serving

package
v0.29.0 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Jan 10, 2024 License: Apache-2.0 Imports: 9 Imported by: 6

Documentation

Overview

These APIs allow you to manage Apps, Serving Endpoints, etc.

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

This section is empty.

Types

type Ai21LabsConfig added in v0.27.0 

type Ai21LabsConfig struct {
	// The Databricks secret key reference for an AI21Labs API key.
	Ai21labsApiKey string `json:"ai21labs_api_key"`
}

type AnthropicConfig added in v0.27.0 

type AnthropicConfig struct {
	// The Databricks secret key reference for an Anthropic API key.
	AnthropicApiKey string `json:"anthropic_api_key"`
}

type AppEvents added in v0.25.0 

type AppEvents struct {
	EventName string `json:"event_name,omitempty"`

	EventTime string `json:"event_time,omitempty"`

	EventType string `json:"event_type,omitempty"`

	Message string `json:"message,omitempty"`

	ServiceName string `json:"service_name,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (AppEvents) MarshalJSON added in v0.25.0 

func (s AppEvents) MarshalJSON() ([]byte, error)

func (*AppEvents) UnmarshalJSON added in v0.25.0 

func (s *AppEvents) UnmarshalJSON(b []byte) error

type AppManifest added in v0.24.0 

type AppManifest struct {
	// Workspace dependencies.
	Dependencies []any `json:"dependencies,omitempty"`
	// application description
	Description string `json:"description,omitempty"`
	// Ingress rules for app public endpoints
	Ingress any `json:"ingress,omitempty"`
	// Only a-z and dashes (-). Max length of 30.
	Name string `json:"name,omitempty"`
	// Container private registry
	Registry any `json:"registry,omitempty"`
	// list of app services. Restricted to one for now.
	Services any `json:"services,omitempty"`
	// The manifest format version. Must be set to 1.
	Version any `json:"version,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (AppManifest) MarshalJSON added in v0.24.0 

func (s AppManifest) MarshalJSON() ([]byte, error)

func (*AppManifest) UnmarshalJSON added in v0.24.0 

func (s *AppManifest) UnmarshalJSON(b []byte) error

type AppServiceStatus added in v0.25.0 

type AppServiceStatus struct {
	Deployment any `json:"deployment,omitempty"`

	Name string `json:"name,omitempty"`

	Template any `json:"template,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (AppServiceStatus) MarshalJSON added in v0.25.0 

func (s AppServiceStatus) MarshalJSON() ([]byte, error)

func (*AppServiceStatus) UnmarshalJSON added in v0.25.0 

func (s *AppServiceStatus) UnmarshalJSON(b []byte) error

type AppsAPI added in v0.24.0 

type AppsAPI struct {
	// contains filtered or unexported fields
}

Lakehouse Apps run directly on a customer’s Databricks instance, integrate with their data, use and extend Databricks services, and enable users to interact through single sign-on.

func NewApps added in v0.24.0 

func NewApps(client *client.DatabricksClient) *AppsAPI

func (*AppsAPI) Create added in v0.24.0 

func (a *AppsAPI) Create(ctx context.Context, request DeployAppRequest) (*DeploymentStatus, error)

Create and deploy an application.

Creates and deploys an application.

func (*AppsAPI) DeleteApp added in v0.25.0 

func (a *AppsAPI) DeleteApp(ctx context.Context, request DeleteAppRequest) (*DeleteAppResponse, error)

Delete an application.

Delete an application definition

func (*AppsAPI) DeleteAppByName added in v0.25.0 

func (a *AppsAPI) DeleteAppByName(ctx context.Context, name string) (*DeleteAppResponse, error)

Delete an application.

Delete an application definition

func (*AppsAPI) GetApp added in v0.25.0 

func (a *AppsAPI) GetApp(ctx context.Context, request GetAppRequest) (*GetAppResponse, error)

Get definition for an application.

Get an application definition

func (*AppsAPI) GetAppByName added in v0.25.0 

func (a *AppsAPI) GetAppByName(ctx context.Context, name string) (*GetAppResponse, error)

Get definition for an application.

Get an application definition

func (*AppsAPI) GetAppDeploymentStatus added in v0.25.0 

func (a *AppsAPI) GetAppDeploymentStatus(ctx context.Context, request GetAppDeploymentStatusRequest) (*DeploymentStatus, error)

Get deployment status for an application.

Get deployment status for an application

func (*AppsAPI) GetAppDeploymentStatusByDeploymentId added in v0.25.0 

func (a *AppsAPI) GetAppDeploymentStatusByDeploymentId(ctx context.Context, deploymentId string) (*DeploymentStatus, error)

Get deployment status for an application.

Get deployment status for an application

func (*AppsAPI) GetApps added in v0.25.0 

func (a *AppsAPI) GetApps(ctx context.Context) (*ListAppsResponse, error)

List all applications.

List all available applications

func (*AppsAPI) GetEvents added in v0.25.0 

func (a *AppsAPI) GetEvents(ctx context.Context, request GetEventsRequest) (*ListAppEventsResponse, error)

Get deployment events for an application.

Get deployment events for an application

func (*AppsAPI) GetEventsByName added in v0.25.0 

func (a *AppsAPI) GetEventsByName(ctx context.Context, name string) (*ListAppEventsResponse, error)

Get deployment events for an application.

Get deployment events for an application

func (*AppsAPI) Impl added in v0.24.0 

func (a *AppsAPI) Impl() AppsService

Impl returns low-level Apps API implementation Deprecated: use MockAppsInterface instead.

func (*AppsAPI) WithImpl added in v0.24.0 

func (a *AppsAPI) WithImpl(impl AppsService) AppsInterface

WithImpl could be used to override low-level API implementations for unit testing purposes with github.com/golang/mock or other mocking frameworks. Deprecated: use MockAppsInterface instead.

type AppsInterface added in v0.29.0 

type AppsInterface interface {
	// WithImpl could be used to override low-level API implementations for unit
	// testing purposes with [github.com/golang/mock] or other mocking frameworks.
	// Deprecated: use MockAppsInterface instead.
	WithImpl(impl AppsService) AppsInterface

	// Impl returns low-level Apps API implementation
	// Deprecated: use MockAppsInterface instead.
	Impl() AppsService

	// Create and deploy an application.
	//
	// Creates and deploys an application.
	Create(ctx context.Context, request DeployAppRequest) (*DeploymentStatus, error)

	// Delete an application.
	//
	// Delete an application definition
	DeleteApp(ctx context.Context, request DeleteAppRequest) (*DeleteAppResponse, error)

	// Delete an application.
	//
	// Delete an application definition
	DeleteAppByName(ctx context.Context, name string) (*DeleteAppResponse, error)

	// Get definition for an application.
	//
	// Get an application definition
	GetApp(ctx context.Context, request GetAppRequest) (*GetAppResponse, error)

	// Get definition for an application.
	//
	// Get an application definition
	GetAppByName(ctx context.Context, name string) (*GetAppResponse, error)

	// Get deployment status for an application.
	//
	// Get deployment status for an application
	GetAppDeploymentStatus(ctx context.Context, request GetAppDeploymentStatusRequest) (*DeploymentStatus, error)

	// Get deployment status for an application.
	//
	// Get deployment status for an application
	GetAppDeploymentStatusByDeploymentId(ctx context.Context, deploymentId string) (*DeploymentStatus, error)

	// List all applications.
	//
	// List all available applications
	GetApps(ctx context.Context) (*ListAppsResponse, error)

	// Get deployment events for an application.
	//
	// Get deployment events for an application
	GetEvents(ctx context.Context, request GetEventsRequest) (*ListAppEventsResponse, error)

	// Get deployment events for an application.
	//
	// Get deployment events for an application
	GetEventsByName(ctx context.Context, name string) (*ListAppEventsResponse, error)
}

type AppsService added in v0.24.0 

type AppsService interface {

	// Create and deploy an application.
	//
	// Creates and deploys an application.
	Create(ctx context.Context, request DeployAppRequest) (*DeploymentStatus, error)

	// Delete an application.
	//
	// Delete an application definition
	DeleteApp(ctx context.Context, request DeleteAppRequest) (*DeleteAppResponse, error)

	// Get definition for an application.
	//
	// Get an application definition
	GetApp(ctx context.Context, request GetAppRequest) (*GetAppResponse, error)

	// Get deployment status for an application.
	//
	// Get deployment status for an application
	GetAppDeploymentStatus(ctx context.Context, request GetAppDeploymentStatusRequest) (*DeploymentStatus, error)

	// List all applications.
	//
	// List all available applications
	GetApps(ctx context.Context) (*ListAppsResponse, error)

	// Get deployment events for an application.
	//
	// Get deployment events for an application
	GetEvents(ctx context.Context, request GetEventsRequest) (*ListAppEventsResponse, error)
}

