v1beta1

type AIXExplainerSpec struct {
	// The type of AIX explainer
	Type AIXExplainerType `json:"type"`
	// Contains fields shared across all explainers
	ExplainerExtensionSpec `json:",inline"`
}

type AIXExplainerType string

type ARTExplainerSpec struct {
	// The type of ART explainer
	Type ARTExplainerType `json:"type"`
	// Contains fields shared across all explainers
	ExplainerExtensionSpec `json:",inline"`
}

type ARTExplainerType string

type AlibiExplainerSpec struct {
	// The type of Alibi explainer <br />
	// Valid values are: <br />
	// - "AnchorTabular"; <br />
	// - "AnchorImages"; <br />
	// - "AnchorText"; <br />
	// - "Counterfactuals"; <br />
	// - "Contrastive"; <br />
	Type AlibiExplainerType `json:"type"`
	// Contains fields shared across all explainers
	ExplainerExtensionSpec `json:",inline"`
}

type AlibiExplainerType string

type Batcher struct {
	// Specifies the max number of requests to trigger a batch
	// +optional
	MaxBatchSize *int `json:"maxBatchSize,omitempty"`
	// Specifies the max latency to trigger a batch
	// +optional
	MaxLatency *int `json:"maxLatency,omitempty"`
	// Specifies the timeout of a batch
	// +optional
	Timeout *int `json:"timeout,omitempty"`
}

type Component interface {
	GetImplementation() ComponentImplementation
	GetImplementations() []ComponentImplementation
	GetExtensions() *ComponentExtensionSpec
}

type ComponentExtensionSpec struct {
	// Minimum number of replicas, defaults to 1 but can be set to 0 to enable scale-to-zero.
	// +optional
	MinReplicas *int `json:"minReplicas,omitempty"`
	// Maximum number of replicas for autoscaling.
	// +optional
	MaxReplicas int `json:"maxReplicas,omitempty"`
	// ContainerConcurrency specifies how many requests can be processed concurrently, this sets the hard limit of the container
	// concurrency(https://knative.dev/docs/serving/autoscaling/concurrency).
	// +optional
	ContainerConcurrency *int64 `json:"containerConcurrency,omitempty"`
	// TimeoutSeconds specifies the number of seconds to wait before timing out a request to the component.
	// +optional
	TimeoutSeconds *int64 `json:"timeout,omitempty"`
	// CanaryTrafficPercent defines the traffic split percentage between the candidate revision and the last ready revision
	// +optional
	CanaryTrafficPercent *int64 `json:"canaryTrafficPercent,omitempty"`
	// Activate request/response logging and logger configurations
	// +optional
	Logger *LoggerSpec `json:"logger,omitempty"`
	// Activate request batching and batching configurations
	// +optional
	Batcher *Batcher `json:"batcher,omitempty"`
}

type ComponentImplementation interface {
	Default(config *InferenceServicesConfig)
	Validate() error
	GetContainer(metadata metav1.ObjectMeta, extensions *ComponentExtensionSpec, config *InferenceServicesConfig) *v1.Container
	GetStorageUri() *string
	GetProtocol() constants.InferenceServiceProtocol
	IsMMS(config *InferenceServicesConfig) bool
}

type ComponentStatusSpec struct {
	// Latest revision name that is in ready state
	// +optional
	LatestReadyRevision string `json:"latestReadyRevision,omitempty"`
	// Latest revision name that is created
	// +optional
	LatestCreatedRevision string `json:"latestCreatedRevision,omitempty"`
	// Previous revision name that is rolled out with 100 percent traffic
	// +optional
	PreviousRolledoutRevision string `json:"previousRolledoutRevision,omitempty"`
	// Latest revision name that is rolled out with 100 percent traffic
	// +optional
	LatestRolledoutRevision string `json:"latestRolledoutRevision,omitempty"`
	// Traffic holds the configured traffic distribution for latest ready revision and previous rolled out revision.
	// +optional
	Traffic []knservingv1.TrafficTarget `json:"traffic,omitempty"`
	// URL holds the url that will distribute traffic over the provided traffic targets.
	// It generally has the form http[s]://{route-name}.{route-namespace}.{cluster-level-suffix}
	// +optional
	URL *apis.URL `json:"url,omitempty"`
	// Addressable endpoint for the InferenceService
	// +optional
	Address *duckv1.Addressable `json:"address,omitempty"`
}

