Speed it up by reindexing first.
|
||||
|
||||
```sql
|
||||
REINDEX INDEX CONCURRENTLY index_name;
|
||||
VACUUM table_name;
|
||||
```
|
||||
|
||||
## 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.
|
||||
@@ -657,7 +666,7 @@ Get the [Docker image](https://hub.docker.com/r/pgvector/pgvector) with:
|
||||
docker pull pgvector/pgvector:pg16
|
||||
```
|
||||
|
||||
This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (run it the same way).
|
||||
This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (replace `16` with your Postgres server version, and run it the same way).
|
||||
|
||||
You can also build the image manually:
|
||||
|
||||
|
||||
@@ -669,10 +669,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
|
||||
buildstate->efConstruction = HnswGetEfConstruction(index);
|
||||
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)
|
||||
elog(ERROR, "column cannot have more than %d dimensions for hnsw index", HNSW_MAX_DIM);
|
||||
|
||||
|
||||
30
src/vector.c
30
src/vector.c
@@ -866,9 +866,10 @@ vector_mul(PG_FUNCTION_ARGS)
|
||||
int
|
||||
vector_cmp_internal(Vector * a, Vector * b)
|
||||
{
|
||||
CheckDims(a, b);
|
||||
int dim = Min(a->dim, b->dim);
|
||||
|
||||
for (int i = 0; i < a->dim; i++)
|
||||
/* Check values before dimensions to be consistent with Postgres arrays */
|
||||
for (int i = 0; i < dim; i++)
|
||||
{
|
||||
if (a->x[i] < b->x[i])
|
||||
return -1;
|
||||
@@ -876,6 +877,13 @@ vector_cmp_internal(Vector * a, Vector * b)
|
||||
if (a->x[i] > b->x[i])
|
||||
return 1;
|
||||
}
|
||||
|
||||
if (a->dim < b->dim)
|
||||
return -1;
|
||||
|
||||
if (a->dim > b->dim)
|
||||
return 1;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
@@ -889,6 +897,9 @@ vector_lt(PG_FUNCTION_ARGS)
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
|
||||
/* TODO Remove in 0.7.0 */
|
||||
CheckDims(a, b);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) < 0);
|
||||
}
|
||||
|
||||
@@ -902,6 +913,9 @@ vector_le(PG_FUNCTION_ARGS)
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
|
||||
/* TODO Remove in 0.7.0 */
|
||||
CheckDims(a, b);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) <= 0);
|
||||
}
|
||||
|
||||
@@ -915,6 +929,9 @@ vector_eq(PG_FUNCTION_ARGS)
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
|
||||
/* TODO Remove in 0.7.0 */
|
||||
CheckDims(a, b);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) == 0);
|
||||
}
|
||||
|
||||
@@ -928,6 +945,9 @@ vector_ne(PG_FUNCTION_ARGS)
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
|
||||
/* TODO Remove in 0.7.0 */
|
||||
CheckDims(a, b);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) != 0);
|
||||
}
|
||||
|
||||
@@ -941,6 +961,9 @@ vector_ge(PG_FUNCTION_ARGS)
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
|
||||
/* TODO Remove in 0.7.0 */
|
||||
CheckDims(a, b);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) >= 0);
|
||||
}
|
||||
|
||||
@@ -954,6 +977,9 @@ vector_gt(PG_FUNCTION_ARGS)
|
||||
Vector *a = PG_GETARG_VECTOR_P(0);
|
||||
Vector *b = PG_GETARG_VECTOR_P(1);
|
||||
|
||||
/* TODO Remove in 0.7.0 */
|
||||
CheckDims(a, b);
|
||||
|
||||
PG_RETURN_BOOL(vector_cmp_internal(a, b) > 0);
|
||||
}
|
||||
|
||||
|
||||
@@ -24,6 +24,56 @@ SELECT '[1e37]'::vector * '[1e37]';
|
||||
ERROR: value out of range: overflow
|
||||
SELECT '[1e-37]'::vector * '[1e-37]';
|
||||
ERROR: value out of range: underflow
|
||||
SELECT '[1,2,3]'::vector = '[1,2,3]';
|
||||
?column?
|
||||
----------
|
||||
t
|
||||
(1 row)
|
||||
|
||||
SELECT '[1,2,3]'::vector = '[1,2]';
|
||||
ERROR: different vector dimensions 3 and 2
|
||||
SELECT vector_cmp('[1,2,3]', '[1,2,3]');
|
||||
vector_cmp
|
||||
------------
|
||||
0
|
||||
(1 row)
|
||||
|
||||
SELECT vector_cmp('[1,2,3]', '[0,0,0]');
|
||||
vector_cmp
|
||||
------------
|
||||
1
|
||||
(1 row)
|
||||
|
||||
SELECT vector_cmp('[0,0,0]', '[1,2,3]');
|
||||
vector_cmp
|
||||
------------
|
||||
-1
|
||||
(1 row)
|
||||
|
||||
SELECT vector_cmp('[1,2]', '[1,2,3]');
|
||||
vector_cmp
|
||||
------------
|
||||
-1
|
||||
(1 row)
|
||||
|
||||
SELECT vector_cmp('[1,2,3]', '[1,2]');
|
||||
vector_cmp
|
||||
------------
|
||||
1
|
||||
(1 row)
|
||||
|
||||
SELECT vector_cmp('[1,2]', '[2,3,4]');
|
||||
vector_cmp
|
||||
------------
|
||||
-1
|
||||
(1 row)
|
||||
|
||||
SELECT vector_cmp('[2,3]', '[1,2,3]');
|
||||
vector_cmp
|
||||
------------
|
||||
1
|
||||
(1 row)
|
||||
|
||||
SELECT vector_dims('[1,2,3]');
|
||||
vector_dims
|
||||
-------------
|
||||
|
||||
@@ -6,6 +6,17 @@ SELECT '[1,2,3]'::vector * '[4,5,6]';
|
||||
SELECT '[1e37]'::vector * '[1e37]';
|
||||
SELECT '[1e-37]'::vector * '[1e-37]';
|
||||
|
||||
SELECT '[1,2,3]'::vector = '[1,2,3]';
|
||||
SELECT '[1,2,3]'::vector = '[1,2]';
|
||||
|
||||
SELECT vector_cmp('[1,2,3]', '[1,2,3]');
|
||||
SELECT vector_cmp('[1,2,3]', '[0,0,0]');
|
||||
SELECT vector_cmp('[0,0,0]', '[1,2,3]');
|
||||
SELECT vector_cmp('[1,2]', '[1,2,3]');
|
||||
SELECT vector_cmp('[1,2,3]', '[1,2]');
|
||||
SELECT vector_cmp('[1,2]', '[2,3,4]');
|
||||
SELECT vector_cmp('[2,3]', '[1,2,3]');
|
||||
|
||||
SELECT vector_dims('[1,2,3]');
|
||||
|
||||
SELECT round(vector_norm('[1,1]')::numeric, 5);
|
||||
|
||||
113
test/t/020_hnsw_array.pl
Normal file
113
test/t/020_hnsw_array.pl
Normal file
@@ -0,0 +1,113 @@
|
||||
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