Commit message (Expand) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Replace optimaize with OpenNLP language detector | Jon Marius Venstad | 2021-12-17 | 7 | -166/+102 |
* | Add a BERT embedder | Jon Bratseth | 2021-12-16 | 1 | -2/+3 |
* | Time out requests after 200s | Jon Marius Venstad | 2021-12-13 | 1 | -1/+0 |
* | Update 2020 Oath copyrights. | gjoranv | 2021-10-27 | 2 | -2/+2 |
* | Update Verizon Media copyright notices. | gjoranv | 2021-10-07 | 3 | -3/+3 |
* | Update 2018 copyright notices. | gjoranv | 2021-10-07 | 3 | -3/+3 |
* | Update 2017 copyright notices. | gjoranv | 2021-10-07 | 69 | -69/+69 |
* | Encapsulate in a context | Jon Bratseth | 2021-10-01 | 1 | -12/+46 |
* | Pass destination | Jon Bratseth | 2021-09-30 | 1 | -4/+10 |
* | encode -> embed | Jon Bratseth | 2021-09-28 | 2 | -56/+56 |
* | Separate component from linguistics | Jon Bratseth | 2021-09-25 | 15 | -1015/+0 |
* | Linguistics cleanup | Jon Bratseth | 2021-09-21 | 17 | -34/+29 |
* | Add 'encode' expression | Jon Bratseth | 2021-09-19 | 1 | -0/+17 |
* | Provide a (non-working) encoder by default | Jon Bratseth | 2021-09-17 | 1 | -1/+1 |
* | Cleanup | Jon Bratseth | 2021-09-17 | 5 | -9/+2 |
* | Refactor to separate classes | Jon Bratseth | 2021-09-17 | 8 | -203/+279 |
* | Encoder interface | Jon Bratseth | 2021-09-16 | 3 | -4/+55 |
* | Encode to sparse tensor | Jon Bratseth | 2021-09-16 | 2 | -0/+16 |
* | Encode to dense tensor | Jon Bratseth | 2021-09-16 | 3 | -4/+36 |
* | Use a result builder | Jon Bratseth | 2021-09-16 | 1 | -21/+53 |
* | Make SentencePieceEncoder configurable | Jon Bratseth | 2021-09-16 | 5 | -36/+150 |
* | Merge pull request #19130 from vespa-engine/bratseth/sp-export | Jo Kristian Bergum | 2021-09-14 | 1 | -0/+7 |
|\ | |||||
| * | Make public | Jon Bratseth | 2021-09-14 | 1 | -0/+7 |
* | | Merge pull request #19131 from vespa-engine/bratseth/sp-simplify | Jon Bratseth | 2021-09-14 | 1 | -13/+7 |
|\ \ | |||||
| * | | Slight algorithm simplification | Jon Bratseth | 2021-09-14 | 1 | -6/+4 |
| * | | Slight algorithm simplification | Jon Bratseth | 2021-09-14 | 1 | -6/+3 |
| * | | Slight algorithm simplification | Jon Bratseth | 2021-09-14 | 1 | -11/+10 |
| |/ | |||||
* / | More unit tests | Jon Bratseth | 2021-09-14 | 1 | -1/+20 |
|/ | |||||
* | Pure Java sentencepiece implementation | Jon Bratseth | 2021-09-13 | 6 | -2/+723 |
* | we want to compare Linguistics objects for equivalence | Arne Juul | 2021-08-04 | 3 | -0/+7 |
* | Require replacements to be applied during tokenization | Jon Bratseth | 2021-06-15 | 3 | -12/+11 |
* | Revert "Merge pull request #17754 from vespa-engine/revert-17747-bratseth/spe... | Jon Bratseth | 2021-05-05 | 7 | -13/+285 |
* | Revert "Reapply "Bratseth/special tokens"" | Jon Bratseth | 2021-05-05 | 7 | -285/+13 |
* | Revert "Merge pull request #17746 from vespa-engine/revert-17738-revert-17737... | Jon Bratseth | 2021-05-05 | 7 | -13/+285 |
* | Revert "Revert "Revert "Bratseth/special tokens""" | Jon Bratseth | 2021-05-05 | 7 | -285/+13 |
* | Revert "Revert "Bratseth/special tokens"" | Jon Bratseth | 2021-05-04 | 7 | -13/+285 |
* | Revert "Bratseth/special tokens" | Jon Bratseth | 2021-05-04 | 7 | -285/+13 |
* | Avoid config in simple tokenizer | Jon Bratseth | 2021-05-04 | 1 | -7/+4 |
* | Expose tokens as map | Jon Bratseth | 2021-05-04 | 3 | -11/+16 |
* | Wire in (but don't use) SpecialTokens | Jon Bratseth | 2021-05-04 | 6 | -18/+40 |
* | Move specialtokens to linguistics | Jon Bratseth | 2021-05-04 | 3 | -0/+248 |
* | No functional changes | Jon Bratseth | 2021-04-14 | 1 | -37/+26 |
* | No functional changes | Jon Bratseth | 2021-04-14 | 13 | -128/+84 |
* | No functional changes | Jon Bratseth | 2021-02-03 | 2 | -1/+20 |
* | Add a test | Jon Bratseth | 2020-11-12 | 1 | -3/+0 |
* | Use full name in config definition file names | Harald Musum | 2020-09-10 | 1 | -0/+0 |
* | handle plugin tokenizer returning tokens with empty original string | Arne Juul | 2020-08-24 | 2 | -1/+55 |
* | Minor unification of tests. | Henning Baldersheim | 2020-08-12 | 2 | -20/+36 |
* | Surrogate aware gram splitting | Jon Bratseth | 2020-06-25 | 2 | -33/+122 |
* | SpareCapacityMaintainer sketch | Jon Bratseth | 2020-06-12 | 6 | -66/+35 |