Package com.databricks.sdk.service.serving

Interface Summary

Interface	Description
ServingEndpointsDataPlaneService	Serving endpoints DataPlane provides a set of operations to interact with data plane endpoints for Serving endpoints service.
ServingEndpointsService	The Serving Endpoints API allows you to create, update, and delete model serving endpoints.

Class Summary

Class	Description
Ai21LabsConfig
AiGatewayConfig
AiGatewayGuardrailParameters
AiGatewayGuardrailPiiBehavior
AiGatewayGuardrails
AiGatewayInferenceTableConfig
AiGatewayRateLimit
AiGatewayUsageTrackingConfig
AmazonBedrockConfig
AnthropicConfig
ApiKeyAuth
AutoCaptureConfigInput
AutoCaptureConfigOutput
AutoCaptureState
BearerTokenAuth
BuildLogsRequest
BuildLogsResponse
ChatMessage
CohereConfig
CreatePtEndpointRequest
CreateServingEndpoint
CustomProviderConfig	Configs needed to create a custom provider model route.
DatabricksModelServingConfig
DataframeSplitInput
DataPlaneInfo	Details necessary to query this object's API through the DataPlane APIs.
DeleteServingEndpointRequest
EmailNotifications
EmbeddingsV1ResponseEmbeddingElement
EndpointCoreConfigInput
EndpointCoreConfigOutput
EndpointCoreConfigSummary
EndpointPendingConfig
EndpointState
EndpointTag
EndpointTags
ExportMetricsRequest
ExportMetricsResponse
ExternalFunctionRequest	Simple Proto message for testing
ExternalModel
ExternalModelUsageElement
FallbackConfig
FoundationModel	All fields are not sensitive as they are hard-coded in the system and made available to customers.
GetOpenApiRequest
GetOpenApiResponse
GetServingEndpointPermissionLevelsRequest
GetServingEndpointPermissionLevelsResponse
GetServingEndpointPermissionsRequest
GetServingEndpointRequest
GoogleCloudVertexAiConfig
HttpRequestResponse
ListEndpointsResponse
LogsRequest
ModelDataPlaneInfo	A representation of all DataPlaneInfo for operations that can be done on a model through Data Plane APIs.
OpenAiConfig	Configs needed to create an OpenAI model route.
PaLmConfig
PatchServingEndpointTags
PayloadTable
PtEndpointCoreConfig
PtServedModel
PutAiGatewayRequest
PutAiGatewayResponse
PutRequest
PutResponse
QueryEndpointInput
QueryEndpointResponse
RateLimit
Route
ServedEntityInput
ServedEntityOutput
ServedEntitySpec
ServedModelInput
ServedModelOutput
ServedModelSpec
ServedModelState
ServerLogsResponse
ServingEndpoint
ServingEndpointAccessControlRequest
ServingEndpointAccessControlResponse
ServingEndpointDetailed
ServingEndpointPermission
ServingEndpointPermissions
ServingEndpointPermissionsDescription
ServingEndpointPermissionsRequest
ServingEndpointsAPI	The Serving Endpoints API allows you to create, update, and delete model serving endpoints.
ServingEndpointsDataPlaneAPI	Serving endpoints DataPlane provides a set of operations to interact with data plane endpoints for Serving endpoints service.
TrafficConfig
UpdateProvisionedThroughputEndpointConfigRequest
V1ResponseChoiceElement

Enum Summary

Enum	Description
AiGatewayGuardrailPiiBehaviorBehavior
AiGatewayRateLimitKey
AiGatewayRateLimitRenewalPeriod
AmazonBedrockConfigBedrockProvider
ChatMessageRole	The role of the message.
EmbeddingsV1ResponseEmbeddingElementObject	This will always be 'embedding'.
EndpointStateConfigUpdate
EndpointStateReady
ExternalFunctionRequestHttpMethod
ExternalModelProvider
QueryEndpointResponseObject	The type of object returned by the __external/foundation model__ serving endpoint, one of [text_completion, chat.completion, list (of embeddings)].
RateLimitKey
RateLimitRenewalPeriod
ServedModelInputWorkloadType	Please keep this in sync with with workload types in InferenceEndpointEntities.scala
ServedModelStateDeployment
ServingEndpointDetailedPermissionLevel
ServingEndpointPermissionLevel	Permission level
ServingModelWorkloadType	Please keep this in sync with with workload types in InferenceEndpointEntities.scala