Clive Cox
Clive Cox
A PR would indeed be welcome!
The simplest way is probably to extend the code we provide to add the endpoints you want. As @MattiaGallegati suggested there is also undocumented code in MLServer for custom endpoints...
We don't support Ambassador V2 APIs at present. See https://github.com/SeldonIO/seldon-core/issues/3790. Which version of Ambassaor have you installed?
Needs further investigation for Ambassador V2 APIs
[V2 emmisary chart](https://github.com/emissary-ingress/emissary/tree/master/charts/emissary-ingress).
We are looking to be more agnostic for service meshes in some V2 APIs we are introducing during H1. If you can propose some additions to the current SeldonDeployment API...
Still to be confirmed but current plan is an initial alpha release this quarter for feedback
OK will need to investigate. The code that creates it is [here](https://github.com/SeldonIO/seldon-core/blob/127ce8d8321bc2ac9050d9e8e8f99389ffd841f3/operator/controllers/seldondeployment_prepackaged_servers.go#L54) Are you seeing just 1 tfserving container?
You can call out to another Seldon Deployment but you would need to get the SVC URI from the status field
No I mean the SeldonDeployment Status has a url field which could be used to find it and call it.