hanzoai/sql-vector
2
0
Fork 0
mirror of https://github.com/hanzoai/sql-vector.git synced 2026-10-01 00:37:19 +00:00
Code Issues Packages Projects Releases Wiki Activity
845 Commits 2 Branches 38 Tags
27bf515a46d143dbb198e415f096fdbfa957affe
Commit Graph
845 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Andrew Kane 27bf515a46 Improved memory calculation for HNSW and removed vector-specific code 2023-11-09 16:21:26 -08:00
Andrew Kane 26f70608ce Updated comment [skip ci] 2023-11-05 08:42:06 -08:00
Andrew Kane 4fcb9fb9ae Updated comment [skip ci] 2023-11-05 08:40:21 -08:00
Andrew Kane f2728630c7 Improved variable name [skip ci] 2023-11-05 08:35:54 -08:00
Andrew Kane 0c72af59ec Added note about check constraint [skip ci] 2023-11-04 15:01:37 -07:00
Andrew Kane 9e5b6b6128 Improved header installation on Windows 2023-11-04 11:16:40 -07:00
Andrew Kane 7b9f5865e0 Updated example [skip ci] 2023-11-03 23:54:50 -07:00
Andrew Kane bd80f1aebe Updated readme [skip ci] 2023-11-03 23:46:23 -07:00
Andrew Kane 0ef30bd4e5 Updated readme [skip ci] 2023-11-03 23:43:47 -07:00
Andrew Kane ee9e9d7295 Added info on storing vectors with more precision [skip ci] 2023-11-03 20:14:28 -07:00
Andrew Kane a8e64de6a8 Updated readme [skip ci] 2023-11-03 17:02:30 -07:00
Andrew Kane 12dd1eefda Updated readme [skip ci] 2023-11-03 16:48:57 -07:00
Andrew Kane 3ade190558 Improved docs on indexing vectors with different dimensions [skip ci] 2023-11-03 16:42:14 -07:00
Andrew Kane c3f2edd072 Improved upgrading docs - #339 [skip ci] 2023-11-03 16:15:06 -07:00
Andrew Kane 1610d7cadd Added info on columns with different dimensions [skip ci] 2023-11-03 16:02:00 -07:00
Andrew Kane dec1af23e1 Free remaining allocation from deconstruct_array - #332 2023-11-02 21:20:21 -07:00
Andrew Kane da19d6922a Removed unneeded allocation 2023-11-02 21:16:06 -07:00
Andrew Kane 0a3c7a8269 Added link to setup-pgvector [skip ci] 2023-11-02 13:22:19 -07:00
Andrew Kane 47bdbe5a37 Added Reciprocal Rank Fusion example to readme [skip ci] 2023-11-01 13:20:49 -07:00
Andrew Kane 16de069bd3 Added Nim and Zig to readme [skip ci] 2023-10-31 02:26:18 -07:00
Andrew Kane ccd1d97e4e Updated column alias [skip ci] 2023-10-29 16:47:55 -07:00
Andrew Kane 3914b7a084 Improved indexing progress queries [skip ci] 2023-10-29 16:41:39 -07:00
Andrew Kane aedce6e0ec Improved docs for indexing progress - closes #320 and closes #321 [skip ci] 2023-10-29 16:13:12 -07:00
Andrew Kane d944d06957 Added TypeScript to readme [skip ci] 2023-10-29 12:49:01 -07:00
Andrew Kane 87f44b94a9 Added Groovy to readme [skip ci] 2023-10-29 12:39:53 -07:00
Andrew Kane ba7b373efe Updated readme [skip ci] 2023-10-27 13:22:37 -07:00
Andrew Kane c6fd558ddd Added Kotlin to readme [skip ci] 2023-10-26 12:25:58 -07:00
Andrew Kane 7eb5178e9f Added link to pgvector-c [skip ci] 2023-10-26 00:30:06 -07:00
Andrew Kane b59209f307 Added Postgres 17 to CI [skip ci] 2023-10-19 00:37:24 -07:00
Andrew Kane e4d03ef83d Updated checkout action [skip ci] 2023-10-19 00:36:53 -07:00
Andrew Kane b1557499d3 Version bump to 0.5.1 [skip ci] v0.5.1 2023-10-10 17:40:57 -07:00
Andrew Kane 8937fba8d3 Added check for MVCC-compliant snapshot and removed marking tuples as dead for IVFFlat index scans - closes #260 2023-10-10 17:28:48 -07:00
Andrew Kane 4d3fc68e6d Disable closer caching for new elements for now 2023-10-06 14:27:09 -07:00
Andrew Kane d747cbce01 Updated comment [skip ci] 2023-10-06 14:07:35 -07:00
Andrew Kane 904b8a7c7a Updated comment [skip ci] 2023-10-06 13:58:07 -07:00
Andrew Kane 67ec717918 Added comment [skip ci] 2023-10-06 13:56:25 -07:00
Andrew Kane 95cd12742f Improved variable name [skip ci] 2023-10-06 13:46:19 -07:00
Andrew Kane 7e9f1e9011 Improved closerSet logic 2023-10-06 13:39:55 -07:00
Andrew Kane 7dfa2f42f8 Moved sorting logic into SelectNeighbors 2023-10-06 12:56:15 -07:00
Andrew Kane d2abb64a10 Ensure order is deterministic for SelectNeighbors closer caching 2023-10-06 12:26:53 -07:00
Andrew Kane 422c9f0d6f Use e for consistency 2023-10-05 16:15:13 -07:00
Heikki LinnakangasandGitHub 1cd151e1de Improve HNSW index build performance more (#295) 
This takes the approach from commit d1c2265c57 further. Once we have
remove a candidate from the "closer" set, we still don't need to
recalculate everything that follows. Any candidates that were in the
closer set before still only need to be compared with any new
candidates that we have added.
 2023-10-05 16:04:50 -07:00
Andrew KaneandHeikki Linnakangas d1c2265c57 Improved performance of HNSW index builds - closes #292 
Co-authored-by: Heikki Linnakangas <[email protected]>
 2023-10-05 13:21:26 -07:00
Andrew Kane cbc9489af0 DRY max size 2023-10-04 21:43:34 -07:00
Andrew Kane cfa3e0c572 Use BLCKSZ for consistency 2023-10-04 21:37:55 -07:00
Xiaoran WangandGitHub 728c5cf5dd Include ItemIdData when computing the maxSize for the data in a page (#274) 
As the data is aligned, for hnsw, the combined size won't be in the range
(8156 (maxSize exlucding `ItemIdData`), 8160]. So even if the
ItemIdData is not included in the maxSize, it works well now, but I
think it's better to make it correct.
 2023-10-04 21:26:46 -07:00
Andrew Kane 84f0726f58 Added check for MVCC-compliant snapshot for HNSW index scans - closes #281 2023-10-04 20:14:50 -07:00
Andrew Kane caf0a8ebfe Revert "Fixed locking for index scans for HNSW - #256" 
This reverts commit e87e70ff72.
 2023-09-26 23:00:14 -07:00
jeff-davisandGitHub 94d24ff718 No need to MarkBufferDirty(); GenericXLogFinish() does that. (#265) 2023-09-15 13:14:10 -07:00
Andrew Kane c621e18a8a Updated order [skip ci] 2023-09-12 19:53:12 -07:00