type ComponentType string

type CustomExplainer struct {
	v1.PodSpec `json:",inline"`
}

type CustomPredictor struct {
	v1.PodSpec `json:",inline"`
}

type CustomTransformer struct {
	v1.PodSpec `json:",inline"`
}

type ExplainerConfig struct {
	// explainer docker image name
	ContainerImage string `json:"image"`
	// default explainer docker image version
	DefaultImageVersion string `json:"defaultImageVersion"`
}

type ExplainerExtensionSpec struct {
	// The location of a trained explanation model
	StorageURI string `json:"storageUri,omitempty"`
	// Defaults to latest Explainer Version
	RuntimeVersion *string `json:"runtimeVersion,omitempty"`
	// Inline custom parameter settings for explainer
	Config map[string]string `json:"config,omitempty"`
	// Container enables overrides for the predictor.
	// Each framework will have different defaults that are populated in the underlying container spec.
	// +optional
	v1.Container `json:",inline"`
}

type ExplainerSpec struct {
	// Spec for alibi explainer
	Alibi *AlibiExplainerSpec `json:"alibi,omitempty"`
	// Spec for AIX explainer
	AIX *AIXExplainerSpec `json:"aix,omitempty"`
	// Spec for ART explainer
	ART *ARTExplainerSpec `json:"art,omitempty"`
	// This spec is dual purpose.
	// 1) Users may choose to provide a full PodSpec for their custom explainer.
	// The field PodSpec.Containers is mutually exclusive with other explainers (i.e. Alibi).
	// 2) Users may choose to provide a Explainer (i.e. Alibi) and specify PodSpec
	// overrides in the PodSpec. They must not provide PodSpec.Containers in this case.
	PodSpec `json:",inline"`
	// Component extension defines the deployment configurations for explainer
	ComponentExtensionSpec `json:",inline"`
}

type ExplainersConfig struct {
	AlibiExplainer ExplainerConfig `json:"alibi,omitempty"`
	AIXExplainer   ExplainerConfig `json:"aix,omitempty"`
	ARTExplainer   ExplainerConfig `json:"art,omitempty"`
}

type InferenceService struct {
	metav1.TypeMeta   `json:",inline"`
	metav1.ObjectMeta `json:"metadata,omitempty"`

	Spec   InferenceServiceSpec   `json:"spec,omitempty"`
	Status InferenceServiceStatus `json:"status,omitempty"`
}

type InferenceServiceList struct {
	metav1.TypeMeta `json:",inline"`
	metav1.ListMeta `json:"metadata,omitempty"`
	// +listType=set
	Items []InferenceService `json:"items"`
}

type InferenceServiceSpec struct {
	// Predictor defines the model serving spec
	// +required
	Predictor PredictorSpec `json:"predictor"`
	// Explainer defines the model explanation service spec,
	// explainer service calls to predictor or transformer if it is specified.
	// +optional
	Explainer *ExplainerSpec `json:"explainer,omitempty"`
	// Transformer defines the pre/post processing before and after the predictor call,
	// transformer service calls to predictor service.
	// +optional
	Transformer *TransformerSpec `json:"transformer,omitempty"`
}

type InferenceServiceStatus struct {
	// Conditions for the InferenceService <br/>
	// - PredictorReady: predictor readiness condition; <br/>
	// - TransformerReady: transformer readiness condition; <br/>
	// - ExplainerReady: explainer readiness condition; <br/>
	// - RoutesReady: aggregated routing condition; <br/>
	// - Ready: aggregated condition; <br/>
	duckv1.Status `json:",inline"`
	// Addressable endpoint for the InferenceService
	// +optional
	Address *duckv1.Addressable `json:"address,omitempty"`
	// URL holds the url that will distribute traffic over the provided traffic targets.
	// It generally has the form http[s]://{route-name}.{route-namespace}.{cluster-level-suffix}
	// +optional
	URL *apis.URL `json:"url,omitempty"`
	// Statuses for the components of the InferenceService
	Components map[ComponentType]ComponentStatusSpec `json:"components,omitempty"`
}

type InferenceServicesConfig struct {
	// Transformer configurations
	Transformers TransformersConfig `json:"transformers"`
	// Predictor configurations
	Predictors PredictorsConfig `json:"predictors"`
	// Explainer configurations
	Explainers ExplainersConfig `json:"explainers"`
}

