Contents

Serve API Reference

Start or Connect to a Cluster

ray.serve.start(detached: bool = False, http_host: str = '127.0.0.1', http_port: int = 8000, http_middlewares: List[Any] = []) → ray.serve.api.Client[source]

Initialize a serve instance.

By default, the instance will be scoped to the lifetime of the returned Client object (or when the script exits). If detached is set to True, the instance will instead persist until client.shutdown() is called and clients to it can be connected using serve.connect(). This is only relevant if connecting to a long-running Ray cluster (e.g., with address=”auto”).

Parameters

  • detached (bool) – Whether not the instance should be detached from this script.

  • http_host (str) – Host for HTTP servers to listen on. Defaults to “127.0.0.1”. To expose Serve publicly, you probably want to set this to “0.0.0.0”. One HTTP server will be started on each node in the Ray cluster.

  • http_port (int) – Port for HTTP server. Defaults to 8000.

  • http_middleswares (list) – A list of Starlette middlewares that will be applied to the HTTP servers in the cluster.

ray.serve.connect() → ray.serve.api.Client[source]

Connect to an existing Serve instance on this Ray cluster.

If calling from the driver program, the Serve instance on this Ray cluster must first have been initialized using serve.start(detached=True).

If called from within a backend, will connect to the same Serve instance that the backend is running in.

Client API

class ray.serve.api.Client(controller: ray.actor.ActorHandle, controller_name: str, detached: bool = False)[source]
shutdown() → None[source]

Completely shut down the connected Serve instance.

Shuts down all processes and deletes all state associated with the instance.

create_endpoint(endpoint_name: str, *, backend: str = None, route: Optional[str] = None, methods: List[str] = ['GET']) → None[source]

Create a service endpoint given route_expression.

Parameters

  • endpoint_name (str) – A name to associate to with the endpoint.

  • backend (str, required) – The backend that will serve requests to this endpoint. To change this or split traffic among backends, use serve.set_traffic.

  • route (str, optional) – A string begin with “/”. HTTP server will use the string to match the path.

  • methods (List[str], optional) – The HTTP methods that are valid for this endpoint.

delete_endpoint(endpoint: str) → None[source]

Delete the given endpoint.

Does not delete any associated backends.

list_endpoints() → Dict[str, Dict[str, Any]][source]

Returns a dictionary of all registered endpoints.

The dictionary keys are endpoint names and values are dictionaries of the form: {“methods”: List[str], “traffic”: Dict[str, float]}.

update_backend_config(backend_tag: str, config_options: Union[ray.serve.config.BackendConfig, Dict[str, Any]]) → None[source]

Update a backend configuration for a backend tag.

Keys not specified in the passed will be left unchanged.

Parameters

  • backend_tag (str) – A registered backend.

  • config_options (dict, serve.BackendConfig) – Backend config options to update. Either a BackendConfig object or a dict mapping strings to values for the following supported options: - “num_replicas”: number of worker processes to start up that will handle requests to this backend. - “max_batch_size”: the maximum number of requests that will be processed in one batch by this backend. - “batch_wait_timeout”: time in seconds that backend replicas will wait for a full batch of requests before processing a partial batch. - “max_concurrent_queries”: the maximum number of queries that will be sent to a replica of this backend without receiving a response.

get_backend_config(backend_tag: str) → ray.serve.config.BackendConfig[source]

Get the backend configuration for a backend tag.

Parameters

backend_tag (str) – A registered backend.

create_backend(backend_tag: str, func_or_class: Union[Callable, Type[Callable]], *actor_init_args: Any, ray_actor_options: Optional[Dict] = None, config: Union[ray.serve.config.BackendConfig, Dict[str, Any], None] = None) → None[source]

Create a backend with the provided tag.

The backend will serve requests with func_or_class.

Parameters

  • backend_tag (str) – a unique tag assign to identify this backend.

  • func_or_class (callable, class) – a function or a class implementing __call__.

  • actor_init_args (optional) – the arguments to pass to the class. initialization method.

  • ray_actor_options (optional) – options to be passed into the @ray.remote decorator for the backend actor.

  • config (dict, serve.BackendConfig, optional) – configuration options for this backend. Either a BackendConfig, or a dictionary mapping strings to values for the following supported options: - “num_replicas”: number of worker processes to start up that will handle requests to this backend. - “max_batch_size”: the maximum number of requests that will be processed in one batch by this backend. - “batch_wait_timeout”: time in seconds that backend replicas will wait for a full batch of requests before processing a partial batch. - “max_concurrent_queries”: the maximum number of queries that will be sent to a replica of this backend without receiving a response.

list_backends() → Dict[str, Dict[str, Any]][source]

Returns a dictionary of all registered backends.

Dictionary maps backend tags to backend configs.

delete_backend(backend_tag: str) → None[source]

Delete the given backend.

