com.databricks.sdk.service.serving

Class ServingEndpointsAPI

java.lang.Object

com.databricks.sdk.service.serving.ServingEndpointsAPI

@Generated
public class ServingEndpointsAPI
extends Object

The Serving Endpoints API allows you to create, update, and delete model serving endpoints.

You can use a serving endpoint to serve models from the Databricks Model Registry or from Unity Catalog. Endpoints expose the underlying models as scalable REST API endpoints using serverless compute. This means the endpoints and associated compute resources are fully managed by Databricks and will not appear in your cloud account. A serving endpoint can consist of one or more MLflow models from the Databricks Model Registry, called served models. A serving endpoint can have at most ten served models. You can configure traffic settings to define how requests should be routed to your served models behind an endpoint. Additionally, you can configure the scale of resources that should be applied to each served model.

Constructor Summary

Constructors

Constructor and Description
ServingEndpointsAPI(ApiClient apiClient) Regular-use constructor
ServingEndpointsAPI(ServingEndpointsService mock) Constructor for mocks

Method Summary

Modifier and Type	Method and Description
BuildLogsResponse	buildLogs(BuildLogsRequest request) Retrieve the logs associated with building the model's environment for a given serving endpoint's served model.
BuildLogsResponse	buildLogs(String name, String servedModelName)
Wait<ServingEndpointDetailed,ServingEndpointDetailed>	create(CreateServingEndpoint request) Create a new serving endpoint.
Wait<ServingEndpointDetailed,ServingEndpointDetailed>	create(String name, EndpointCoreConfigInput config)
void	delete(DeleteServingEndpointRequest request) Delete a serving endpoint.
void	delete(String name)
void	exportMetrics(ExportMetricsRequest request) Retrieve the metrics associated with a serving endpoint.
void	exportMetrics(String name)
ServingEndpointDetailed	get(GetServingEndpointRequest request) Get a single serving endpoint.
ServingEndpointDetailed	get(String name)
GetServingEndpointPermissionLevelsResponse	getPermissionLevels(GetServingEndpointPermissionLevelsRequest request) Get serving endpoint permission levels.
GetServingEndpointPermissionLevelsResponse	getPermissionLevels(String servingEndpointId)
ServingEndpointPermissions	getPermissions(GetServingEndpointPermissionsRequest request) Get serving endpoint permissions.
ServingEndpointPermissions	getPermissions(String servingEndpointId)
ServingEndpointsService	impl()
Iterable<ServingEndpoint>	list() Retrieve all serving endpoints.
ServerLogsResponse	logs(LogsRequest request) Retrieve the most recent log lines associated with a given serving endpoint's served model.
ServerLogsResponse	logs(String name, String servedModelName)
Iterable<EndpointTag>	patch(PatchServingEndpointTags request) Patch the tags of a serving endpoint.
Iterable<EndpointTag>	patch(String name)
QueryEndpointResponse	query(QueryEndpointInput request) Query a serving endpoint with provided model input.
QueryEndpointResponse	query(String name)
ServingEndpointPermissions	setPermissions(ServingEndpointPermissionsRequest request) Set serving endpoint permissions.
ServingEndpointPermissions	setPermissions(String servingEndpointId)
Wait<ServingEndpointDetailed,ServingEndpointDetailed>	updateConfig(EndpointCoreConfigInput request) Update a serving endpoint with a new config.
Wait<ServingEndpointDetailed,ServingEndpointDetailed>	updateConfig(String name, Collection<ServedModelInput> servedModels)
ServingEndpointPermissions	updatePermissions(ServingEndpointPermissionsRequest request) Update serving endpoint permissions.
ServingEndpointPermissions	updatePermissions(String servingEndpointId)
ServingEndpointDetailed	waitGetServingEndpointNotUpdating(String name)
ServingEndpointDetailed	waitGetServingEndpointNotUpdating(String name, Duration timeout, Consumer<ServingEndpointDetailed> callback)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

ServingEndpointsAPI

public ServingEndpointsAPI(ApiClient apiClient)

Regular-use constructor

ServingEndpointsAPI

public ServingEndpointsAPI(ServingEndpointsService mock)