type IngressConfig struct {
	IngressGateway          string `json:"ingressGateway,omitempty"`
	IngressServiceName      string `json:"ingressService,omitempty"`
	LocalGateway            string `json:"localGateway,omitempty"`
	LocalGatewayServiceName string `json:"localGatewayService,omitempty"`
}

type LightGBMSpec struct {
	// Contains fields shared across all predictors
	PredictorExtensionSpec `json:",inline"`
}

type LoggerSpec struct {
	// URL to send logging events
	// +optional
	URL *string `json:"url,omitempty"`
	// Specifies the scope of the loggers. <br />
	// Valid values are: <br />
	// - "all" (default): log both request and response; <br />
	// - "request": log only request; <br />
	// - "response": log only response <br />
	// +optional
	Mode LoggerType `json:"mode,omitempty"`
}

type LoggerType string

type ONNXRuntimeSpec struct {
	// Contains fields shared across all predictors
	PredictorExtensionSpec `json:",inline"`
}

type PMMLSpec struct {
	// Contains fields shared across all predictors
	PredictorExtensionSpec `json:",inline"`
}

type PaddleServerSpec struct {
	PredictorExtensionSpec `json:",inline"`
}

type PodSpec struct {
	// List of volumes that can be mounted by containers belonging to the pod.
	// More info: https://kubernetes.io/docs/concepts/storage/volumes
	// +optional
	// +patchMergeKey=name
	// +patchStrategy=merge,retainKeys
	Volumes []v1.Volume `json:"volumes,omitempty" patchStrategy:"merge,retainKeys" patchMergeKey:"name" protobuf:"bytes,1,rep,name=volumes"`
	// List of initialization containers belonging to the pod.
	// Init containers are executed in order prior to containers being started. If any
	// init container fails, the pod is considered to have failed and is handled according
	// to its restartPolicy. The name for an init container or normal container must be
	// unique among all containers.
	// Init containers may not have Lifecycle actions, Readiness probes, Liveness probes, or Startup probes.
	// The resourceRequirements of an init container are taken into account during scheduling
	// by finding the highest request/limit for each resource type, and then using the max of
	// of that value or the sum of the normal containers. Limits are applied to init containers
	// in a similar fashion.
	// Init containers cannot currently be added or removed.
	// Cannot be updated.
	// More info: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/
	// +patchMergeKey=name
	// +patchStrategy=merge
	InitContainers []v1.Container `json:"initContainers,omitempty" patchStrategy:"merge" patchMergeKey:"name" protobuf:"bytes,20,rep,name=initContainers"`
	// List of containers belonging to the pod.
	// Containers cannot currently be added or removed.
	// There must be at least one container in a Pod.
	// Cannot be updated.
	// +patchMergeKey=name
	// +patchStrategy=merge
	Containers []v1.Container `json:"containers,omitempty" patchStrategy:"merge" patchMergeKey:"name" protobuf:"bytes,2,rep,name=containers"`
	// List of ephemeral containers run in this pod. Ephemeral containers may be run in an existing
	// pod to perform user-initiated actions such as debugging. This list cannot be specified when
	// creating a pod, and it cannot be modified by updating the pod spec. In order to add an
	// ephemeral container to an existing pod, use the pod's ephemeralcontainers subresource.
	// This field is alpha-level and is only honored by servers that enable the EphemeralContainers feature.
	// +optional
	// +patchMergeKey=name
	// +patchStrategy=merge
	// +kubebuilder:pruning:PreserveUnknownFields
	EphemeralContainers []v1.EphemeralContainer `` /* 128-byte string literal not displayed */
	// Restart policy for all containers within the pod.
	// One of Always, OnFailure, Never.
	// Default to Always.
	// More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#restart-policy
	// +optional
	RestartPolicy v1.RestartPolicy `json:"restartPolicy,omitempty" protobuf:"bytes,3,opt,name=restartPolicy,casttype=RestartPolicy"`
	// Optional duration in seconds the pod needs to terminate gracefully. May be decreased in delete request.
	// Value must be non-negative integer. The value zero indicates delete immediately.
	// If this value is nil, the default grace period will be used instead.
	// The grace period is the duration in seconds after the processes running in the pod are sent
	// a termination signal and the time when the processes are forcibly halted with a kill signal.
	// Set this value longer than the expected cleanup time for your process.
	// Defaults to 30 seconds.
	// +optional
	TerminationGracePeriodSeconds *int64 `json:"terminationGracePeriodSeconds,omitempty" protobuf:"varint,4,opt,name=terminationGracePeriodSeconds"`
	// Optional duration in seconds the pod may be active on the node relative to
	// StartTime before the system will actively try to mark it failed and kill associated containers.
	// Value must be a positive integer.
	// +optional
	ActiveDeadlineSeconds *int64 `json:"activeDeadlineSeconds,omitempty" protobuf:"varint,5,opt,name=activeDeadlineSeconds"`
	// Set DNS policy for the pod.
	// Defaults to "ClusterFirst".
	// Valid values are 'ClusterFirstWithHostNet', 'ClusterFirst', 'Default' or 'None'.
	// DNS parameters given in DNSConfig will be merged with the policy selected with DNSPolicy.
	// To have DNS options set along with hostNetwork, you have to specify DNS policy
	// explicitly to 'ClusterFirstWithHostNet'.
	// +optional
	DNSPolicy v1.DNSPolicy `json:"dnsPolicy,omitempty" protobuf:"bytes,6,opt,name=dnsPolicy,casttype=DNSPolicy"`
	// NodeSelector is a selector which must be true for the pod to fit on a node.
	// Selector which must match a node's labels for the pod to be scheduled on that node.
	// More info: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
	// +optional
	NodeSelector map[string]string `json:"nodeSelector,omitempty" protobuf:"bytes,7,rep,name=nodeSelector"`

