Andrew Kane
fc804925a4
Added todo [skip ci]
2026-06-16 12:33:25 -07:00
Andrew Kane
98dc4aa6d0
Added pass to confirm graph was repaired for HNSW vacuuming
2026-06-16 10:51:54 -07:00
Andrew Kane
7b72aeeff3
Added check for deleted element [skip ci]
2026-06-16 10:13:40 -07:00
Andrew Kane
4682d51e5d
Added memory usage for HNSW vacuuming [skip ci]
2026-06-16 10:10:13 -07:00
Andrew Kane
91fe2e62e7
Added benchmarking for HNSW vacuuming [skip ci]
2026-06-16 09:53:47 -07:00
Andrew Kane
eedba7ee14
Fixed possible index corruption with HNSW vacuuming - resolves #988
...
Co-authored-by: Bhagyesh Chaturvedi <bhagyeshc@google.com >
2026-06-16 09:44:34 -07:00
Andrew Kane
2b7ad083dc
Always use inline pg_popcount64 for Postgres 19+ - #985
2026-06-10 20:08:03 -07:00
Andrew Kane
421a35fcdc
Fixed performance regression with Hamming distance and Jaccard distance with Postgres 18 - fixes #985
2026-06-10 19:55:21 -07:00
Andrew Kane
88a0085459
Improved casting [skip ci]
2026-05-26 14:09:19 -07:00
Andrew Kane
ea23884efd
Ran latest pgindent [skip ci]
2026-05-26 13:39:55 -07:00
Andrew Kane
3351f3d43e
Simplified comment [skip ci]
2026-05-26 13:39:20 -07:00
Zhang Jinrui
529f37175b
Fix CREATE INDEX CONCURRENTLY crash on ivfflat with assertion-enabled PostgreSQL by passing anyvisible=false in ivfflat SampleRows
2026-04-27 10:15:32 +00:00
Andrew Kane
a7551a61ca
Updated style [skip ci]
2026-04-14 16:21:32 -07:00
lychen0613
5c9a97af3b
optimize: defer sample normalization when building ivfflat
2026-04-14 16:14:17 -07:00
Andrew Kane
8af675cd25
Added comment [skip ci]
2026-04-14 16:10:45 -07:00
Andrew Kane
97e0ed4464
Fixed compilation errors with Postgres 19
2026-04-14 15:46:10 -07:00
Andrew Kane
533ad160e0
Fixed CI
2026-04-14 13:51:04 -07:00
Andrew Kane
dfbd724a1f
Changed rowstoskip to double to match reservoir_get_next_S
2026-04-14 13:38:20 -07:00
lychen0613
5f270c9663
Add benchmark for ivfflat sample rows
2026-04-14 21:56:10 +08:00
lychen0613
352ec5be29
fix: correctly use reservoir_get_next_S when building ivfflat
2026-04-14 17:57:40 +08:00
Andrew Kane
17916cad00
Improved includes [skip ci]
2026-02-25 17:35:23 -08:00
Andrew Kane
284f2f0fec
Improved casting for HNSW scan memory limit [skip ci]
2026-02-25 12:59:17 -08:00
Andrew Kane
edd49863ba
Improved limit for HNSW scan memory
2026-02-25 12:52:29 -08:00
Andrew Kane
cab9da72c0
Version bump to 0.8.2 [skip ci]
2026-02-25 10:46:57 -08:00
Andrew Kane
9ed39fb94b
Hardened shared memory allocator
...
Co-authored-by: chungkn from OneMount Group <kimngocchung.k2a@gmail.com >
2026-02-25 10:39:01 -08:00
Andrew Kane
b7e680d41a
Fixed integer wraparound leading to buffer overflow with parallel HNSW index build
...
Reported-by: chungkn from OneMount Group <kimngocchung.k2a@gmail.com >
2026-02-25 10:35:14 -08:00
Andrew Kane
35ab919bf5
Switched to statically-allocated IndexAmRoutine for Postgres 19 [skip ci]
2026-01-21 16:40:35 -08:00
Andrew Kane
aca89aec73
Switched to scanner_isspace for Postgres 17+ - resolves #942
2026-01-05 12:54:04 -08:00
Andrew Kane
3d6dd20469
Removed unneeded check
2025-12-11 16:28:45 -08:00
Andrew Kane
c711da411c
Improved includes for indexes
2025-12-11 15:35:37 -08:00
Andrew Kane
3975e212cc
Improved includes for ivfkmeans [skip ci]
2025-12-11 13:26:36 -08:00
Andrew Kane
2b741ef068
Improved includes for types
2025-12-11 00:35:18 -08:00
Andrew Kane
f85a7d3fd0
Keep clang-tidy happy [skip ci]
2025-12-10 20:03:26 -08:00
Andrew Kane
5c25f81789
Fixed inconsistent parameter names [skip ci]
2025-12-10 18:49:00 -08:00
Andrew Kane
d72ee71f23
Fixed compilation errors with Postgres 19
2025-12-10 14:59:29 -08:00
Andrew Kane
3ebb9a506e
Added varatt headers for Postgres 16+
2025-10-22 11:56:05 -07:00
Andrew Kane
727d4836d2
Fixed Index Searches in EXPLAIN output for Postgres 18
2025-10-22 11:47:11 -07:00
Andrew Kane
d823c44591
Removed unused parameter [skip ci]
2025-09-27 15:58:18 -07:00
Andrew Kane
8f4aa0751c
Removed unused parameters [skip ci]
2025-09-27 15:51:32 -07:00
Andrew Kane
778dacf20c
Version bump to 0.8.1 [skip ci]
2025-09-04 17:51:09 -07:00
Andrew Kane
3f687687ee
Fixed compilation error with Postgres 19
2025-09-04 15:58:23 -07:00
Julien Rouhaud
dd3a1e9137
Use NIL for empty lists ( #890 )
...
Postgres standard way to check for list emptiness is to compare a pointer to
NIL rather than NULL.
2025-08-23 03:31:22 -07:00
Andrew Kane
ea4746f6c0
Updated comment [skip ci]
2025-08-19 14:26:36 -07:00
Andrew Kane
6aec80ccdb
Improved performance of binary_quantize function for halfvec
2025-08-19 13:47:11 -07:00
Luca Giacchino
0c9070ba82
Add autovectorized implementation of binary quantize
2025-08-19 13:18:50 -07:00
Andrew Kane
30382418da
Ran pgindent [skip ci]
2025-08-19 12:44:54 -07:00
Andrew Kane
e29fc3aa1a
Switched to PG_MODULE_MAGIC_EXT for Postgres 18+ [skip ci]
2025-07-31 19:59:27 -07:00
Andrew Kane
5b8b68ba1d
Use consistent style [skip ci]
2025-07-27 18:19:28 -07:00
Andrew Kane
e6bad96a03
Ran pgindent [skip ci]
2025-06-18 20:07:46 -07:00
Jon Daniel
3a49d141b3
Vectorizing vector_concat for improved performance ( #861 )
...
* Vectorizing vector_concat for improved performance
On an ARM chip this should generate SIMD instructions to copy the two
incoming vectors to the new vector as opposed to doing it all in
software.
* Moving declarations to above CheckDim
* Removing const from dims
* Formatting
2025-06-18 20:06:32 -07:00