From 3c184aed816326d412bf37406a59e54b19f1edaa Mon Sep 17 00:00:00 2001 From: Parham Alvani Date: Sat, 13 Apr 2024 18:59:08 +0000 Subject: [PATCH] feat: update slides --- slides.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/slides.md b/slides.md index e33ce95..9f7e222 100644 --- a/slides.md +++ b/slides.md @@ -187,3 +187,13 @@ The null hypothesis in this test is that the distributions are the same. If this hypothesis is rejected, it suggests that there is a drift in the model. The K-S test is a useful tool for comparing datasets and determining whether they come from the same distribution. + +--- + +## Drift Detection in Seldon Core + +The general framework shown is to use the Seldon Core payload logger to pass requests to components that +process them asynchronously. The results can be passed onwards to alerting systems. + +Logging of request and response payloads from your Seldon Deployment can be accomplished by adding a _logging section_ +to any part of the Seldon deployment graph.