567 Commits

Author SHA1 Message Date
Amir Fathi 57991cb164 Fix WordVectors.index() silently dropping the checkpoint argument (#1198) 2026-08-24 20:38:28 -04:00
serhiizghama 406e417be0 test(ann): cover deleted-row exclusion for quantized numpy backend 2026-08-24 17:18:26 +07:00
morgan-coded b94f770301 Resolve LEMUR and MUVERA settings 2026-08-22 16:19:06 -05:00
Arnaud Thery adbcccda46 Merge pull request #1195 from St4r4x/fix/crossencoder-multiclass-labels
fix: rank CrossEncoder by a fixed label, not top-1 position
2026-08-22 14:15:21 -04:00
morgan-coded ee0416e87b Add centermean validation test 2026-08-18 20:22:07 -05:00
morgan-coded 00ec81a10e Fix LEMUR collection centering 2026-08-18 10:54:10 -05:00
davidmezzetti 47c05994bf Cleanup of Pooling PRs 2026-08-18 09:53:29 -04:00
Kole Harvey 8f3735101b Resolve pooling method from a config missing pooling_mode_mean_tokens 2026-08-18 09:14:20 -04:00
Aryan Pardeshi 438ade31b6 Add max pooling 2026-08-18 09:12:32 -04:00
davidmezzetti 3ea197468d Code cleanup 2026-08-12 09:35:13 -04:00
LHMQ878 99ebbdfea2 fix: create default agent tools on first use (#1175) 2026-08-12 07:30:37 -04:00
FU-max-boop 01b456900a Fix OpenAI chat message selection 2026-08-11 13:26:29 +08:00
davidmezzetti f35d932979 Refactor late encoding logic to cleanup logic paths, closes #1180 2026-08-10 18:47:58 -04:00
Tai An a1c9b94d00 fix(muvera): consume true token rows instead of batch-padded ones (#1177) 2026-08-10 13:24:21 -04:00
Aryan Pardeshi 11ebacdb23 Convert MUVERA algorithm from NumPy to Torch (#1178) 2026-08-10 13:20:58 -04:00
davidmezzetti 893a333887 Test Docling build fix #1176 2026-08-10 10:15:16 -04:00
davidmezzetti ea531b3420 Build script workaround #1176 2026-08-04 12:24:05 -04:00
davidmezzetti 756917f14b Build script workaround #1176 2026-08-04 12:20:17 -04:00
morgan-coded 193facd144 test: cover the tqdm library stub 2026-08-03 20:50:04 -05:00
morgan-coded 436662e32b feat: promote tqdm to a default library dependency 2026-08-03 14:32:12 -05:00
morgan-coded 54644a0526 chore: add lint pragma and docstring for relocated trainer tests 2026-08-02 18:11:54 -05:00
morgan-coded 987cff001f feat: consolidate LEMUR training in trainer
Move fitting, data preparation, model setup, epoch selection and progress feedback into LemurTrainer while keeping artifact loading and encoding in the pooler.
2026-08-02 16:55:32 -05:00
morgan-coded 0be1231d8d chore: align LEMUR names with txtai style 2026-08-02 14:21:38 -05:00
morgan-coded f4472312ba test: use portable tolerances for cross-batch comparisons 2026-08-02 06:47:56 -05:00
morgan-coded 90f7cc2078 test: isolate uncentered LEMUR coverage 2026-08-01 22:40:57 -05:00
morgan-coded ce11b08ab1 fix: address centering review feedback 2026-08-01 22:13:38 -05:00
morgan-coded 75b4ce5c7f feat: add configurable late pooling centering 2026-08-01 18:37:42 -05:00
David Mezzetti 2ef401bb78 Merge pull request #1164 from morgan-coded/feat/lemur
Add LEMUR fixed dimensional encoding
2026-08-01 17:35:07 -04:00
David Mezzetti 48e22b593c Merge pull request #1163 from AmirF194/fix/scoring-delete-unindexed-id
Fix Scoring.delete() crashing on ids that were never indexed
2026-07-30 14:48:11 -04:00
davidmezzetti 3beea7f4bf Add safeopen option for retrieve task, closes #1166 2026-07-30 14:36:52 -04:00
morgan-coded 626cc8fbe0 Add LEMUR validation coverage 2026-07-30 12:03:07 -05:00
Amir Fathi bd199158b6 Fix Scoring.delete() crashing on ids that were never indexed 2026-07-30 12:35:35 +00:00
morgan-coded feac4c8306 Test LEMUR pooling and training 2026-07-30 07:02:16 -05:00
davidmezzetti a910ddbbea Add Milvus tests on Windows #1156 2026-07-28 10:37:38 -04:00
davidmezzetti 7b49504dca Update test
build / build (macos-latest) (push) Has been cancelled
build / build (ubuntu-latest) (push) Has been cancelled
build / build (windows-latest) (push) Has been cancelled
docs / deploy (push) Has been cancelled
minimal / deploy (push) Has been cancelled
2026-07-23 11:54:09 -04:00
davidmezzetti 86af7ec344 Test updates 2026-07-23 10:10:28 -04:00
Amir Fathi 50ca7b2fde Fix HNSW search RuntimeError when limit exceeds indexed element count (#1159) 2026-07-23 08:42:33 -04:00
davidmezzetti a1224c06f1 Doc and test update
docs / deploy (push) Has been cancelled
build / build (macos-latest) (push) Has been cancelled
build / build (ubuntu-latest) (push) Has been cancelled
build / build (windows-latest) (push) Has been cancelled
minimal / deploy (push) Has been cancelled
2026-07-22 09:43:36 -04:00
davidmezzetti 1d084941f4 Code cleanup 2026-07-22 06:37:42 -04:00
Andrew Chen 597ba8133d Fix msgpack Accept header crashing streaming API endpoints (#1144) 2026-07-22 06:14:07 -04:00
Andrew Chen 6bbb25872a Fix Terms KeyError on a query with no similar() clause (#1142) 2026-07-22 06:13:33 -04:00
davidmezzetti f22bf5bbb5 Update test 2026-07-21 14:29:12 -04:00
davidmezzetti 2c6ec162d0 Skip Milvus tests on Windows #1156 2026-07-21 13:10:56 -04:00
davidmezzetti d59c88424d Code cleanup 2026-07-21 12:59:57 -04:00
David Mezzetti 95c7b8df1e Merge pull request #1149 from morgan-coded/milvus-lite-backend
Add milvus-lite embedded dense ANN backend
2026-07-21 12:41:05 -04:00
Loi Nguyen 2389b5946c Fix Segmentation dropping paragraph/section splits on CRLF line endings (#1152) 2026-07-21 12:29:12 -04:00
Andrew Chen b246b642c7 Fix LIMIT bind-parameter crashing content SQL search (#1148) 2026-07-21 12:26:15 -04:00
Andrew Chen 46467a3453 Raise SQLError on empty select expressions and a dangling AS (#1147) 2026-07-21 12:24:12 -04:00
davidmezzetti fcfd340ff1 Cleanup tests 2026-07-21 12:18:35 -04:00
Andrew Chen 77965f44dd Fix Cluster.shard TypeError on tuple documents and empty-string ids (#1146) 2026-07-21 11:57:57 -04:00