Lakehouse Apps run directly on a customer’s Databricks instance, integrate with their data, use and extend Databricks services, and enable users to interact through single sign-on.

type AutoCaptureConfigInput added in v0.27.0 

type AutoCaptureConfigInput struct {
	// The name of the catalog in Unity Catalog. NOTE: On update, you cannot
	// change the catalog name if it was already set.
	CatalogName string `json:"catalog_name,omitempty"`
	// If inference tables are enabled or not. NOTE: If you have already
	// disabled payload logging once, you cannot enable again.
	Enabled bool `json:"enabled,omitempty"`
	// The name of the schema in Unity Catalog. NOTE: On update, you cannot
	// change the schema name if it was already set.
	SchemaName string `json:"schema_name,omitempty"`
	// The prefix of the table in Unity Catalog. NOTE: On update, you cannot
	// change the prefix name if it was already set.
	TableNamePrefix string `json:"table_name_prefix,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (AutoCaptureConfigInput) MarshalJSON added in v0.27.0 

func (s AutoCaptureConfigInput) MarshalJSON() ([]byte, error)

func (*AutoCaptureConfigInput) UnmarshalJSON added in v0.27.0 

func (s *AutoCaptureConfigInput) UnmarshalJSON(b []byte) error

type AutoCaptureConfigOutput added in v0.27.0 

type AutoCaptureConfigOutput struct {
	// The name of the catalog in Unity Catalog.
	CatalogName string `json:"catalog_name,omitempty"`
	// If inference tables are enabled or not.
	Enabled bool `json:"enabled,omitempty"`
	// The name of the schema in Unity Catalog.
	SchemaName string `json:"schema_name,omitempty"`

	State *AutoCaptureState `json:"state,omitempty"`
	// The prefix of the table in Unity Catalog.
	TableNamePrefix string `json:"table_name_prefix,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (AutoCaptureConfigOutput) MarshalJSON added in v0.27.0 

func (s AutoCaptureConfigOutput) MarshalJSON() ([]byte, error)

func (*AutoCaptureConfigOutput) UnmarshalJSON added in v0.27.0 

func (s *AutoCaptureConfigOutput) UnmarshalJSON(b []byte) error

type AutoCaptureState added in v0.27.0 

type AutoCaptureState struct {
	PayloadTable *PayloadTable `json:"payload_table,omitempty"`
}

type AwsBedrockConfig added in v0.27.0 

type AwsBedrockConfig struct {
	// The Databricks secret key reference for an AWS Access Key ID with
	// permissions to interact with Bedrock services.
	AwsAccessKeyId string `json:"aws_access_key_id"`
	// The AWS region to use. Bedrock has to be enabled there.
	AwsRegion string `json:"aws_region"`
	// The Databricks secret key reference for an AWS Secret Access Key paired
	// with the access key ID, with permissions to interact with Bedrock
	// services.
	AwsSecretAccessKey string `json:"aws_secret_access_key"`
	// The underlying provider in AWS Bedrock. Supported values (case
	// insensitive) include: Anthropic, Cohere, AI21Labs, Amazon.
	BedrockProvider AwsBedrockConfigBedrockProvider `json:"bedrock_provider"`
}

type AwsBedrockConfigBedrockProvider added in v0.27.0 

type AwsBedrockConfigBedrockProvider string

The underlying provider in AWS Bedrock. Supported values (case insensitive) include: Anthropic, Cohere, AI21Labs, Amazon. 

const AwsBedrockConfigBedrockProviderAi21labs AwsBedrockConfigBedrockProvider = `ai21labs`
const AwsBedrockConfigBedrockProviderAmazon AwsBedrockConfigBedrockProvider = `amazon`
const AwsBedrockConfigBedrockProviderAnthropic AwsBedrockConfigBedrockProvider = `anthropic`
const AwsBedrockConfigBedrockProviderCohere AwsBedrockConfigBedrockProvider = `cohere`

func (*AwsBedrockConfigBedrockProvider) Set added in v0.27.0 

func (f *AwsBedrockConfigBedrockProvider) Set(v string) error

Set raw string value and validate it against allowed values

func (*AwsBedrockConfigBedrockProvider) String added in v0.27.0 

func (f *AwsBedrockConfigBedrockProvider) String() string

String representation for fmt.Print

func (*AwsBedrockConfigBedrockProvider) Type added in v0.27.0 

func (f *AwsBedrockConfigBedrockProvider) Type() string

Type always returns AwsBedrockConfigBedrockProvider to satisfy [pflag.Value] interface

type BuildLogsRequest 

type BuildLogsRequest struct {
	// The name of the serving endpoint that the served model belongs to. This
	// field is required.
	Name string `json:"-" url:"-"`
	// The name of the served model that build logs will be retrieved for. This
	// field is required.
	ServedModelName string `json:"-" url:"-"`
}

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

type BuildLogsResponse 

type BuildLogsResponse struct {
	// The logs associated with building the served entity's environment.
	Logs string `json:"logs"`
}

type ChatMessage added in v0.27.0 

type ChatMessage struct {
	// The content of the message.
	Content string `json:"content,omitempty"`
	// The role of the message. One of [system, user, assistant].
	Role ChatMessageRole `json:"role,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ChatMessage) MarshalJSON added in v0.27.0 

func (s ChatMessage) MarshalJSON() ([]byte, error)

func (*ChatMessage) UnmarshalJSON added in v0.27.0 

func (s *ChatMessage) UnmarshalJSON(b []byte) error

type ChatMessageRole added in v0.27.0 

type ChatMessageRole string

The role of the message. One of [system, user, assistant]. 

const ChatMessageRoleAssistant ChatMessageRole = `assistant`
const ChatMessageRoleSystem ChatMessageRole = `system`
const ChatMessageRoleUser ChatMessageRole = `user`

func (*ChatMessageRole) Set added in v0.27.0 

func (f *ChatMessageRole) Set(v string) error

Set raw string value and validate it against allowed values

func (*ChatMessageRole) String added in v0.27.0 

func (f *ChatMessageRole) String() string

String representation for fmt.Print

func (*ChatMessageRole) Type added in v0.27.0 

func (f *ChatMessageRole) Type() string

Type always returns ChatMessageRole to satisfy [pflag.Value] interface

type CohereConfig added in v0.27.0 

type CohereConfig struct {
	// The Databricks secret key reference for a Cohere API key.
	CohereApiKey string `json:"cohere_api_key"`
}

type CreateServingEndpoint 

type CreateServingEndpoint struct {
	// The core config of the serving endpoint.
	Config EndpointCoreConfigInput `json:"config"`
	// The name of the serving endpoint. This field is required and must be
	// unique across a Databricks workspace. An endpoint name can consist of
	// alphanumeric characters, dashes, and underscores.
	Name string `json:"name"`
	// Rate limits to be applied to the serving endpoint. NOTE: only external
	// and foundation model endpoints are supported as of now.
	RateLimits []RateLimit `json:"rate_limits,omitempty"`
	// Tags to be attached to the serving endpoint and automatically propagated
	// to billing logs.
	Tags []EndpointTag `json:"tags,omitempty"`
}

type DatabricksModelServingConfig added in v0.27.0 

type DatabricksModelServingConfig struct {
	// The Databricks secret key reference for a Databricks API token that
	// corresponds to a user or service principal with Can Query access to the
	// model serving endpoint pointed to by this external model.
	DatabricksApiToken string `json:"databricks_api_token"`
	// The URL of the Databricks workspace containing the model serving endpoint
	// pointed to by this external model.
	DatabricksWorkspaceUrl string `json:"databricks_workspace_url"`
}

type DataframeSplitInput added in v0.21.0 

type DataframeSplitInput struct {
	Columns []any `json:"columns,omitempty"`

	Data []any `json:"data,omitempty"`

	Index []int `json:"index,omitempty"`
}

type DeleteAppRequest added in v0.24.0 

type DeleteAppRequest struct {
	// The name of an application. This field is required.
	Name string `json:"-" url:"-"`
}

Delete an application

type DeleteAppResponse added in v0.25.0 

type DeleteAppResponse struct {
	Name string `json:"name,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (DeleteAppResponse) MarshalJSON added in v0.25.0 

func (s DeleteAppResponse) MarshalJSON() ([]byte, error)

func (*DeleteAppResponse) UnmarshalJSON added in v0.25.0 

func (s *DeleteAppResponse) UnmarshalJSON(b []byte) error

type DeleteServingEndpointRequest 

type DeleteServingEndpointRequest struct {
	// The name of the serving endpoint. This field is required.
	Name string `json:"-" url:"-"`
}