	// ServiceAccountName is the name of the ServiceAccount to use to run this pod.
	// More info: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/
	// +optional
	ServiceAccountName string `json:"serviceAccountName,omitempty" protobuf:"bytes,8,opt,name=serviceAccountName"`
	// DeprecatedServiceAccount is a depreciated alias for ServiceAccountName.
	// Deprecated: Use serviceAccountName instead.
	// +k8s:conversion-gen=false
	// +optional
	DeprecatedServiceAccount string `json:"serviceAccount,omitempty" protobuf:"bytes,9,opt,name=serviceAccount"`
	// AutomountServiceAccountToken indicates whether a service account token should be automatically mounted.
	// +optional
	AutomountServiceAccountToken *bool `json:"automountServiceAccountToken,omitempty" protobuf:"varint,21,opt,name=automountServiceAccountToken"`

	// NodeName is a request to schedule this pod onto a specific node. If it is non-empty,
	// the scheduler simply schedules this pod onto that node, assuming that it fits resource
	// requirements.
	// +optional
	NodeName string `json:"nodeName,omitempty" protobuf:"bytes,10,opt,name=nodeName"`
	// Host networking requested for this pod. Use the host's network namespace.
	// If this option is set, the ports that will be used must be specified.
	// Default to false.
	// +k8s:conversion-gen=false
	// +optional
	HostNetwork bool `json:"hostNetwork,omitempty" protobuf:"varint,11,opt,name=hostNetwork"`
	// Use the host's pid namespace.
	// Optional: Default to false.
	// +k8s:conversion-gen=false
	// +optional
	HostPID bool `json:"hostPID,omitempty" protobuf:"varint,12,opt,name=hostPID"`
	// Use the host's ipc namespace.
	// Optional: Default to false.
	// +k8s:conversion-gen=false
	// +optional
	HostIPC bool `json:"hostIPC,omitempty" protobuf:"varint,13,opt,name=hostIPC"`
	// Share a single process namespace between all of the containers in a pod.
	// When this is set containers will be able to view and signal processes from other containers
	// in the same pod, and the first process in each container will not be assigned PID 1.
	// HostPID and ShareProcessNamespace cannot both be set.
	// Optional: Default to false.
	// +k8s:conversion-gen=false
	// +optional
	ShareProcessNamespace *bool `json:"shareProcessNamespace,omitempty" protobuf:"varint,27,opt,name=shareProcessNamespace"`
	// SecurityContext holds pod-level security attributes and common container settings.
	// Optional: Defaults to empty.  See type description for default values of each field.
	// +optional
	SecurityContext *v1.PodSecurityContext `json:"securityContext,omitempty" protobuf:"bytes,14,opt,name=securityContext"`
	// ImagePullSecrets is an optional list of references to secrets in the same namespace to use for pulling any of the images used by this PodSpec.
	// If specified, these secrets will be passed to individual puller implementations for them to use. For example,
	// in the case of docker, only DockerConfig type secrets are honored.
	// More info: https://kubernetes.io/docs/concepts/containers/images#specifying-imagepullsecrets-on-a-pod
	// +optional
	// +patchMergeKey=name
	// +patchStrategy=merge
	ImagePullSecrets []v1.LocalObjectReference `json:"imagePullSecrets,omitempty" patchStrategy:"merge" patchMergeKey:"name" protobuf:"bytes,15,rep,name=imagePullSecrets"`
	// Specifies the hostname of the Pod
	// If not specified, the pod's hostname will be set to a system-defined value.
	// +optional
	Hostname string `json:"hostname,omitempty" protobuf:"bytes,16,opt,name=hostname"`
	// If specified, the fully qualified Pod hostname will be "<hostname>.<subdomain>.<pod namespace>.svc.<cluster domain>".
	// If not specified, the pod will not have a domainname at all.
	// +optional
	Subdomain string `json:"subdomain,omitempty" protobuf:"bytes,17,opt,name=subdomain"`
	// If specified, the pod's scheduling constraints
	// +optional
	Affinity *v1.Affinity `json:"affinity,omitempty" protobuf:"bytes,18,opt,name=affinity"`
	// If specified, the pod will be dispatched by specified scheduler.
	// If not specified, the pod will be dispatched by default scheduler.
	// +optional
	SchedulerName string `json:"schedulerName,omitempty" protobuf:"bytes,19,opt,name=schedulerName"`
	// If specified, the pod's tolerations.
	// +optional
	Tolerations []v1.Toleration `json:"tolerations,omitempty" protobuf:"bytes,22,opt,name=tolerations"`
	// HostAliases is an optional list of hosts and IPs that will be injected into the pod's hosts
	// file if specified. This is only valid for non-hostNetwork pods.
	// +optional
	// +patchMergeKey=ip
	// +patchStrategy=merge
	HostAliases []v1.HostAlias `json:"hostAliases,omitempty" patchStrategy:"merge" patchMergeKey:"ip" protobuf:"bytes,23,rep,name=hostAliases"`
	// If specified, indicates the pod's priority. "system-node-critical" and
	// "system-cluster-critical" are two special keywords which indicate the
