Clive Cox
Clive Cox
Hard to say. This looks supicious `OSError: [Errno 98[] Address already in use` is this happening on a crashLoopBackoff of the Pod? Or under high load?
Can you clarify the exact issue you are seeing so we can understand the issue better. Maybe with an example?
You can create custom metrics as outlined [here](https://docs.seldon.io/projects/seldon-core/en/latest/python/python_wrapping_docker.html#custom-metrics). Does this fulfil your requirements?
Is this related to https://github.com/SeldonIO/seldon-core/issues/4014 and https://github.com/SeldonIO/seldon-core/issues/4017
We use both knative serving and eventing its true for this demo. Can you provide a PR to update requirements?
Further work has not been started on this issue yet. A useful addition would be to clarify your use case for us @marcoramosh that is affected by this issue.
I can also verify this is an issue with a set of certificates rather than a single certificate defined in `ssl.ca.pem`
We have tied Dex into Auth for kfserving in our internal work. @ryandawsonuk can you comment?
You are free to place existing data anywhere the Kubernetes clusters can get access to. If you want this data to be usable by the existing Spark jobs then it...
The server does not store the raw actions into the relational db (MySQL) for scalability reasons. By default actions are stored into MemCache so that only recent activity is available....