Delete a serving endpoint

type DeployAppRequest added in v0.24.0 

type DeployAppRequest struct {
	// Manifest that specifies the application requirements
	Manifest AppManifest `json:"manifest"`
	// Information passed at app deployment time to fulfill app dependencies
	Resources any `json:"resources,omitempty"`
}

type DeploymentStatus added in v0.24.0 

type DeploymentStatus struct {
	// Container logs.
	ContainerLogs []any `json:"container_logs,omitempty"`
	// description
	DeploymentId string `json:"deployment_id,omitempty"`
	// Supplementary information about pod
	ExtraInfo string `json:"extra_info,omitempty"`
	// State: one of DEPLOYING,SUCCESS, FAILURE, DEPLOYMENT_STATE_UNSPECIFIED
	State DeploymentStatusState `json:"state,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (DeploymentStatus) MarshalJSON added in v0.24.0 

func (s DeploymentStatus) MarshalJSON() ([]byte, error)

func (*DeploymentStatus) UnmarshalJSON added in v0.24.0 

func (s *DeploymentStatus) UnmarshalJSON(b []byte) error

type DeploymentStatusState added in v0.24.0 

type DeploymentStatusState string

State: one of DEPLOYING,SUCCESS, FAILURE, DEPLOYMENT_STATE_UNSPECIFIED 

const DeploymentStatusStateDeploying DeploymentStatusState = `DEPLOYING`
const DeploymentStatusStateDeploymentStateUnspecified DeploymentStatusState = `DEPLOYMENT_STATE_UNSPECIFIED`
const DeploymentStatusStateFailure DeploymentStatusState = `FAILURE`
const DeploymentStatusStateSuccess DeploymentStatusState = `SUCCESS`

func (*DeploymentStatusState) Set added in v0.24.0 

func (f *DeploymentStatusState) Set(v string) error

Set raw string value and validate it against allowed values

func (*DeploymentStatusState) String added in v0.24.0 

func (f *DeploymentStatusState) String() string

String representation for fmt.Print

func (*DeploymentStatusState) Type added in v0.24.0 

func (f *DeploymentStatusState) Type() string

Type always returns DeploymentStatusState to satisfy [pflag.Value] interface

type EmbeddingsV1ResponseEmbeddingElement added in v0.27.0 

type EmbeddingsV1ResponseEmbeddingElement struct {
	Embedding []float64 `json:"embedding,omitempty"`
	// The index of the embedding in the response.
	Index int `json:"index,omitempty"`
	// This will always be 'embedding'.
	Object EmbeddingsV1ResponseEmbeddingElementObject `json:"object,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (EmbeddingsV1ResponseEmbeddingElement) MarshalJSON added in v0.27.0 

func (s EmbeddingsV1ResponseEmbeddingElement) MarshalJSON() ([]byte, error)

func (*EmbeddingsV1ResponseEmbeddingElement) UnmarshalJSON added in v0.27.0 

func (s *EmbeddingsV1ResponseEmbeddingElement) UnmarshalJSON(b []byte) error

type EmbeddingsV1ResponseEmbeddingElementObject added in v0.27.0 

type EmbeddingsV1ResponseEmbeddingElementObject string

This will always be 'embedding'. 

const EmbeddingsV1ResponseEmbeddingElementObjectEmbedding EmbeddingsV1ResponseEmbeddingElementObject = `embedding`

func (*EmbeddingsV1ResponseEmbeddingElementObject) Set added in v0.27.0 

func (f *EmbeddingsV1ResponseEmbeddingElementObject) Set(v string) error

Set raw string value and validate it against allowed values

func (*EmbeddingsV1ResponseEmbeddingElementObject) String added in v0.27.0 

func (f *EmbeddingsV1ResponseEmbeddingElementObject) String() string

String representation for fmt.Print

func (*EmbeddingsV1ResponseEmbeddingElementObject) Type added in v0.27.0 

func (f *EmbeddingsV1ResponseEmbeddingElementObject) Type() string

Type always returns EmbeddingsV1ResponseEmbeddingElementObject to satisfy [pflag.Value] interface

type EndpointCoreConfigInput 

type EndpointCoreConfigInput struct {
	// Configuration for Inference Tables which automatically logs requests and
	// responses to Unity Catalog.
	AutoCaptureConfig *AutoCaptureConfigInput `json:"auto_capture_config,omitempty"`
	// The name of the serving endpoint to update. This field is required.
	Name string `json:"-" url:"-"`
	// A list of served entities for the endpoint to serve. A serving endpoint
	// can have up to 10 served entities.
	ServedEntities []ServedEntityInput `json:"served_entities,omitempty"`
	// (Deprecated, use served_entities instead) A list of served models for the
	// endpoint to serve. A serving endpoint can have up to 10 served models.
	ServedModels []ServedModelInput `json:"served_models,omitempty"`
	// The traffic config defining how invocations to the serving endpoint
	// should be routed.
	TrafficConfig *TrafficConfig `json:"traffic_config,omitempty"`
}

type EndpointCoreConfigOutput 

type EndpointCoreConfigOutput struct {
	// Configuration for Inference Tables which automatically logs requests and
	// responses to Unity Catalog.
	AutoCaptureConfig *AutoCaptureConfigOutput `json:"auto_capture_config,omitempty"`
	// The config version that the serving endpoint is currently serving.
	ConfigVersion int `json:"config_version,omitempty"`
	// The list of served entities under the serving endpoint config.
	ServedEntities []ServedEntityOutput `json:"served_entities,omitempty"`
	// (Deprecated, use served_entities instead) The list of served models under
	// the serving endpoint config.
	ServedModels []ServedModelOutput `json:"served_models,omitempty"`
	// The traffic configuration associated with the serving endpoint config.
	TrafficConfig *TrafficConfig `json:"traffic_config,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (EndpointCoreConfigOutput) MarshalJSON added in v0.23.0 

func (s EndpointCoreConfigOutput) MarshalJSON() ([]byte, error)

func (*EndpointCoreConfigOutput) UnmarshalJSON added in v0.23.0 

func (s *EndpointCoreConfigOutput) UnmarshalJSON(b []byte) error

type EndpointCoreConfigSummary 

type EndpointCoreConfigSummary struct {
	// The list of served entities under the serving endpoint config.
	ServedEntities []ServedEntitySpec `json:"served_entities,omitempty"`
	// (Deprecated, use served_entities instead) The list of served models under
	// the serving endpoint config.
	ServedModels []ServedModelSpec `json:"served_models,omitempty"`
}

type EndpointPendingConfig 

type EndpointPendingConfig struct {
	// The config version that the serving endpoint is currently serving.
	ConfigVersion int `json:"config_version,omitempty"`
	// The list of served entities belonging to the last issued update to the
	// serving endpoint.
	ServedEntities []ServedEntityOutput `json:"served_entities,omitempty"`
	// (Deprecated, use served_entities instead) The list of served models
	// belonging to the last issued update to the serving endpoint.
	ServedModels []ServedModelOutput `json:"served_models,omitempty"`
	// The timestamp when the update to the pending config started.
	StartTime int64 `json:"start_time,omitempty"`
	// The traffic config defining how invocations to the serving endpoint
	// should be routed.
	TrafficConfig *TrafficConfig `json:"traffic_config,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (EndpointPendingConfig) MarshalJSON added in v0.23.0 

func (s EndpointPendingConfig) MarshalJSON() ([]byte, error)

func (*EndpointPendingConfig) UnmarshalJSON added in v0.23.0 

func (s *EndpointPendingConfig) UnmarshalJSON(b []byte) error

type EndpointState 

type EndpointState struct {
	// The state of an endpoint's config update. This informs the user if the
	// pending_config is in progress, if the update failed, or if there is no
	// update in progress. Note that if the endpoint's config_update state value
	// is IN_PROGRESS, another update can not be made until the update completes
	// or fails."
	ConfigUpdate EndpointStateConfigUpdate `json:"config_update,omitempty"`
	// The state of an endpoint, indicating whether or not the endpoint is
	// queryable. An endpoint is READY if all of the served entities in its
	// active configuration are ready. If any of the actively served entities
	// are in a non-ready state, the endpoint state will be NOT_READY.
	Ready EndpointStateReady `json:"ready,omitempty"`
}

type EndpointStateConfigUpdate 

type EndpointStateConfigUpdate string

The state of an endpoint's config update. This informs the user if the pending_config is in progress, if the update failed, or if there is no update in progress. Note that if the endpoint's config_update state value is IN_PROGRESS, another update can not be made until the update completes or fails." 