	// highest priorities with the former being the highest priority. Any other
	// name must be defined by creating a PriorityClass object with that name.
	// If not specified, the pod priority will be default or zero if there is no
	// default.
	// +optional
	PriorityClassName string `json:"priorityClassName,omitempty" protobuf:"bytes,24,opt,name=priorityClassName"`
	// The priority value. Various system components use this field to find the
	// priority of the pod. When Priority Admission Controller is enabled, it
	// prevents users from setting this field. The admission controller populates
	// this field from PriorityClassName.
	// The higher the value, the higher the priority.
	// +optional
	Priority *int32 `json:"priority,omitempty" protobuf:"bytes,25,opt,name=priority"`
	// Specifies the DNS parameters of a pod.
	// Parameters specified here will be merged to the generated DNS
	// configuration based on DNSPolicy.
	// +optional
	DNSConfig *v1.PodDNSConfig `json:"dnsConfig,omitempty" protobuf:"bytes,26,opt,name=dnsConfig"`
	// If specified, all readiness gates will be evaluated for pod readiness.
	// A pod is ready when all its containers are ready AND
	// all conditions specified in the readiness gates have status equal to "True"
	// More info: https://git.k8s.io/enhancements/keps/sig-network/0007-pod-ready%2B%2B.md
	// +optional
	ReadinessGates []v1.PodReadinessGate `json:"readinessGates,omitempty" protobuf:"bytes,28,opt,name=readinessGates"`
	// RuntimeClassName refers to a RuntimeClass object in the node.k8s.io group, which should be used
	// to run this pod.  If no RuntimeClass resource matches the named class, the pod will not be run.
	// If unset or empty, the "legacy" RuntimeClass will be used, which is an implicit class with an
	// empty definition that uses the default runtime handler.
	// More info: https://git.k8s.io/enhancements/keps/sig-node/runtime-class.md
	// This is a beta feature as of Kubernetes v1.14.
	// +optional
	RuntimeClassName *string `json:"runtimeClassName,omitempty" protobuf:"bytes,29,opt,name=runtimeClassName"`
	// EnableServiceLinks indicates whether information about services should be injected into pod's
	// environment variables, matching the syntax of Docker links.
	// Optional: Defaults to true.
	// +optional
	EnableServiceLinks *bool `json:"enableServiceLinks,omitempty" protobuf:"varint,30,opt,name=enableServiceLinks"`
	// PreemptionPolicy is the Policy for preempting pods with lower priority.
	// One of Never, PreemptLowerPriority.
	// Defaults to PreemptLowerPriority if unset.
	// This field is beta-level, gated by the NonPreemptingPriority feature-gate.
	// +optional
	PreemptionPolicy *v1.PreemptionPolicy `json:"preemptionPolicy,omitempty" protobuf:"bytes,31,opt,name=preemptionPolicy"`
	// Overhead represents the resource overhead associated with running a pod for a given RuntimeClass.
	// This field will be autopopulated at admission time by the RuntimeClass admission controller. If
	// the RuntimeClass admission controller is enabled, overhead must not be set in Pod create requests.
	// The RuntimeClass admission controller will reject Pod create requests which have the overhead already
	// set. If RuntimeClass is configured and selected in the PodSpec, Overhead will be set to the value
	// defined in the corresponding RuntimeClass, otherwise it will remain unset and treated as zero.
	// More info: https://git.k8s.io/enhancements/keps/sig-node/20190226-pod-overhead.md
	// This field is alpha-level as of Kubernetes v1.16, and is only honored by servers that enable the PodOverhead feature.
	// +optional
	Overhead v1.ResourceList `json:"overhead,omitempty" protobuf:"bytes,32,opt,name=overhead"`
	// TopologySpreadConstraints describes how a group of pods ought to spread across topology
	// domains. Scheduler will schedule pods in a way which abides by the constraints.
	// All topologySpreadConstraints are ANDed.
	// +optional
	// +patchMergeKey=topologyKey
	// +patchStrategy=merge
	// +listType=map
	// +listMapKey=topologyKey
	// +listMapKey=whenUnsatisfiable
	TopologySpreadConstraints []v1.TopologySpreadConstraint `` /* 147-byte string literal not displayed */
	// If true the pod's hostname will be configured as the pod's FQDN, rather than the leaf name (the default).
	// In Linux containers, this means setting the FQDN in the hostname field of the kernel (the nodename field of struct utsname).
	// In Windows containers, this means setting the registry value of hostname for the registry key HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Services\\Tcpip\\Parameters to FQDN.
	// If a pod does not have FQDN, this has no effect.
	// Default to false.
	// +optional
	SetHostnameAsFQDN *bool `json:"setHostnameAsFQDN,omitempty" protobuf:"varint,35,opt,name=setHostnameAsFQDN"`
}

