Schemas

The ray.serve.schema module defines the models that describe Serve’s state and configuration. The Serve REST API accepts the config schemas and returns the response schemas.

Status and details

serve.schema.ServeActorDetails	Detailed info about a Ray Serve actor.
serve.schema.ProxyDetails	Detailed info about a Ray Serve ProxyActor.
serve.schema.ApplicationStatusOverview	Describes the status of an application and all its deployments.
serve.schema.ServeStatus	Describes the status of Serve.
serve.schema.DeploymentStatusOverview	Describes the status of a deployment.
serve.schema.EncodingType	Encoding type for the serve logs.
serve.schema.AutoscalingMetricsHealth	PublicAPI (alpha): This API is in alpha and may change before becoming stable.
serve.schema.AutoscalingStatus	PublicAPI (alpha): This API is in alpha and may change before becoming stable.
serve.schema.ScalingDecision	One autoscaling decision with minimal provenance.
serve.schema.DeploymentAutoscalingDetail	Deployment-level autoscaler observability.
serve.schema.ReplicaRank	Replica rank model.

serve.schema.TaskProcessorAdapter

Abstract base class for task processing adapters.

Config schemas

serve.schema.ServeDeploySchema	Multi-application config for deploying a list of Serve applications to the Ray cluster.
serve.schema.gRPCOptionsSchema	Options to start the gRPC Proxy with.
serve.schema.HTTPOptionsSchema	Options to start the HTTP Proxy with.
serve.schema.ServeApplicationSchema	Describes one Serve application, and currently can also be used as a standalone config to deploy a single application to a Ray cluster.
serve.schema.DeploymentSchema
serve.schema.RayActorOptionsSchema	Options with which to start a replica actor.
serve.schema.CeleryAdapterConfig	Celery adapter config. You can use it to configure the Celery task processor for your Serve application.
serve.schema.TaskProcessorConfig	Task processor config. You can use it to configure the task processor for your Serve application.
serve.schema.TaskResult	Task result Model.
serve.schema.ScaleDeploymentRequest	Request schema for scaling a deployment's replicas.

Response schemas

serve.schema.ServeInstanceDetails	Serve metadata with system-level info and details on all applications deployed to the Ray cluster.
serve.schema.ApplicationDetails	Detailed info about a Serve application.
serve.schema.DeploymentDetails	Detailed info about a deployment within a Serve application.
serve.schema.ReplicaDetails	Detailed info about a single deployment replica.
serve.schema.TargetGroup	PublicAPI (alpha): This API is in alpha and may change before becoming stable.
serve.schema.Target	PublicAPI (alpha): This API is in alpha and may change before becoming stable.
serve.schema.DeploymentNode	Represents a node in the deployment topology.
serve.schema.DeploymentTopology	Represents the dependency graph of deployments in an application.
serve.schema.ControllerHealthMetrics	Health metrics for the Ray Serve controller.
serve.schema.DurationStats	Statistics for a collection of duration/latency measurements.

serve.schema.APIType	Tracks the type of API that an application originates from.
serve.schema.ApplicationStatus	The current status of the application.
serve.schema.ProxyStatus	The current status of the proxy.