const EndpointStateConfigUpdateInProgress EndpointStateConfigUpdate = `IN_PROGRESS`
const EndpointStateConfigUpdateNotUpdating EndpointStateConfigUpdate = `NOT_UPDATING`
const EndpointStateConfigUpdateUpdateFailed EndpointStateConfigUpdate = `UPDATE_FAILED`

func (*EndpointStateConfigUpdate) Set 

func (f *EndpointStateConfigUpdate) Set(v string) error

Set raw string value and validate it against allowed values

func (*EndpointStateConfigUpdate) String 

func (f *EndpointStateConfigUpdate) String() string

String representation for fmt.Print

func (*EndpointStateConfigUpdate) Type 

func (f *EndpointStateConfigUpdate) Type() string

Type always returns EndpointStateConfigUpdate to satisfy [pflag.Value] interface

type EndpointStateReady 

type EndpointStateReady string

The state of an endpoint, indicating whether or not the endpoint is queryable. An endpoint is READY if all of the served entities in its active configuration are ready. If any of the actively served entities are in a non-ready state, the endpoint state will be NOT_READY. 

const EndpointStateReadyNotReady EndpointStateReady = `NOT_READY`
const EndpointStateReadyReady EndpointStateReady = `READY`

func (*EndpointStateReady) Set 

func (f *EndpointStateReady) Set(v string) error

Set raw string value and validate it against allowed values

func (*EndpointStateReady) String 

func (f *EndpointStateReady) String() string

String representation for fmt.Print

func (*EndpointStateReady) Type 

func (f *EndpointStateReady) Type() string

Type always returns EndpointStateReady to satisfy [pflag.Value] interface

type EndpointTag added in v0.20.0 

type EndpointTag struct {
	// Key field for a serving endpoint tag.
	Key string `json:"key"`
	// Optional value field for a serving endpoint tag.
	Value string `json:"value,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (EndpointTag) MarshalJSON added in v0.23.0 

func (s EndpointTag) MarshalJSON() ([]byte, error)

func (*EndpointTag) UnmarshalJSON added in v0.23.0 

func (s *EndpointTag) UnmarshalJSON(b []byte) error

type ExportMetricsRequest 

type ExportMetricsRequest struct {
	// The name of the serving endpoint to retrieve metrics for. This field is
	// required.
	Name string `json:"-" url:"-"`
}

Retrieve the metrics associated with a serving endpoint

type ExternalModel added in v0.27.0 

type ExternalModel struct {
	// The config for the external model, which must match the provider.
	Config ExternalModelConfig `json:"config"`
	// The name of the external model.
	Name string `json:"name"`
	// The name of the provider for the external model. Currently, the supported
	// providers are 'ai21labs', 'anthropic', 'aws-bedrock', 'cohere',
	// 'databricks-model-serving', 'openai', and 'palm'.",
	Provider ExternalModelProvider `json:"provider"`
	// The task type of the external model.
	Task string `json:"task"`
}

type ExternalModelConfig added in v0.27.0 

type ExternalModelConfig struct {
	// AI21Labs Config
	Ai21labsConfig *Ai21LabsConfig `json:"ai21labs_config,omitempty"`
	// Anthropic Config
	AnthropicConfig *AnthropicConfig `json:"anthropic_config,omitempty"`
	// AWS Bedrock Config
	AwsBedrockConfig *AwsBedrockConfig `json:"aws_bedrock_config,omitempty"`
	// Cohere Config
	CohereConfig *CohereConfig `json:"cohere_config,omitempty"`
	// Databricks Model Serving Config
	DatabricksModelServingConfig *DatabricksModelServingConfig `json:"databricks_model_serving_config,omitempty"`
	// OpenAI Config
	OpenaiConfig *OpenAiConfig `json:"openai_config,omitempty"`
	// PaLM Config
	PalmConfig *PaLmConfig `json:"palm_config,omitempty"`
}

type ExternalModelProvider added in v0.27.0 

type ExternalModelProvider string

The name of the provider for the external model. Currently, the supported providers are 'ai21labs', 'anthropic', 'aws-bedrock', 'cohere', 'databricks-model-serving', 'openai', and 'palm'.", 

const ExternalModelProviderAi21labs ExternalModelProvider = `ai21labs`
const ExternalModelProviderAnthropic ExternalModelProvider = `anthropic`
const ExternalModelProviderAwsBedrock ExternalModelProvider = `aws-bedrock`
const ExternalModelProviderCohere ExternalModelProvider = `cohere`
const ExternalModelProviderDatabricksModelServing ExternalModelProvider = `databricks-model-serving`
const ExternalModelProviderOpenai ExternalModelProvider = `openai`
const ExternalModelProviderPalm ExternalModelProvider = `palm`

func (*ExternalModelProvider) Set added in v0.27.0 

func (f *ExternalModelProvider) Set(v string) error

Set raw string value and validate it against allowed values

func (*ExternalModelProvider) String added in v0.27.0 

func (f *ExternalModelProvider) String() string

String representation for fmt.Print

func (*ExternalModelProvider) Type added in v0.27.0 

func (f *ExternalModelProvider) Type() string

Type always returns ExternalModelProvider to satisfy [pflag.Value] interface

type ExternalModelUsageElement added in v0.27.0 

type ExternalModelUsageElement struct {
	// The number of tokens in the chat/completions response.
	CompletionTokens int `json:"completion_tokens,omitempty"`
	// The number of tokens in the prompt.
	PromptTokens int `json:"prompt_tokens,omitempty"`
	// The total number of tokens in the prompt and response.
	TotalTokens int `json:"total_tokens,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ExternalModelUsageElement) MarshalJSON added in v0.27.0 

func (s ExternalModelUsageElement) MarshalJSON() ([]byte, error)

func (*ExternalModelUsageElement) UnmarshalJSON added in v0.27.0 

func (s *ExternalModelUsageElement) UnmarshalJSON(b []byte) error

type FoundationModel added in v0.27.0 

type FoundationModel struct {
	// The description of the foundation model.
	Description string `json:"description,omitempty"`
	// The display name of the foundation model.
	DisplayName string `json:"display_name,omitempty"`
	// The URL to the documentation of the foundation model.
	Docs string `json:"docs,omitempty"`
	// The name of the foundation model.
	Name string `json:"name,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (FoundationModel) MarshalJSON added in v0.27.0 

func (s FoundationModel) MarshalJSON() ([]byte, error)

func (*FoundationModel) UnmarshalJSON added in v0.27.0 

func (s *FoundationModel) UnmarshalJSON(b []byte) error

type GetAppDeploymentStatusRequest added in v0.25.0 

type GetAppDeploymentStatusRequest struct {
	// The deployment id for an application. This field is required.
	DeploymentId string `json:"-" url:"-"`
	// Boolean flag to include application logs
	IncludeAppLog string `json:"-" url:"include_app_log,omitempty"`

	ForceSendFields []string `json:"-"`
}

Get deployment status for an application

func (GetAppDeploymentStatusRequest) MarshalJSON added in v0.25.0 

func (s GetAppDeploymentStatusRequest) MarshalJSON() ([]byte, error)

func (*GetAppDeploymentStatusRequest) UnmarshalJSON added in v0.25.0 

func (s *GetAppDeploymentStatusRequest) UnmarshalJSON(b []byte) error

type GetAppRequest added in v0.24.0 

type GetAppRequest struct {
	// The name of an application. This field is required.
	Name string `json:"-" url:"-"`
}

Get definition for an application

type GetAppResponse added in v0.25.0 

type GetAppResponse struct {
	CurrentServices []AppServiceStatus `json:"current_services,omitempty"`

	Name string `json:"name,omitempty"`

	PendingServices []AppServiceStatus `json:"pending_services,omitempty"`

	Url string `json:"url,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (GetAppResponse) MarshalJSON added in v0.25.0 

func (s GetAppResponse) MarshalJSON() ([]byte, error)

func (*GetAppResponse) UnmarshalJSON added in v0.25.0 

func (s *GetAppResponse) UnmarshalJSON(b []byte) error

type GetEventsRequest added in v0.25.0 

type GetEventsRequest struct {
	// The name of an application. This field is required.
	Name string `json:"-" url:"-"`
}

Get deployment events for an application

type GetServingEndpointPermissionLevelsRequest added in v0.15.0 

type GetServingEndpointPermissionLevelsRequest struct {
	// The serving endpoint for which to get or manage permissions.
	ServingEndpointId string `json:"-" url:"-"`
}

Get serving endpoint permission levels

type GetServingEndpointPermissionLevelsResponse added in v0.15.0 

type GetServingEndpointPermissionLevelsResponse struct {
	// Specific permission levels
	PermissionLevels []ServingEndpointPermissionsDescription `json:"permission_levels,omitempty"`
}

type GetServingEndpointPermissionsRequest added in v0.15.0 

type GetServingEndpointPermissionsRequest struct {
	// The serving endpoint for which to get or manage permissions.
	ServingEndpointId string `json:"-" url:"-"`
}

Get serving endpoint permissions

type GetServingEndpointRequest 

type GetServingEndpointRequest struct {
	// The name of the serving endpoint. This field is required.
	Name string `json:"-" url:"-"`
}

