Document custom inference servers

[adriangonz]

Fixes #1416

Changelog

• Add new page on building and adding "Custom Inference Servers".
• Split S2I + Docker link to wrapping your own model in 2 separate lines.

[adriangonz]

/cc @axsaucedo @RafalSkolasinski

[seldondev]

Tue Apr 7 17:05:55 UTC 2020
The logs for [pr-build] [1] will show after the pipeline context has finished.
https://github.com/SeldonIO/seldon-core/blob/gh-pages/jenkins-x/logs/SeldonIO/seldon-core/PR-1673/1.log

impatient try
jx get build logs SeldonIO/seldon-core/PR-1673 --build=1

[seldondev]

Tue Apr 7 17:06:00 UTC 2020
The logs for [lint] [2] will show after the pipeline context has finished.
https://github.com/SeldonIO/seldon-core/blob/gh-pages/jenkins-x/logs/SeldonIO/seldon-core/PR-1673/2.log

impatient try
jx get build logs SeldonIO/seldon-core/PR-1673 --build=2

[axsaucedo]

Awesome!! @adriangonz if you add the link to the index in readme.md it should be good to land

[RafalSkolasinski]

If it possible to specify custom inference server without modifying configmap it may be worth adding.
It would allow users who only have single-namespace access to deploy such servers without asking admins to modify seldon-core wide configmap.

[axsaucedo]

@RafalSkolasinski that's an interesting point, I think we could abstract this eventually, but I think we shoudl create a ticket for that, as I agree that this is something that may be worth exploring - ie how users coudl add their own prepackaged servers withou modifying the global config.. perhaps this could even be a namespace configmap that can overrride the global configmap

[RafalSkolasinski]

/lgtm

[RafalSkolasinski]

/approve

[RafalSkolasinski]

@adriangonz It may be a good idea to link that custom prepackaged servers from mlflow server docpage, what do you think?

[adriangonz]

Thanks for the comments @RafalSkolasinski @axsaucedo. Both should be added now!

[RafalSkolasinski]

Awesome stuff!
/lgtm
/approve

[seldondev]

Wed Apr 8 14:41:57 UTC 2020
The logs for [pr-build] [3] will show after the pipeline context has finished.
https://github.com/SeldonIO/seldon-core/blob/gh-pages/jenkins-x/logs/SeldonIO/seldon-core/PR-1673/3.log

impatient try
jx get build logs SeldonIO/seldon-core/PR-1673 --build=3

[seldondev]

Wed Apr 8 14:42:02 UTC 2020
The logs for [lint] [4] will show after the pipeline context has finished.
https://github.com/SeldonIO/seldon-core/blob/gh-pages/jenkins-x/logs/SeldonIO/seldon-core/PR-1673/4.log

impatient try
jx get build logs SeldonIO/seldon-core/PR-1673 --build=4

[seldondev]

[APPROVALNOTIFIER] This PR is APPROVED

Approval requirements bypassed by manually added approval.

This pull-request has been approved by: RafalSkolasinski

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[seldondev]

failed to trigger Pull Request pipeline

• failed to create agent
• failed to calculate in repo config
• failed to load trigger config for repository SeldonIO/seldon-core for ref 9753aa1
• failed to find any lighthouse configuration files in repo SeldonIO/seldon-core at sha 9753aa1
• failed to process repo SeldonIO/seldon-core refref 9753aa1
• failed to list files in directory /var/tmp/gitrepo660600678/.lighthouse
• open /var/tmp/gitrepo660600678/.lighthouse
• no such file or directory