type PredictorConfig struct {
	// predictor docker image name
	ContainerImage string `json:"image"`
	// default predictor docker image version on cpu
	DefaultImageVersion string `json:"defaultImageVersion"`
	// default predictor docker image version on gpu
	DefaultGpuImageVersion string `json:"defaultGpuImageVersion"`
	// Default timeout of predictor for serving a request, in seconds
	DefaultTimeout int64 `json:"defaultTimeout,string,omitempty"`
	// Flag to determine if multi-model serving is supported
	MultiModelServer bool `json:"multiModelServer,boolean,omitempty"`
	// frameworks the model agent is able to run
	SupportedFrameworks []string `json:"supportedFrameworks"`
}

type PredictorExtensionSpec struct {
	// This field points to the location of the trained model which is mounted onto the pod.
	// +optional
	StorageURI *string `json:"storageUri,omitempty"`
	// Runtime version of the predictor docker image
	// +optional
	RuntimeVersion *string `json:"runtimeVersion,omitempty"`
	// Protocol version to use by the predictor (i.e. v1 or v2)
	// +optional
	ProtocolVersion *constants.InferenceServiceProtocol `json:"protocolVersion,omitempty"`
	// Container enables overrides for the predictor.
	// Each framework will have different defaults that are populated in the underlying container spec.
	// +optional
	v1.Container `json:",inline"`
}

type PredictorImplementation interface {
	IsFrameworkSupported(framework string, config *InferenceServicesConfig) bool
}