Get a single serving endpoint

type ListAppEventsResponse added in v0.25.0 

type ListAppEventsResponse struct {
	// App events
	Events []AppEvents `json:"events,omitempty"`
}

type ListAppsResponse added in v0.25.0 

type ListAppsResponse struct {
	// Available apps.
	Apps []any `json:"apps,omitempty"`

	NextPageToken string `json:"next_page_token,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ListAppsResponse) MarshalJSON added in v0.25.0 

func (s ListAppsResponse) MarshalJSON() ([]byte, error)

func (*ListAppsResponse) UnmarshalJSON added in v0.25.0 

func (s *ListAppsResponse) UnmarshalJSON(b []byte) error

type ListEndpointsResponse 

type ListEndpointsResponse struct {
	// The list of endpoints.
	Endpoints []ServingEndpoint `json:"endpoints,omitempty"`
}

type LogsRequest 

type LogsRequest struct {
	// The name of the serving endpoint that the served model belongs to. This
	// field is required.
	Name string `json:"-" url:"-"`
	// The name of the served model that logs will be retrieved for. This field
	// is required.
	ServedModelName string `json:"-" url:"-"`
}

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

type OpenAiConfig added in v0.27.0 

type OpenAiConfig struct {
	// This is the base URL for the OpenAI API (default:
	// "https://api.openai.com/v1"). For Azure OpenAI, this field is required,
	// and is the base URL for the Azure OpenAI API service provided by Azure.
	OpenaiApiBase string `json:"openai_api_base,omitempty"`
	// The Databricks secret key reference for an OpenAI or Azure OpenAI API
	// key.
	OpenaiApiKey string `json:"openai_api_key"`
	// This is an optional field to specify the type of OpenAI API to use. For
	// Azure OpenAI, this field is required, and adjust this parameter to
	// represent the preferred security access validation protocol. For access
	// token validation, use azure. For authentication using Azure Active
	// Directory (Azure AD) use, azuread.
	OpenaiApiType string `json:"openai_api_type,omitempty"`
	// This is an optional field to specify the OpenAI API version. For Azure
	// OpenAI, this field is required, and is the version of the Azure OpenAI
	// service to utilize, specified by a date.
	OpenaiApiVersion string `json:"openai_api_version,omitempty"`
	// This field is only required for Azure OpenAI and is the name of the
	// deployment resource for the Azure OpenAI service.
	OpenaiDeploymentName string `json:"openai_deployment_name,omitempty"`
	// This is an optional field to specify the organization in OpenAI or Azure
	// OpenAI.
	OpenaiOrganization string `json:"openai_organization,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (OpenAiConfig) MarshalJSON added in v0.27.0 

func (s OpenAiConfig) MarshalJSON() ([]byte, error)

func (*OpenAiConfig) UnmarshalJSON added in v0.27.0 

func (s *OpenAiConfig) UnmarshalJSON(b []byte) error

type PaLmConfig added in v0.27.0 

type PaLmConfig struct {
	// The Databricks secret key reference for a PaLM API key.
	PalmApiKey string `json:"palm_api_key"`
}

type PatchServingEndpointTags added in v0.20.0 

type PatchServingEndpointTags struct {
	// List of endpoint tags to add
	AddTags []EndpointTag `json:"add_tags,omitempty"`
	// List of tag keys to delete
	DeleteTags []string `json:"delete_tags,omitempty"`
	// The name of the serving endpoint who's tags to patch. This field is
	// required.
	Name string `json:"-" url:"-"`
}

type PayloadTable added in v0.27.0 

type PayloadTable struct {
	// The name of the payload table.
	Name string `json:"name,omitempty"`
	// The status of the payload table.
	Status string `json:"status,omitempty"`
	// The status message of the payload table.
	StatusMessage string `json:"status_message,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (PayloadTable) MarshalJSON added in v0.27.0 

func (s PayloadTable) MarshalJSON() ([]byte, error)

func (*PayloadTable) UnmarshalJSON added in v0.27.0 

func (s *PayloadTable) UnmarshalJSON(b []byte) error

type PutRequest added in v0.27.0 

type PutRequest struct {
	// The name of the serving endpoint whose rate limits are being updated.
	// This field is required.
	Name string `json:"-" url:"-"`
	// The list of endpoint rate limits.
	RateLimits []RateLimit `json:"rate_limits,omitempty"`
}

Update the rate limits of a serving endpoint

type PutResponse added in v0.27.0 

type PutResponse struct {
	// The list of endpoint rate limits.
	RateLimits []RateLimit `json:"rate_limits,omitempty"`
}

type QueryEndpointInput added in v0.21.0 

type QueryEndpointInput struct {
	// Pandas Dataframe input in the records orientation.
	DataframeRecords []any `json:"dataframe_records,omitempty"`
	// Pandas Dataframe input in the split orientation.
	DataframeSplit *DataframeSplitInput `json:"dataframe_split,omitempty"`
	// The extra parameters field used ONLY for __completions, chat,__ and
	// __embeddings external & foundation model__ serving endpoints. This is a
	// map of strings and should only be used with other external/foundation
	// model query fields.
	ExtraParams map[string]string `json:"extra_params,omitempty"`
	// The input string (or array of strings) field used ONLY for __embeddings
	// external & foundation model__ serving endpoints and is the only field
	// (along with extra_params if needed) used by embeddings queries.
	Input any `json:"input,omitempty"`
	// Tensor-based input in columnar format.
	Inputs any `json:"inputs,omitempty"`
	// Tensor-based input in row format.
	Instances []any `json:"instances,omitempty"`
	// The max tokens field used ONLY for __completions__ and __chat external &
	// foundation model__ serving endpoints. This is an integer and should only
	// be used with other chat/completions query fields.
	MaxTokens int `json:"max_tokens,omitempty"`
	// The messages field used ONLY for __chat external & foundation model__
	// serving endpoints. This is a map of strings and should only be used with
	// other chat query fields.
	Messages []ChatMessage `json:"messages,omitempty"`
	// The n (number of candidates) field used ONLY for __completions__ and
	// __chat external & foundation model__ serving endpoints. This is an
	// integer between 1 and 5 with a default of 1 and should only be used with
	// other chat/completions query fields.
	N int `json:"n,omitempty"`
	// The name of the serving endpoint. This field is required.
	Name string `json:"-" url:"-"`
	// The prompt string (or array of strings) field used ONLY for __completions
	// external & foundation model__ serving endpoints and should only be used
	// with other completions query fields.
	Prompt any `json:"prompt,omitempty"`
	// The stop sequences field used ONLY for __completions__ and __chat
	// external & foundation model__ serving endpoints. This is a list of
	// strings and should only be used with other chat/completions query fields.
	Stop []string `json:"stop,omitempty"`
	// The stream field used ONLY for __completions__ and __chat external &
	// foundation model__ serving endpoints. This is a boolean defaulting to
	// false and should only be used with other chat/completions query fields.
	Stream bool `json:"stream,omitempty"`
	// The temperature field used ONLY for __completions__ and __chat external &
	// foundation model__ serving endpoints. This is a float between 0.0 and 2.0
	// with a default of 1.0 and should only be used with other chat/completions
	// query fields.
	Temperature float64 `json:"temperature,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (QueryEndpointInput) MarshalJSON added in v0.27.0 

func (s QueryEndpointInput) MarshalJSON() ([]byte, error)

func (*QueryEndpointInput) UnmarshalJSON added in v0.27.0 

func (s *QueryEndpointInput) UnmarshalJSON(b []byte) error

type QueryEndpointResponse 

type QueryEndpointResponse struct {
	// The list of choices returned by the __chat or completions
	// external/foundation model__ serving endpoint.
	Choices []V1ResponseChoiceElement `json:"choices,omitempty"`
	// The timestamp in seconds when the query was created in Unix time returned
	// by a __completions or chat external/foundation model__ serving endpoint.
	Created int64 `json:"created,omitempty"`
	// The list of the embeddings returned by the __embeddings
	// external/foundation model__ serving endpoint.
	Data []EmbeddingsV1ResponseEmbeddingElement `json:"data,omitempty"`
	// The ID of the query that may be returned by a __completions or chat
	// external/foundation model__ serving endpoint.
	Id string `json:"id,omitempty"`
	// The name of the __external/foundation model__ used for querying. This is
	// the name of the model that was specified in the endpoint config.
	Model string `json:"model,omitempty"`
	// The type of object returned by the __external/foundation model__ serving
	// endpoint, one of [text_completion, chat.completion, list (of
	// embeddings)].
	Object QueryEndpointResponseObject `json:"object,omitempty"`
	// The predictions returned by the serving endpoint.
	Predictions []any `json:"predictions,omitempty"`
	// The usage object that may be returned by the __external/foundation
	// model__ serving endpoint. This contains information about the number of
	// tokens used in the prompt and response.
	Usage *ExternalModelUsageElement `json:"usage,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (QueryEndpointResponse) MarshalJSON added in v0.27.0 

func (s QueryEndpointResponse) MarshalJSON() ([]byte, error)

func (*QueryEndpointResponse) UnmarshalJSON added in v0.27.0 

func (s *QueryEndpointResponse) UnmarshalJSON(b []byte) error

type QueryEndpointResponseObject added in v0.27.0 

type QueryEndpointResponseObject string

The type of object returned by the __external/foundation model__ serving endpoint, one of [text_completion, chat.completion, list (of embeddings)]. 

