Deployment handles

Deployment handles call one deployment from another, or call a running application from Python. The handle and response classes live in ray.serve.handle.

Note

The deprecated RayServeHandle and RayServeSyncHandle APIs have been fully removed as of Ray 2.10. See the model composition guide for how to update code to use the DeploymentHandle API instead.

Handle and response classes

serve.handle.DeploymentHandle	A handle used to make requests to a deployment at runtime.
serve.handle.DeploymentResponse	A future-like object wrapping the result of a unary deployment handle call.
serve.handle.DeploymentResponseGenerator	A future-like object wrapping the result of a streaming deployment handle call.
serve.handle.DeploymentBroadcastResponse	Wraps the results of a broadcast call to all replicas of a deployment.

Get a handle

serve.get_app_handle	Get a handle to the application's ingress deployment by name.
serve.get_deployment_handle	Get a handle to a deployment by name.