43 Commits
Author SHA1 Message Date
Morgan Carr 69ede9ec3e Fall back to root tokenizers for ONNX and LiteRT Hub subdirectory models (#1277) 2026-09-30 07:41:03 -04:00
Morgan Carr 6ebfbbb716 Improve late pooling configuration errors (#1217) 2026-09-03 13:52:46 -04:00
serhiizghama 5ade7881c8 test: cover spool file cleanup for sparse vectors 2026-09-03 20:19:31 +07:00
Joe Bergin 007d61077a Add ONNX vectors backend (#1212) 2026-09-02 12:19:57 -04:00
Amir Fathi 57991cb164 Fix WordVectors.index() silently dropping the checkpoint argument (#1198) 2026-08-24 20:38:28 -04:00
davidmezzetti d8ae6776f8 Only resolve transform functions when env variable set, closes #1155 2026-07-21 11:07:58 -04:00
davidmezzetti 638a2e12b1 Validate resolver target classes, closes #1153 2026-07-21 09:13:43 -04:00
davidmezzetti 8844ec96b4 Update test 2026-05-19 15:13:15 -04:00
davidmezzetti 9d5f82e824 Add support for LiteRT vectors, closes #1097 2026-05-19 14:30:04 -04:00
davidmezzetti b14229c1da Make transformers package optional for minimal install, closes #1091 2026-05-05 15:27:44 -04:00
davidmezzetti f013ca7d1d Workaround macOS test failure 2026-02-10 13:12:37 -05:00
davidmezzetti b53c966fa7 Change sparse vector normalization logic, closes #946 2025-08-05 18:26:49 -04:00
davidmezzetti e765be3f6c Refactor of ann and vectors packages for sparse vectors. Closes #930. Closes #934. Closes #935. Closes #936. Closes #937. 2025-07-14 07:48:23 -04:00
davidmezzetti 408a053001 Fix test that was using a method deprecated in Python 3.10 2025-04-08 12:04:06 -04:00
davidmezzetti a1a7d34cd8 Embeddings index checkpointing, closes #695 2025-02-19 16:44:37 -05:00
davidmezzetti f52ce51413 Word vector model improvements, closes #868 2025-02-05 13:23:01 -05:00
davidmezzetti 986da4700a Check for multiple exception types #859 2025-01-27 12:34:28 -05:00
davidmezzetti f79d8062ae Replace fasttext and pymagnitude with staticvectors. Closes #857. Closes #858. Closes #859 2025-01-27 11:17:51 -05:00
davidmezzetti 65a8316de5 Vector encoding using multiple-GPUs, closes #541 2024-12-21 20:30:55 -05:00
davidmezzetti 5fdbc90d24 Autodetect Model2Vec model paths, closes #822. Refactor vectors package, closes #826. 2024-12-01 08:27:09 -05:00
davidmezzetti a246052f4a Add model2vec vectorization, closes #801 2024-10-21 13:53:11 -04:00
davidmezzetti 61bf4879d5 Modify vector transforms to load/save data using np.load/np.save, closes #777 2024-08-24 07:36:07 -04:00
davidmezzetti 3422e0fbb1 Add additional vector backends. Closes #725. Closes #726. Closes #727 2024-05-28 08:26:29 -04:00
davidmezzetti 88430d7824 Add support for dynamic vector dimensions, pass options to underlying vector models and move vector model caching. Closes #674. Closes #675. Closes #678 2024-02-27 21:20:51 -05:00
davidmezzetti 168f7e4efd Change default embeddings config to json, closes #652, Store index ids outside of config when content is disabled, closes #653. 2024-01-30 17:12:33 -05:00
davidmezzetti 0f35409219 Add scalar quantization support to vectors, closes #583 2023-10-27 15:01:40 -04:00
davidmezzetti 5aeefc3ab8 Update tests 2023-02-19 13:49:13 -05:00
davidmezzetti edda6b65e8 Improve batchtransform performance, closes #396, closes #399 2022-12-12 11:53:40 -05:00
davidmezzetti 332b232349 Embeddings vector batch improvements, closes #309 2022-07-21 15:48:28 -04:00
davidmezzetti 1a8a8f1ca4 Add logic to detect external vectors method, closes #277 2022-05-12 12:31:17 -04:00
davidmezzetti b8c29666de Refactor vectors package to improve code reuse, closes #276 2022-05-11 07:18:49 -04:00
davidmezzetti a86e161d9b Fix word embeddings regression with batch transformation, closes #245 2022-03-11 15:05:41 -05:00
davidmezzetti 0bf536a604 Update tests 2022-01-28 17:24:57 -05:00
davidmezzetti b8cc67670d Makefile update to debug GitHub action issues 2022-01-28 15:48:45 -05:00
davidmezzetti 0b53138c76 Revert unnecessary test changes 2022-01-28 11:52:30 -05:00
davidmezzetti eda1cabcdc Pin fasteners version in build workflow to workaround deadlocking issue for word vector unit tests 2022-01-28 11:26:53 -05:00
davidmezzetti 3ac6a5b332 Skip word vector embeddings test on macOS 2022-01-28 07:23:43 -05:00
davidmezzetti 13d620ebd6 Reduce number of vector process indexers for unit test 2022-01-27 19:04:49 -05:00
davidmezzetti d646ca70c8 Reduce number of vector process indexers for unit test 2022-01-27 18:51:13 -05:00
davidmezzetti d21d00acc5 Update tests to improve memory cleanup 2022-01-27 17:09:11 -05:00
davidmezzetti 1e65a3b75e Add pre-computed vector support, closes #192 2021-12-28 18:16:58 -05:00
davidmezzetti 1b5a180221 Improve efficiency of vector transformations, closes #191 2021-12-28 18:16:10 -05:00
davidmezzetti b14d8769dd Update test method docs for consistency 2021-12-22 06:44:49 -05:00