const QueryEndpointResponseObjectChatCompletion QueryEndpointResponseObject = `chat.completion`
const QueryEndpointResponseObjectList QueryEndpointResponseObject = `list`
const QueryEndpointResponseObjectTextCompletion QueryEndpointResponseObject = `text_completion`

func (*QueryEndpointResponseObject) Set added in v0.27.0 

func (f *QueryEndpointResponseObject) Set(v string) error

Set raw string value and validate it against allowed values

func (*QueryEndpointResponseObject) String added in v0.27.0 

func (f *QueryEndpointResponseObject) String() string

String representation for fmt.Print

func (*QueryEndpointResponseObject) Type added in v0.27.0 

func (f *QueryEndpointResponseObject) Type() string

Type always returns QueryEndpointResponseObject to satisfy [pflag.Value] interface

type RateLimit added in v0.27.0 

type RateLimit struct {
	// Used to specify how many calls are allowed for a key within the
	// renewal_period.
	Calls int `json:"calls"`
	// Key field for a serving endpoint rate limit. Currently, only 'user' and
	// 'endpoint' are supported, with 'endpoint' being the default if not
	// specified.
	Key RateLimitKey `json:"key,omitempty"`
	// Renewal period field for a serving endpoint rate limit. Currently, only
	// 'minute' is supported.
	RenewalPeriod RateLimitRenewalPeriod `json:"renewal_period"`
}

type RateLimitKey added in v0.27.0 

type RateLimitKey string

Key field for a serving endpoint rate limit. Currently, only 'user' and 'endpoint' are supported, with 'endpoint' being the default if not specified. 

const RateLimitKeyEndpoint RateLimitKey = `endpoint`
const RateLimitKeyUser RateLimitKey = `user`

func (*RateLimitKey) Set added in v0.27.0 

func (f *RateLimitKey) Set(v string) error

Set raw string value and validate it against allowed values

func (*RateLimitKey) String added in v0.27.0 

func (f *RateLimitKey) String() string

String representation for fmt.Print

func (*RateLimitKey) Type added in v0.27.0 

func (f *RateLimitKey) Type() string

Type always returns RateLimitKey to satisfy [pflag.Value] interface

type RateLimitRenewalPeriod added in v0.27.0 

type RateLimitRenewalPeriod string

Renewal period field for a serving endpoint rate limit. Currently, only 'minute' is supported. 

const RateLimitRenewalPeriodMinute RateLimitRenewalPeriod = `minute`

func (*RateLimitRenewalPeriod) Set added in v0.27.0 

func (f *RateLimitRenewalPeriod) Set(v string) error

Set raw string value and validate it against allowed values

func (*RateLimitRenewalPeriod) String added in v0.27.0 

func (f *RateLimitRenewalPeriod) String() string

String representation for fmt.Print

func (*RateLimitRenewalPeriod) Type added in v0.27.0 

func (f *RateLimitRenewalPeriod) Type() string

Type always returns RateLimitRenewalPeriod to satisfy [pflag.Value] interface

type Route 

type Route struct {
	// The name of the served model this route configures traffic for.
	ServedModelName string `json:"served_model_name"`
	// The percentage of endpoint traffic to send to this route. It must be an
	// integer between 0 and 100 inclusive.
	TrafficPercentage int `json:"traffic_percentage"`
}

type ServedEntityInput added in v0.27.0 

type ServedEntityInput struct {
	// The name of the entity to be served. The entity may be a model in the
	// Databricks Model Registry, a model in the Unity Catalog (UC), or a
	// function of type FEATURE_SPEC in the UC. If it is a UC object, the full
	// name of the object should be given in the form of
	// __catalog_name__.__schema_name__.__model_name__.
	EntityName string `json:"entity_name,omitempty"`
	// The version of the model in Databricks Model Registry to be served or
	// empty if the entity is a FEATURE_SPEC.
	EntityVersion string `json:"entity_version,omitempty"`
	// An object containing a set of optional, user-specified environment
	// variable key-value pairs used for serving this entity. Note: this is an
	// experimental feature and subject to change. Example entity environment
	// variables that refer to Databricks secrets: `{"OPENAI_API_KEY":
	// "{{secrets/my_scope/my_key}}", "DATABRICKS_TOKEN":
	// "{{secrets/my_scope2/my_key2}}"}`
	EnvironmentVars map[string]string `json:"environment_vars,omitempty"`
	// The external model to be served. NOTE: Only one of external_model and
	// (entity_name, entity_version, workload_size, workload_type, and
	// scale_to_zero_enabled) can be specified with the latter set being used
	// for custom model serving for a Databricks registered model. When an
	// external_model is present, the served entities list can only have one
	// served_entity object. For an existing endpoint with external_model, it
	// can not be updated to an endpoint without external_model. If the endpoint
	// is created without external_model, users cannot update it to add
	// external_model later.
	ExternalModel *ExternalModel `json:"external_model,omitempty"`
	// ARN of the instance profile that the served entity uses to access AWS
	// resources.
	InstanceProfileArn string `json:"instance_profile_arn,omitempty"`
	// The name of a served entity. It must be unique across an endpoint. A
	// served entity name can consist of alphanumeric characters, dashes, and
	// underscores. If not specified for an external model, this field defaults
	// to external_model.name, with '.' and ':' replaced with '-', and if not
	// specified for other entities, it defaults to
	// <entity-name>-<entity-version>.
	Name string `json:"name,omitempty"`
	// Whether the compute resources for the served entity should scale down to
	// zero.
	ScaleToZeroEnabled bool `json:"scale_to_zero_enabled,omitempty"`
	// The workload size of the served entity. The workload size corresponds to
	// a range of provisioned concurrency that the compute autoscales between. A
	// single unit of provisioned concurrency can process one request at a time.
	// Valid workload sizes are "Small" (4 - 4 provisioned concurrency),
	// "Medium" (8 - 16 provisioned concurrency), and "Large" (16 - 64
	// provisioned concurrency). If scale-to-zero is enabled, the lower bound of
	// the provisioned concurrency for each workload size is 0.
	WorkloadSize string `json:"workload_size,omitempty"`
	// The workload type of the served entity. The workload type selects which
	// type of compute to use in the endpoint. The default value for this
	// parameter is "CPU". For deep learning workloads, GPU acceleration is
	// available by selecting workload types like GPU_SMALL and others. See the
	// available [GPU types].
	//
	// [GPU types]: https://docs.databricks.com/machine-learning/model-serving/create-manage-serving-endpoints.html#gpu-workload-types
	WorkloadType string `json:"workload_type,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServedEntityInput) MarshalJSON added in v0.27.0 

func (s ServedEntityInput) MarshalJSON() ([]byte, error)