Constructor for mocks

Method Detail

waitGetServingEndpointNotUpdating

public ServingEndpointDetailed waitGetServingEndpointNotUpdating(String name)
                                                          throws TimeoutException

Throws:

TimeoutException

waitGetServingEndpointNotUpdating

public ServingEndpointDetailed waitGetServingEndpointNotUpdating(String name,
                                                                 Duration timeout,
                                                                 Consumer<ServingEndpointDetailed> callback)
                                                          throws TimeoutException

Throws:

TimeoutException

buildLogs

public BuildLogsResponse buildLogs(String name,
                                   String servedModelName)

buildLogs

public BuildLogsResponse buildLogs(BuildLogsRequest request)

Retrieve the logs associated with building the model's environment for a given serving endpoint's served model.

Retrieves the build logs associated with the provided served model.

create

public Wait<ServingEndpointDetailed,ServingEndpointDetailed> create(String name,
                                                                    EndpointCoreConfigInput config)

create

public Wait<ServingEndpointDetailed,ServingEndpointDetailed> create(CreateServingEndpoint request)

Create a new serving endpoint.

delete

public void delete(String name)

delete

public void delete(DeleteServingEndpointRequest request)

Delete a serving endpoint.

exportMetrics

public void exportMetrics(String name)

exportMetrics

public void exportMetrics(ExportMetricsRequest request)

Retrieve the metrics associated with a serving endpoint.

Retrieves the metrics associated with the provided serving endpoint in either Prometheus or OpenMetrics exposition format.

get

public ServingEndpointDetailed get(String name)

get

public ServingEndpointDetailed get(GetServingEndpointRequest request)

Get a single serving endpoint.

Retrieves the details for a single serving endpoint.

getPermissionLevels

public GetServingEndpointPermissionLevelsResponse getPermissionLevels(String servingEndpointId)

getPermissionLevels

public GetServingEndpointPermissionLevelsResponse getPermissionLevels(GetServingEndpointPermissionLevelsRequest request)

Get serving endpoint permission levels.

Gets the permission levels that a user can have on an object.

getPermissions

public ServingEndpointPermissions getPermissions(String servingEndpointId)

getPermissions

public ServingEndpointPermissions getPermissions(GetServingEndpointPermissionsRequest request)

Get serving endpoint permissions.

Gets the permissions of a serving endpoint. Serving endpoints can inherit permissions from their root object.

list

public Iterable<ServingEndpoint> list()

Retrieve all serving endpoints.

logs

public ServerLogsResponse logs(String name,
                               String servedModelName)

logs

public ServerLogsResponse logs(LogsRequest request)

Retrieve the most recent log lines associated with a given serving endpoint's served model.

Retrieves the service logs associated with the provided served model.

patch

public Iterable<EndpointTag> patch(String name)

patch

public Iterable<EndpointTag> patch(PatchServingEndpointTags request)

Patch the tags of a serving endpoint.

Used to batch add and delete tags from a serving endpoint with a single API call.

query

public QueryEndpointResponse query(String name)

query

public QueryEndpointResponse query(QueryEndpointInput request)

Query a serving endpoint with provided model input.

setPermissions

public ServingEndpointPermissions setPermissions(String servingEndpointId)

setPermissions

public ServingEndpointPermissions setPermissions(ServingEndpointPermissionsRequest request)

Set serving endpoint permissions.

Sets permissions on a serving endpoint. Serving endpoints can inherit permissions from their root object.

updateConfig

public Wait<ServingEndpointDetailed,ServingEndpointDetailed> updateConfig(String name,
                                                                          Collection<ServedModelInput> servedModels)

updateConfig

public Wait<ServingEndpointDetailed,ServingEndpointDetailed> updateConfig(EndpointCoreConfigInput request)

Update a serving endpoint with a new config.

Updates any combination of the serving endpoint's served models, the compute configuration of those served models, and the endpoint's traffic config. An endpoint that already has an update in progress can not be updated until the current update completes or fails.

updatePermissions

public ServingEndpointPermissions updatePermissions(String servingEndpointId)

updatePermissions

public ServingEndpointPermissions updatePermissions(ServingEndpointPermissionsRequest request)

Update serving endpoint permissions.

Updates the permissions on a serving endpoint. Serving endpoints can inherit permissions from their root object.

impl

public ServingEndpointsService impl()