type PredictorProtocols struct {
	V1 *PredictorConfig `json:"v1,omitempty"`
	V2 *PredictorConfig `json:"v2,omitempty"`
}

type PredictorSpec struct {
	// Spec for SKLearn model server
	SKLearn *SKLearnSpec `json:"sklearn,omitempty"`
	// Spec for XGBoost model server
	XGBoost *XGBoostSpec `json:"xgboost,omitempty"`
	// Spec for TFServing (https://github.com/tensorflow/serving)
	Tensorflow *TFServingSpec `json:"tensorflow,omitempty"`
	// Spec for TorchServe (https://pytorch.org/serve)
	PyTorch *TorchServeSpec `json:"pytorch,omitempty"`
	// Spec for Triton Inference Server (https://github.com/triton-inference-server/server)
	Triton *TritonSpec `json:"triton,omitempty"`
	// Spec for ONNX runtime (https://github.com/microsoft/onnxruntime)
	ONNX *ONNXRuntimeSpec `json:"onnx,omitempty"`
	// Spec for PMML (http://dmg.org/pmml/v4-1/GeneralStructure.html)
	PMML *PMMLSpec `json:"pmml,omitempty"`
	// Spec for LightGBM model server
	LightGBM *LightGBMSpec `json:"lightgbm,omitempty"`
	// Spec for Paddle model server (https://github.com/PaddlePaddle/Serving)
	Paddle *PaddleServerSpec `json:"paddle,omitempty"`

	// This spec is dual purpose. <br />
	// 1) Provide a full PodSpec for custom predictor.
	// The field PodSpec.Containers is mutually exclusive with other predictors (i.e. TFServing). <br />
	// 2) Provide a predictor (i.e. TFServing) and specify PodSpec
	// overrides, you must not provide PodSpec.Containers in this case. <br />
	PodSpec `json:",inline"`
	// Component extension defines the deployment configurations for a predictor
	ComponentExtensionSpec `json:",inline"`
}

type PredictorsConfig struct {
	Tensorflow PredictorConfig    `json:"tensorflow,omitempty"`
	Triton     PredictorConfig    `json:"triton,omitempty"`
	XGBoost    PredictorProtocols `json:"xgboost,omitempty"`
	SKlearn    PredictorProtocols `json:"sklearn,omitempty"`
	PyTorch    PredictorProtocols `json:"pytorch,omitempty"`
	ONNX       PredictorConfig    `json:"onnx,omitempty"`
	PMML       PredictorConfig    `json:"pmml,omitempty"`
	LightGBM   PredictorConfig    `json:"lightgbm,omitempty"`
	Paddle     PredictorConfig    `json:"paddle,omitempty"`
}

type SKLearnSpec struct {
	// Contains fields shared across all predictors
	PredictorExtensionSpec `json:",inline"`
}

type TFServingSpec struct {
	// Contains fields shared across all predictors
	PredictorExtensionSpec `json:",inline"`
}

type TorchServeSpec struct {
	// When this field is specified KFS chooses the KFServer implementation, otherwise KFS uses the TorchServe implementation
	// +optional
	ModelClassName string `json:"modelClassName,omitempty"`
	// Contains fields shared across all predictors
	PredictorExtensionSpec `json:",inline"`
}

type TransformerConfig struct {
	// transformer docker image name
	ContainerImage string `json:"image"`
	// default transformer docker image version
	DefaultImageVersion string `json:"defaultImageVersion"`
}

type TransformerSpec struct {
	// This spec is dual purpose. <br />
	// 1) Provide a full PodSpec for custom transformer.
	// The field PodSpec.Containers is mutually exclusive with other transformers. <br />
	// 2) Provide a transformer and specify PodSpec
	// overrides, you must not provide PodSpec.Containers in this case. <br />
	PodSpec `json:",inline"`
	// Component extension defines the deployment configurations for a transformer
	ComponentExtensionSpec `json:",inline"`
}

type TransformersConfig struct {
	Feast TransformerConfig `json:"feast,omitempty"`
}

type TritonSpec struct {
	// Contains fields shared across all predictors
	PredictorExtensionSpec `json:",inline"`
}

type XGBoostSpec struct {
	// Contains fields shared across all predictors
	PredictorExtensionSpec `json:",inline"`
}