func (*ServedEntityInput) UnmarshalJSON added in v0.27.0 

func (s *ServedEntityInput) UnmarshalJSON(b []byte) error

type ServedEntityOutput added in v0.27.0 

type ServedEntityOutput struct {
	// The creation timestamp of the served entity in Unix time.
	CreationTimestamp int64 `json:"creation_timestamp,omitempty"`
	// The email of the user who created the served entity.
	Creator string `json:"creator,omitempty"`
	// The name of the entity served. The entity may be a model in the
	// Databricks Model Registry, a model in the Unity Catalog (UC), or a
	// function of type FEATURE_SPEC in the UC. If it is a UC object, the full
	// name of the object is given in the form of
	// __catalog_name__.__schema_name__.__model_name__.
	EntityName string `json:"entity_name,omitempty"`
	// The version of the served entity in Databricks Model Registry or empty if
	// the entity is a FEATURE_SPEC.
	EntityVersion string `json:"entity_version,omitempty"`
	// An object containing a set of optional, user-specified environment
	// variable key-value pairs used for serving this entity. Note: this is an
	// experimental feature and subject to change. Example entity environment
	// variables that refer to Databricks secrets: `{"OPENAI_API_KEY":
	// "{{secrets/my_scope/my_key}}", "DATABRICKS_TOKEN":
	// "{{secrets/my_scope2/my_key2}}"}`
	EnvironmentVars map[string]string `json:"environment_vars,omitempty"`
	// The external model that is served. NOTE: Only one of external_model,
	// foundation_model, and (entity_name, entity_version, workload_size,
	// workload_type, and scale_to_zero_enabled) is returned based on the
	// endpoint type.
	ExternalModel *ExternalModel `json:"external_model,omitempty"`
	// The foundation model that is served. NOTE: Only one of foundation_model,
	// external_model, and (entity_name, entity_version, workload_size,
	// workload_type, and scale_to_zero_enabled) is returned based on the
	// endpoint type.
	FoundationModel *FoundationModel `json:"foundation_model,omitempty"`
	// ARN of the instance profile that the served entity uses to access AWS
	// resources.
	InstanceProfileArn string `json:"instance_profile_arn,omitempty"`
	// The name of the served entity.
	Name string `json:"name,omitempty"`
	// Whether the compute resources for the served entity should scale down to
	// zero.
	ScaleToZeroEnabled bool `json:"scale_to_zero_enabled,omitempty"`
	// Information corresponding to the state of the served entity.
	State *ServedModelState `json:"state,omitempty"`
	// The workload size of the served entity. The workload size corresponds to
	// a range of provisioned concurrency that the compute autoscales between. A
	// single unit of provisioned concurrency can process one request at a time.
	// Valid workload sizes are "Small" (4 - 4 provisioned concurrency),
	// "Medium" (8 - 16 provisioned concurrency), and "Large" (16 - 64
	// provisioned concurrency). If scale-to-zero is enabled, the lower bound of
	// the provisioned concurrency for each workload size will be 0.
	WorkloadSize string `json:"workload_size,omitempty"`
	// The workload type of the served entity. The workload type selects which
	// type of compute to use in the endpoint. The default value for this
	// parameter is "CPU". For deep learning workloads, GPU acceleration is
	// available by selecting workload types like GPU_SMALL and others. See the
	// available [GPU types].
	//
	// [GPU types]: https://docs.databricks.com/machine-learning/model-serving/create-manage-serving-endpoints.html#gpu-workload-types
	WorkloadType string `json:"workload_type,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServedEntityOutput) MarshalJSON added in v0.27.0 

func (s ServedEntityOutput) MarshalJSON() ([]byte, error)

func (*ServedEntityOutput) UnmarshalJSON added in v0.27.0 

func (s *ServedEntityOutput) UnmarshalJSON(b []byte) error

type ServedEntitySpec added in v0.27.0 

type ServedEntitySpec struct {
	// The name of the entity served. The entity may be a model in the
	// Databricks Model Registry, a model in the Unity Catalog (UC), or a
	// function of type FEATURE_SPEC in the UC. If it is a UC object, the full
	// name of the object is given in the form of
	// __catalog_name__.__schema_name__.__model_name__.
	EntityName string `json:"entity_name,omitempty"`
	// The version of the served entity in Databricks Model Registry or empty if
	// the entity is a FEATURE_SPEC.
	EntityVersion string `json:"entity_version,omitempty"`
	// The external model that is served. NOTE: Only one of external_model,
	// foundation_model, and (entity_name, entity_version) is returned based on
	// the endpoint type.
	ExternalModel *ExternalModel `json:"external_model,omitempty"`
	// The foundation model that is served. NOTE: Only one of foundation_model,
	// external_model, and (entity_name, entity_version) is returned based on
	// the endpoint type.
	FoundationModel *FoundationModel `json:"foundation_model,omitempty"`
	// The name of the served entity.
	Name string `json:"name,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServedEntitySpec) MarshalJSON added in v0.27.0 

func (s ServedEntitySpec) MarshalJSON() ([]byte, error)

func (*ServedEntitySpec) UnmarshalJSON added in v0.27.0 

func (s *ServedEntitySpec) UnmarshalJSON(b []byte) error

type ServedModelInput 

type ServedModelInput struct {
	// An object containing a set of optional, user-specified environment
	// variable key-value pairs used for serving this model. Note: this is an
	// experimental feature and subject to change. Example model environment
	// variables that refer to Databricks secrets: `{"OPENAI_API_KEY":
	// "{{secrets/my_scope/my_key}}", "DATABRICKS_TOKEN":
	// "{{secrets/my_scope2/my_key2}}"}`
	EnvironmentVars map[string]string `json:"environment_vars,omitempty"`
	// ARN of the instance profile that the served model will use to access AWS
	// resources.
	InstanceProfileArn string `json:"instance_profile_arn,omitempty"`
	// The name of the model in Databricks Model Registry to be served or if the
	// model resides in Unity Catalog, the full name of model, in the form of
	// __catalog_name__.__schema_name__.__model_name__.
	ModelName string `json:"model_name"`
	// The version of the model in Databricks Model Registry or Unity Catalog to
	// be served.
	ModelVersion string `json:"model_version"`
	// The name of a served model. It must be unique across an endpoint. If not
	// specified, this field will default to <model-name>-<model-version>. A
	// served model name can consist of alphanumeric characters, dashes, and
	// underscores.
	Name string `json:"name,omitempty"`
	// Whether the compute resources for the served model should scale down to
	// zero.
	ScaleToZeroEnabled bool `json:"scale_to_zero_enabled"`
	// The workload size of the served model. The workload size corresponds to a
	// range of provisioned concurrency that the compute will autoscale between.
	// A single unit of provisioned concurrency can process one request at a
	// time. Valid workload sizes are "Small" (4 - 4 provisioned concurrency),
	// "Medium" (8 - 16 provisioned concurrency), and "Large" (16 - 64
	// provisioned concurrency). If scale-to-zero is enabled, the lower bound of
	// the provisioned concurrency for each workload size will be 0.
	WorkloadSize ServedModelInputWorkloadSize `json:"workload_size"`
	// The workload type of the served model. The workload type selects which
	// type of compute to use in the endpoint. The default value for this
	// parameter is "CPU". For deep learning workloads, GPU acceleration is
	// available by selecting workload types like GPU_SMALL and others. See the
	// available [GPU types].
	//
	// [GPU types]: https://docs.databricks.com/machine-learning/model-serving/create-manage-serving-endpoints.html#gpu-workload-types
	WorkloadType ServedModelInputWorkloadType `json:"workload_type,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServedModelInput) MarshalJSON added in v0.23.0 

func (s ServedModelInput) MarshalJSON() ([]byte, error)

func (*ServedModelInput) UnmarshalJSON added in v0.23.0 

func (s *ServedModelInput) UnmarshalJSON(b []byte) error

type ServedModelInputWorkloadSize added in v0.27.0 

type ServedModelInputWorkloadSize string

The workload size of the served model. The workload size corresponds to a range of provisioned concurrency that the compute will autoscale between. A single unit of provisioned concurrency can process one request at a time. Valid workload sizes are "Small" (4 - 4 provisioned concurrency), "Medium" (8 - 16 provisioned concurrency), and "Large" (16 - 64 provisioned concurrency). If scale-to-zero is enabled, the lower bound of the provisioned concurrency for each workload size will be 0. 

const ServedModelInputWorkloadSizeLarge ServedModelInputWorkloadSize = `Large`
const ServedModelInputWorkloadSizeMedium ServedModelInputWorkloadSize = `Medium`
const ServedModelInputWorkloadSizeSmall ServedModelInputWorkloadSize = `Small`

func (*ServedModelInputWorkloadSize) Set added in v0.27.0 

func (f *ServedModelInputWorkloadSize) Set(v string) error

Set raw string value and validate it against allowed values

func (*ServedModelInputWorkloadSize) String added in v0.27.0 

func (f *ServedModelInputWorkloadSize) String() string

String representation for fmt.Print

func (*ServedModelInputWorkloadSize) Type added in v0.27.0 

func (f *ServedModelInputWorkloadSize) Type() string

Type always returns ServedModelInputWorkloadSize to satisfy [pflag.Value] interface

type ServedModelInputWorkloadType added in v0.27.0 

type ServedModelInputWorkloadType string

The workload type of the served model. The workload type selects which type of compute to use in the endpoint. The default value for this parameter is "CPU". For deep learning workloads, GPU acceleration is available by selecting workload types like GPU_SMALL and others. See the available GPU types. 

