 Andrew Kane
|
6f3c587df0
|
Improved copy test [skip ci]
|
2024-04-25 15:39:47 -07:00 |
|
|
Andrew Kane
|
b4483245b6
|
Condensed regression tests [skip ci]
|
2024-04-25 15:35:36 -07:00 |
|
|
Andrew Kane
|
f79e34532a
|
Condensed regression tests [skip ci]
|
2024-04-25 15:30:38 -07:00 |
|
|
Andrew Kane
|
8f728038b3
|
Increased max sparsevec dimensions to 1B [skip ci]
|
2024-04-24 11:17:25 -07:00 |
|
|
Andrew Kane
|
3bf18af035
|
Improved error messages for sparsevec input
|
2024-04-24 11:12:28 -07:00 |
|
|
Andrew Kane
|
312b0c258e
|
Improved tests for sparsevec input [skip ci]
|
2024-04-24 09:58:27 -07:00 |
|
|
Andrew Kane
|
96e08e1b6d
|
Switched to strtoint for sparsevec input
|
2024-04-24 09:56:09 -07:00 |
|
|
Andrew Kane
|
540bdf784e
|
Added more tests for subvector function [skip ci]
|
2024-04-24 01:31:50 -07:00 |
|
|
Andrew Kane
|
745b5f0264
|
Added more tests for subvector function [skip ci]
|
2024-04-24 01:28:25 -07:00 |
|
|
Heikki LinnakangasandGitHub
|
e452e0afc7
|
Fix integer overflow in subvector() function (#530)
`end = start + count` can overflow if `start` is very large. That
leads to a segfault later in the function. Add test case for it.
|
2024-04-24 01:20:16 -07:00 |
|
|
Andrew Kane
|
2ea421470e
|
Improved test [skip ci]
|
2024-04-23 20:42:30 -07:00 |
|
|
Andrew Kane
|
9474a82f9b
|
Improved test [skip ci]
|
2024-04-23 20:41:11 -07:00 |
|
|
Andrew Kane
|
61e7566ec7
|
Improved tests for l2_norm [skip ci]
|
2024-04-23 20:38:22 -07:00 |
|
|
Andrew Kane
|
bf87c5607c
|
Improved tests for sparsevec distance functions [skip ci]
|
2024-04-23 20:29:04 -07:00 |
|
|
Andrew Kane
|
939bcbe0ca
|
Increased max sparsevec dimensions to 1M [skip ci]
|
2024-04-23 17:47:11 -07:00 |
|
|
Andrew Kane
|
8d903b6858
|
Added more tests for vector distance functions [skip ci]
|
2024-04-22 15:53:13 -07:00 |
|
|
Andrew Kane
|
dc47a83d80
|
Improved tests for halfvec l1_distance [skip ci]
|
2024-04-22 14:43:54 -07:00 |
|
|
Andrew Kane
|
d8fc05d709
|
Removed support for L1 distance and Jaccard distance from ivfflat due to non-optimal clustering
|
2024-04-22 14:11:29 -07:00 |
|
|
Andrew Kane
|
2cbe3999c5
|
Added support for indexing sparsevec with L1 distance [skip ci]
|
2024-04-22 13:08:12 -07:00 |
|
|
Andrew Kane
|
d94609e606
|
Added support for indexing halfvec with L1 distance [skip ci]
|
2024-04-22 13:00:59 -07:00 |
|
|
Andrew Kane
|
ded794aaa7
|
Updated test name [skip ci]
|
2024-04-22 12:57:01 -07:00 |
|
|
Andrew Kane
|
3f607ae1e3
|
Updated test name [skip ci]
|
2024-04-22 12:48:22 -07:00 |
|
|
Andrew Kane
|
e6ee034e7b
|
Added support for indexing L1 distance
|
2024-04-22 12:44:03 -07:00 |
|
|
Andrew Kane
|
e37c97a7e8
|
Added more tests for sparsevec to halfvec cast [skip ci]
|
2024-04-19 18:05:03 -07:00 |