The backend must not currently be used by any endpoints.

set_traffic(endpoint_name: str, traffic_policy_dictionary: Dict[str, float]) → None[source]

Associate a service endpoint with traffic policy.

Example:

>>> serve.set_traffic("service-name", {
    "backend:v1": 0.5,
    "backend:v2": 0.5
})
Parameters

  • endpoint_name (str) – A registered service endpoint.

  • traffic_policy_dictionary (dict) – a dictionary maps backend names to their traffic weights. The weights must sum to 1.

shadow_traffic(endpoint_name: str, backend_tag: str, proportion: float) → None[source]

Shadow traffic from an endpoint to a backend.

The specified proportion of requests will be duplicated and sent to the backend. Responses of the duplicated traffic will be ignored. The backend must not already be in use.

To stop shadowing traffic to a backend, call shadow_traffic with proportion equal to 0.

Parameters

  • endpoint_name (str) – A registered service endpoint.

  • backend_tag (str) – A registered backend.

  • proportion (float) – The proportion of traffic from 0 to 1.

get_handle(endpoint_name: str) → ray.serve.handle.RayServeHandle[source]

Retrieve RayServeHandle for service endpoint to invoke it from Python.

Parameters

endpoint_name (str) – A registered service endpoint.

Returns

RayServeHandle

Backend Configuration

class ray.serve.BackendConfig[source]

Configuration options for a backend, to be set by the user.

Parameters

  • num_replicas (int, optional) – The number of worker processes to start up that will handle requests to this backend. Defaults to 0.

  • max_batch_size (int, optional) – The maximum number of requests that will be processed in one batch by this backend. Defaults to None (no maximium).

  • batch_wait_timeout (float, optional) – The time in seconds that backend replicas will wait for a full batch of requests before processing a partial batch. Defaults to 0.

  • max_concurrent_queries (int, optional) – The maximum number of queries that will be sent to a replica of this backend without receiving a response. Defaults to None (no maximum).

Handle API

class ray.serve.handle.RayServeHandle(router_handle, endpoint_name, *, method_name=None, shard_key=None, http_method=None, http_headers=None)[source]

A handle to a service endpoint.

Invoking this endpoint with .remote is equivalent to pinging an HTTP endpoint.

Example

>>> handle = serve.get_handle("my_endpoint")
>>> handle
RayServeHandle(
     Endpoint="my_endpoint",
     Traffic=...
)
>>> handle.remote(my_request_content)
ObjectRef(...)
>>> ray.get(handle.remote(...))
# result
>>> ray.get(handle.remote(let_it_crash_request))
# raises RayTaskError Exception
remote(request_data: Union[Dict, Any, None] = None, **kwargs)[source]

Issue an asynchrounous request to the endpoint.

Returns a Ray ObjectRef whose results can be waited for or retrieved using ray.wait or ray.get, respectively.

Returns

ray.ObjectRef

Parameters

  • request_data (dict, Any) – If it’s a dictionary, the data will be available in request.json() or request.form(). Otherwise, it will be available in request.data.

  • **kwargs – All keyword arguments will be available in request.args.

options(method_name: Optional[str] = None, *, shard_key: Optional[str] = None, http_method: Optional[str] = None, http_headers: Optional[Dict[str, str]] = None)[source]

Set options for this handle.

Parameters

  • method_name (str) – The method to invoke on the backend.

  • http_method (str) – The HTTP method to use for the request.

  • shard_key (str) – A string to use to deterministically map this request to a backend if there are multiple for this endpoint.

When calling from Python, the backend implementation will receive ServeRequest objects instead of Flask requests.

class ray.serve.utils.ServeRequest(data, kwargs, headers, method)[source]

The request object used in Python context.

ServeRequest is built to have similar API as Flask.Request. You only need to write your model serving code once; it can be queried by both HTTP and Python.

property headers

The HTTP headers from handle.option(http_headers=...).

property method

The HTTP method data from handle.option(http_method=...).

property args

The keyword arguments from handle.remote(**kwargs).

property json

The request dictionary, from handle.remote(dict).

property form

The request dictionary, from handle.remote(dict).

property data

The request data from handle.remote(obj).

Batching Requests

ray.serve.accept_batch(f: Callable) → Callable[source]

Annotation to mark that a serving function accepts batches of requests.

In order to accept batches of requests as input, the implementation must handle a list of requests being passed in rather than just a single request.

This must be set on any backend implementation that will have max_batch_size set to greater than 1.

Example:

>>> @serve.accept_batch
    def serving_func(requests):
        assert isinstance(requests, list)
        ...

>>> class ServingActor:
        @serve.accept_batch
        def __call__(self, requests):
            assert isinstance(requests, list)
Serve Architecture Tune: Scalable Hyperparameter Tuning