Compare commits

...

5 Commits

Author SHA1 Message Date
Andrew Kane
2627c5ff77 Version bump to 0.8.0 [skip ci] 2024-10-30 13:06:34 -07:00
Andrew Kane
34b3cfdc43 Updated min Postgres version in META.json [skip ci] 2024-10-30 13:06:12 -07:00
Andrew Kane
cd218aae5a Removed unneeded code 2024-10-30 13:05:10 -07:00
Andrew Kane
ba9367f86c Updated readme [skip ci] 2024-10-30 12:58:00 -07:00
Andrew Kane
9c20550a41 Updated readme 2024-10-30 12:54:42 -07:00
7 changed files with 16 additions and 22 deletions

View File

@@ -1,4 +1,4 @@
## 0.8.0 (unreleased)
## 0.8.0 (2024-10-30)
- Added support for iterative index scans
- Added casts for arrays to `sparsevec`

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": "0.7.4",
"version": "0.8.0",
"maintainer": [
"Andrew Kane <andrew@ankane.org>"
],
@@ -12,7 +12,7 @@
"prereqs": {
"runtime": {
"requires": {
"PostgreSQL": "12.0.0"
"PostgreSQL": "13.0.0"
}
}
},
@@ -20,7 +20,7 @@
"vector": {
"file": "sql/vector.sql",
"docfile": "README.md",
"version": "0.7.4",
"version": "0.8.0",
"abstract": "Open-source vector similarity search for Postgres"
}
},

View File

@@ -1,5 +1,5 @@
EXTENSION = vector
EXTVERSION = 0.7.4
EXTVERSION = 0.8.0
MODULE_big = vector
DATA = $(wildcard sql/*--*--*.sql)

View File

@@ -1,5 +1,5 @@
EXTENSION = vector
EXTVERSION = 0.7.4
EXTVERSION = 0.8.0
DATA_built = sql\$(EXTENSION)--$(EXTVERSION).sql
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

View File

@@ -17,11 +17,11 @@ Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recove
### Linux and Mac
Compile and install the extension (supports Postgres 12+)
Compile and install the extension (supports Postgres 13+)
```sh
cd /tmp
git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git
git clone --branch v0.8.0 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 v0.7.4 https://github.com/pgvector/pgvector.git
git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
cd pgvector
nmake /F Makefile.win
nmake /F Makefile.win install
@@ -324,7 +324,7 @@ For a large number of workers, you may also need to increase `max_parallel_worke
### Indexing Progress
Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING)
```sql
SELECT phase, round(100.0 * blocks_done / nullif(blocks_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
@@ -410,7 +410,7 @@ For a large number of workers, you may also need to increase `max_parallel_worke
### Indexing Progress
Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING)
```sql
SELECT phase, round(100.0 * tuples_done / nullif(tuples_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
@@ -477,7 +477,7 @@ CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(cate
## Iterative Index Scans
*Unreleased*
*Added in 0.8.0*
With approximate indexes, queries with filtering can return less results since filtering is applied *after* the index is scanned. Starting with 0.8.0, you can enable iterative index scans, which will automatically scan more of the index until enough results are found (or it reaches `hnsw.max_scan_tuples` or `ivfflat.max_probes`).
@@ -1153,7 +1153,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
You can also build the image manually:
```sh
git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git
git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
cd pgvector
docker build --pull --build-arg PG_MAJOR=17 -t myuser/pgvector .
```

View File

@@ -4,6 +4,7 @@
#include <math.h>
#include "catalog/pg_type.h"
#include "common/shortest_dec.h"
#include "common/string.h"
#include "fmgr.h"
#include "halfutils.h"
@@ -12,17 +13,10 @@
#include "sparsevec.h"
#include "utils/array.h"
#include "utils/builtins.h"
#include "utils/float.h"
#include "utils/lsyscache.h"
#include "vector.h"
#if PG_VERSION_NUM >= 120000
#include "common/shortest_dec.h"
#include "utils/float.h"
#else
#include <float.h>
#include "utils/builtins.h"
#endif
typedef struct SparseInputElement
{
int32 index;

View File

@@ -1,4 +1,4 @@
comment = 'vector data type and ivfflat and hnsw access methods'
default_version = '0.7.4'
default_version = '0.8.0'
module_pathname = '$libdir/vector'
relocatable = true