KF 5328 integrate paddleserver rock (#219)

* update README.md to reduce maintenance

This edits README.md to point at the source of truth for default images rather than having it written a second time in the README.md, removing the need to keep the readme up to date as well as reducing the chance for error.

* integrate paddleserver rock for 0.11.2

* fix: use correct paddle image, remove extra namespace

.gitignore

@@ -3,3 +3,4 @@
 *.tox
 build/
 .vscode
+.python-version

README.md

@@ -206,28 +206,7 @@ Please see the [official docs site](https://charmed-kubeflow.io/docs) for comple
 
 ## Setting Custom Images for Kserve controller
 
-KServe controller comes with a set of preconfigured images that are used in Kserve workloads. This is the list of default images used in charm.
-
-```json
-{
-    "configmap__agent": "kserve/agent:v0.11.1",
-    "configmap__batcher": "kserve/agent:v0.11.1",
-    "configmap__explainers__alibi": "kserve/alibi-explainer:latest",
-    "configmap__explainers__art": "kserve/art-explainer:latest",
-    "configmap__logger": "kserve/agent:v0.11.1",
-    "configmap__router": "kserve/router:v0.11.1",
-    "configmap__storageInitializer": "kserve/storage-initializer:v0.11.1",
-    "serving_runtimes__lgbserver": "kserve/lgbserver:v0.11.1",
-    "serving_runtimes__kserve_mlserver": "docker.io/seldonio/mlserver:1.3.2",
-    "serving_runtimes__paddleserver": "kserve/paddleserver:v0.11.1",
-    "serving_runtimes__pmmlserver": "kserve/pmmlserver:v0.11.1",
-    "serving_runtimes__sklearnserver": "kserve/sklearnserver:v0.11.1",
-    "serving_runtimes__tensorflow_serving": "tensorflow/serving:2.6.2",
-    "serving_runtimes__torchserve": "pytorch/torchserve-kfs:0.8.2",
-    "serving_runtimes__tritonserver": "nvcr.io/nvidia/tritonserver:23.05-py3",
-    "serving_runtimes__xgbserver": "kserve/xgbserver:v0.11.1",
-}
-```
+KServe controller comes with a set of preconfigured images that are used in Kserve workloads. The default images are listed in [default-custom-images.json](https://github.com/canonical/kserve-operators/blob/main/charms/kserve-controller/src/default-custom-images.json)
 
 These images can be overridden in the charm configuration under custom_images in the charms/kserve-controller/config.yaml file. Whenever you leave the custom_images field empty in the config, the default images will be used (listed above). You can specify your own images with the config by filling one or multiple entries. The config accepts either YAML or JSON entries. For example.
 

charms/kserve-controller/src/default-custom-images.json

@@ -8,7 +8,7 @@
     "configmap__storageInitializer": "kserve/storage-initializer:v0.11.1",
     "serving_runtimes__lgbserver": "kserve/lgbserver:v0.11.1",
     "serving_runtimes__kserve_mlserver": "docker.io/seldonio/mlserver:1.3.2",
-    "serving_runtimes__paddleserver": "kserve/paddleserver:v0.11.1",
+    "serving_runtimes__paddleserver": "charmedkubeflow/paddleserver:0.11.2-ee9909a",
     "serving_runtimes__pmmlserver": "kserve/pmmlserver:v0.11.1",
     "serving_runtimes__sklearnserver": "kserve/sklearnserver:v0.11.1",
     "serving_runtimes__tensorflow_serving": "tensorflow/serving:2.6.2",

charms/kserve-controller/tests/integration/paddleserver-resnet.yaml

@@ -0,0 +1,17 @@
+apiVersion: "serving.kserve.io/v1beta1"
+kind: "InferenceService"
+metadata:
+  name: "paddle-resnet50"
+spec:
+  predictor:
+    model:
+      modelFormat:
+        name: paddle
+      storageUri: "gs://kfserving-examples/models/paddle/resnet"
+      resources:
+        limits:
+          cpu: 1
+          memory: 500Mi
+        requests:
+          cpu: 100m
+          memory: 250Mi

charms/kserve-controller/tests/integration/test_charm.py

@@ -197,7 +197,11 @@ def create_namespace():
 
 @pytest.mark.parametrize(
     "inference_file",
-    ["./tests/integration/sklearn-iris.yaml", "./tests/integration/pmml-server.yaml"],
+    [
+        "./tests/integration/sklearn-iris.yaml",
+        "./tests/integration/pmml-server.yaml",
+        "./tests/integration/paddleserver-resnet.yaml",
+    ],
 )
 def test_inference_service_raw_deployment(
     test_namespace: None, lightkube_client: lightkube.Client, inference_file, ops_test: OpsTest