yadda yadda yadda

@baelamri-ankorstore I have a couple of questions to triage the issue: * is Metarank running in Docker or as a regular app? * Can you post a longer log snippet...

@baelamri-ankorstore I guess I may know what's going on. In 0.5.15 when running on kubernetes, the pod manifest lacks two important things related to memory usage: * there was no...

Can you please describe the use-case for PyTorch? We do have plans regarding Python in general for a foreseeable future: - API bindings for Python (#641 ) - Wrap sasrec/bert4rec...

I guess the easiest way would be to copy-paste the most optimal params you've got after the optuna into the lightgbm model settings in metarank's config file and retrain. See...

Hi there. Yes, there is such a plan, but probably somewhere in June. This library is a part of the ltrlib project, which is part of metarank project, and we're...

Hi @jornd13, kudos for the complete hs_err log! There are some strange things I observe there: * we have a CI with matrix tests to validate that the library works...

The main problem is that we don't build the win64 binaries for the `lightgbm.dll` by ourselves, but just bundle the ones made by upstream LightGBM project. For me it seems...

Can you please make a clean reproducer for the issue? * it can be shared in public - so I can reproduce the issue locally. As for now you're the...

@jornd13 * the JVM crash with use-after-close is fixed in https://github.com/metarank/lightgbm4j/pull/82 * there's also a fix https://github.com/metarank/lightgbm4j/pull/86 which may affect yours ACCESS_VIOLATION issue - there might be stale `lib_lightgbm_swig.dll` living...

AFAIK you need to pass the `categorical_feature` parameter prior to creating the booster. See this example: https://github.com/metarank/ltrlib/blob/02cec0419ccc83a85837d1235d89ebdf385b274c/src/main/scala/io/github/metarank/ltrlib/booster/LightGBMBooster.scala#L57