adding required decorator, some more validation and defaulting

Author: kfswain

api/v1alpha1/inferencemodel_types.go

@@ -51,14 +51,21 @@ type InferenceModelSpec struct {
 	// +kubebuilder:validation:MaxLength=253
 	ModelName string `json:"modelName,omitempty"`
 	// Defines how important it is to serve the model compared to other models referencing the same pool.
+	//
 	// +optional
+	// +kubebuilder:default="Default"
 	Criticality *Criticality `json:"criticality,omitempty"`
 	// Allow multiple versions of a model for traffic splitting.
 	// If not specified, the target model name is defaulted to the modelName parameter.
 	// modelName is often in reference to a LoRA adapter.
+	//
 	// +optional
+	// +kubebuilder:validation:MinItems=1
+	// +kubebuilder:validation:MaxItems=10
 	TargetModels []TargetModel `json:"targetModels,omitempty"`
 	// Reference to the poolIt must exist in the same namespace.
+	//
+	// +kubebuilder:validation:Required
 	PoolRef *LocalObjectReference `json:"poolRef,omitempty"`
 }
 
@@ -74,6 +81,7 @@ type LocalObjectReference struct {
 	Group string `json:"group,omitempty"`
 
 	// Kind is kind of the referent. For example "InferencePool".
+	//
 	// +optional
 	// +kubebuilder:default="InferencePool"
 	// +kubebuilder:validation:MinLength=1

api/v1alpha1/inferencepool_types.go

@@ -31,13 +31,17 @@ type InferencePoolSpec struct {
 	// and will result in sub-optimal utilization.
 	// In some cases, implementations may translate this to a Service selector, so this matches the simple
 	// map used for Service selectors instead of the full Kubernetes LabelSelector type.
+	//
+	// +kubebuilder:validation:Required
 	Selector map[LabelString]LabelString `json:"selector,omitempty"`
 
 	// TargetPort is the port number that the model servers within the pool expect
 	// to recieve traffic from.
 	// This maps to the TargetPort in: https://pkg.go.dev/k8s.io/api/core/v1#ServicePort
+	//
 	// +kubebuilder:validation:Minimum=0
 	// +kubebuilder:validation:Maximum=65535
+	// +kubebuilder:validation:Required
 	TargetPort int32 `json:"targetPort,omitempty"`
 }
 

config/crd/bases/inference.networking.x-k8s.io_inferencemodels.yaml

@@ -55,6 +55,7 @@ spec:
               condition, one will be selected at random.
             properties:
               criticality:
+                default: Default
                 description: Defines how important it is to serve the model compared
                   to other models referencing the same pool.
                 enum:
@@ -124,7 +125,11 @@ spec:
                       minimum: 0
                       type: integer
                   type: object
+                maxItems: 10
+                minItems: 1
                 type: array
+            required:
+            - poolRef
             type: object
           status:
             description: InferenceModelStatus defines the observed state of InferenceModel

config/crd/bases/inference.networking.x-k8s.io_inferencepools.yaml

@@ -63,6 +63,9 @@ spec:
                 maximum: 65535
                 minimum: 0
                 type: integer
+            required:
+            - selector
+            - targetPort
             type: object
           status:
             description: InferencePoolStatus defines the observed state of InferencePool