|
|
Andrew Kane
|
3d4543b696
|
Added casts between halfvec and sparsevec
|
2024-04-19 18:03:07 -07:00 |
|
|
Andrew Kane
|
4eae97e99f
|
Updated sparsevec input to support indices in any order [skip ci]
|
2024-04-19 16:54:19 -07:00 |
|
|
|
337922a6b5
|
Improved performance of bit distance functions - #519
Co-authored-by: Nathan Bossart <[email protected]>
Co-authored-by: "Jonathan S. Katz" <[email protected]>
|
2024-04-18 13:45:00 -07:00 |
|
|
Andrew Kane
|
6cfa836afb
|
Skip duplicate center check for bit [skip ci]
|
2024-04-16 17:20:48 -07:00 |
|
|
Andrew Kane
|
e687b83138
|
Added support for bit to IVFFlat
|
2024-04-16 17:12:27 -07:00 |
|
|
Andrew Kane
|
3e6ff096a6
|
Improved l2_normalize test for sparsevec [skip ci]
|
2024-04-15 14:59:11 -07:00 |
|
|
Andrew Kane
|
a26c369a7d
|
Updated l2_normalize to remove zeros for sparsevec
|
2024-04-15 14:42:53 -07:00 |
|
|
Andrew Kane
|
6c8d095462
|
Added todo [skip ci]
|
2024-04-15 14:11:17 -07:00 |
|
|
Andrew Kane
|
4002dbc9d2
|
Added l2_normalize function for sparsevec
|
2024-04-15 14:05:18 -07:00 |
|
|
Andrew Kane
|
ef410c8b25
|
Improved cosine distance tests for halfvec [skip ci]
|
2024-04-15 10:51:52 -07:00 |
|
|
Andrew Kane
|
417b89a7c8
|
Added tests for operators [skip ci]
|
2024-04-15 01:04:16 -07:00 |
|
|
Andrew Kane
|
827dd206f7
|
Improved sparsevec test [skip ci]
|
2024-04-15 00:58:47 -07:00 |
|
|
Andrew Kane
|
2bf0225801
|
Improved sparsevec tests [skip ci]
|
2024-04-15 00:57:53 -07:00 |
|
|
Andrew Kane
|
df78fb4249
|
Improved sparsevec tests [skip ci]
|
2024-04-15 00:55:52 -07:00 |
|
|
Andrew Kane
|
2d3f9d2510
|
Improved tests [skip ci]
|
2024-04-15 00:53:44 -07:00 |
|
|
Andrew Kane
|
67f57e3106
|
Improved tests [skip ci]
|
2024-04-15 00:46:19 -07:00 |
|
|
Andrew Kane
|
196396aaaf
|
Improved tests [skip ci]
|
2024-04-15 00:41:30 -07:00 |
|
|
Andrew Kane
|
44c7c72870
|
Improved tests for l1_distance [skip ci]
|
2024-04-15 00:37:38 -07:00 |
|
|
Andrew Kane
|
b735367c10
|
Simplified concat tests [skip ci]
|
2024-04-14 23:18:07 -07:00 |
|
|
Andrew Kane
|
bb07148238
|
Added concatenate operator for vectors
|
2024-04-14 23:12:07 -07:00 |
|
|
Andrew Kane
|
f04d52558a
|
Added l1_distance function for sparsevec [skip ci]
|
2024-04-14 22:59:28 -07:00 |
|
|
Andrew Kane
|
a89b1382c5
|
Added l2_normalize function - closes #220
|
2024-04-14 20:53:05 -07:00 |
|
|
Andrew Kane
|
b58f3cf181
|
Renamed quantize_binary to binary_quantize
|
2024-04-14 16:57:28 -07:00 |
|
|
Andrew Kane
|
ddac9fe707
|
Renamed halfvec_dims to vector_dims [skip ci]
|
2024-04-14 16:40:16 -07:00 |
|
|
Andrew Kane
|
8c56025a7f
|
Renamed functions to l2_norm [skip ci]
|
2024-04-14 16:29:27 -07:00 |
|
|
Andrew Kane
|
5e9feda80e
|
Added sum for half vectors
|
2024-04-14 15:16:17 -07:00 |
|