const ServedModelInputWorkloadTypeCpu ServedModelInputWorkloadType = `CPU`
const ServedModelInputWorkloadTypeGpuLarge ServedModelInputWorkloadType = `GPU_LARGE`
const ServedModelInputWorkloadTypeGpuMedium ServedModelInputWorkloadType = `GPU_MEDIUM`
const ServedModelInputWorkloadTypeGpuSmall ServedModelInputWorkloadType = `GPU_SMALL`
const ServedModelInputWorkloadTypeMultigpuMedium ServedModelInputWorkloadType = `MULTIGPU_MEDIUM`

func (*ServedModelInputWorkloadType) Set added in v0.27.0 

func (f *ServedModelInputWorkloadType) Set(v string) error

Set raw string value and validate it against allowed values

func (*ServedModelInputWorkloadType) String added in v0.27.0 

func (f *ServedModelInputWorkloadType) String() string

String representation for fmt.Print

func (*ServedModelInputWorkloadType) Type added in v0.27.0 

func (f *ServedModelInputWorkloadType) Type() string

Type always returns ServedModelInputWorkloadType to satisfy [pflag.Value] interface

type ServedModelOutput 

type ServedModelOutput struct {
	// The creation timestamp of the served model in Unix time.
	CreationTimestamp int64 `json:"creation_timestamp,omitempty"`
	// The email of the user who created the served model.
	Creator string `json:"creator,omitempty"`
	// An object containing a set of optional, user-specified environment
	// variable key-value pairs used for serving this model. Note: this is an
	// experimental feature and subject to change. Example model environment
	// variables that refer to Databricks secrets: `{"OPENAI_API_KEY":
	// "{{secrets/my_scope/my_key}}", "DATABRICKS_TOKEN":
	// "{{secrets/my_scope2/my_key2}}"}`
	EnvironmentVars map[string]string `json:"environment_vars,omitempty"`
	// ARN of the instance profile that the served model will use to access AWS
	// resources.
	InstanceProfileArn string `json:"instance_profile_arn,omitempty"`
	// The name of the model in Databricks Model Registry or the full name of
	// the model in Unity Catalog.
	ModelName string `json:"model_name,omitempty"`
	// The version of the model in Databricks Model Registry or Unity Catalog to
	// be served.
	ModelVersion string `json:"model_version,omitempty"`
	// The name of the served model.
	Name string `json:"name,omitempty"`
	// Whether the compute resources for the Served Model should scale down to
	// zero.
	ScaleToZeroEnabled bool `json:"scale_to_zero_enabled,omitempty"`
	// Information corresponding to the state of the Served Model.
	State *ServedModelState `json:"state,omitempty"`
	// The workload size of the served model. The workload size corresponds to a
	// range of provisioned concurrency that the compute will autoscale between.
	// A single unit of provisioned concurrency can process one request at a
	// time. Valid workload sizes are "Small" (4 - 4 provisioned concurrency),
	// "Medium" (8 - 16 provisioned concurrency), and "Large" (16 - 64
	// provisioned concurrency). If scale-to-zero is enabled, the lower bound of
	// the provisioned concurrency for each workload size will be 0.
	WorkloadSize string `json:"workload_size,omitempty"`
	// The workload type of the served model. The workload type selects which
	// type of compute to use in the endpoint. The default value for this
	// parameter is "CPU". For deep learning workloads, GPU acceleration is
	// available by selecting workload types like GPU_SMALL and others. See the
	// available [GPU types].
	//
	// [GPU types]: https://docs.databricks.com/machine-learning/model-serving/create-manage-serving-endpoints.html#gpu-workload-types
	WorkloadType string `json:"workload_type,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServedModelOutput) MarshalJSON added in v0.23.0 

func (s ServedModelOutput) MarshalJSON() ([]byte, error)

func (*ServedModelOutput) UnmarshalJSON added in v0.23.0 

func (s *ServedModelOutput) UnmarshalJSON(b []byte) error

type ServedModelSpec 

type ServedModelSpec struct {
	// The name of the model in Databricks Model Registry or the full name of
	// the model in Unity Catalog.
	ModelName string `json:"model_name,omitempty"`
	// The version of the model in Databricks Model Registry or Unity Catalog to
	// be served.
	ModelVersion string `json:"model_version,omitempty"`
	// The name of the served model.
	Name string `json:"name,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServedModelSpec) MarshalJSON added in v0.23.0 

func (s ServedModelSpec) MarshalJSON() ([]byte, error)

func (*ServedModelSpec) UnmarshalJSON added in v0.23.0 

func (s *ServedModelSpec) UnmarshalJSON(b []byte) error

type ServedModelState 

type ServedModelState struct {
	// The state of the served entity deployment. DEPLOYMENT_CREATING indicates
	// that the served entity is not ready yet because the deployment is still
	// being created (i.e container image is building, model server is deploying
	// for the first time, etc.). DEPLOYMENT_RECOVERING indicates that the
	// served entity was previously in a ready state but no longer is and is
	// attempting to recover. DEPLOYMENT_READY indicates that the served entity
	// is ready to receive traffic. DEPLOYMENT_FAILED indicates that there was
	// an error trying to bring up the served entity (e.g container image build
	// failed, the model server failed to start due to a model loading error,
	// etc.) DEPLOYMENT_ABORTED indicates that the deployment was terminated
	// likely due to a failure in bringing up another served entity under the
	// same endpoint and config version.
	Deployment ServedModelStateDeployment `json:"deployment,omitempty"`
	// More information about the state of the served entity, if available.
	DeploymentStateMessage string `json:"deployment_state_message,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServedModelState) MarshalJSON added in v0.23.0 

func (s ServedModelState) MarshalJSON() ([]byte, error)

func (*ServedModelState) UnmarshalJSON added in v0.23.0 

func (s *ServedModelState) UnmarshalJSON(b []byte) error

type ServedModelStateDeployment 

type ServedModelStateDeployment string

The state of the served entity deployment. DEPLOYMENT_CREATING indicates that the served entity is not ready yet because the deployment is still being created (i.e container image is building, model server is deploying for the first time, etc.). DEPLOYMENT_RECOVERING indicates that the served entity was previously in a ready state but no longer is and is attempting to recover. DEPLOYMENT_READY indicates that the served entity is ready to receive traffic. DEPLOYMENT_FAILED indicates that there was an error trying to bring up the served entity (e.g container image build failed, the model server failed to start due to a model loading error, etc.) DEPLOYMENT_ABORTED indicates that the deployment was terminated likely due to a failure in bringing up another served entity under the same endpoint and config version. 

const ServedModelStateDeploymentAborted ServedModelStateDeployment = `DEPLOYMENT_ABORTED`
const ServedModelStateDeploymentCreating ServedModelStateDeployment = `DEPLOYMENT_CREATING`
const ServedModelStateDeploymentFailed ServedModelStateDeployment = `DEPLOYMENT_FAILED`
const ServedModelStateDeploymentReady ServedModelStateDeployment = `DEPLOYMENT_READY`
const ServedModelStateDeploymentRecovering ServedModelStateDeployment = `DEPLOYMENT_RECOVERING`

func (*ServedModelStateDeployment) Set 

func (f *ServedModelStateDeployment) Set(v string) error

Set raw string value and validate it against allowed values

func (*ServedModelStateDeployment) String 

func (f *ServedModelStateDeployment) String() string

String representation for fmt.Print

func (*ServedModelStateDeployment) Type 

func (f *ServedModelStateDeployment) Type() string

Type always returns ServedModelStateDeployment to satisfy [pflag.Value] interface

type ServerLogsResponse 

type ServerLogsResponse struct {
	// The most recent log lines of the model server processing invocation
	// requests.
	Logs string `json:"logs"`
}

type ServingEndpoint 

type ServingEndpoint struct {
	// The config that is currently being served by the endpoint.
	Config *EndpointCoreConfigSummary `json:"config,omitempty"`
	// The timestamp when the endpoint was created in Unix time.
	CreationTimestamp int64 `json:"creation_timestamp,omitempty"`
	// The email of the user who created the serving endpoint.
	Creator string `json:"creator,omitempty"`
	// System-generated ID of the endpoint. This is used to refer to the
	// endpoint in the Permissions API
	Id string `json:"id,omitempty"`
	// The timestamp when the endpoint was last updated by a user in Unix time.
	LastUpdatedTimestamp int64 `json:"last_updated_timestamp,omitempty"`
	// The name of the serving endpoint.
	Name string `json:"name,omitempty"`
	// Information corresponding to the state of the serving endpoint.
	State *EndpointState `json:"state,omitempty"`
	// Tags attached to the serving endpoint.
	Tags []EndpointTag `json:"tags,omitempty"`
	// The task type of the serving endpoint.
	Task string `json:"task,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServingEndpoint) MarshalJSON added in v0.23.0 

func (s ServingEndpoint) MarshalJSON() ([]byte, error)

func (*ServingEndpoint) UnmarshalJSON added in v0.23.0 

func (s *ServingEndpoint) UnmarshalJSON(b []byte) error

type ServingEndpointAccessControlRequest added in v0.15.0 

type ServingEndpointAccessControlRequest struct {
	// name of the group
	GroupName string `json:"group_name,omitempty"`
	// Permission level
	PermissionLevel ServingEndpointPermissionLevel `json:"permission_level,omitempty"`
	// Application ID of an active service principal. Setting this field
	// requires the `servicePrincipal/user` role.
	ServicePrincipalName string `json:"service_principal_name,omitempty"`
	// name of the user
	UserName string `json:"user_name,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServingEndpointAccessControlRequest) MarshalJSON added in v0.23.0 

func (s ServingEndpointAccessControlRequest) MarshalJSON() ([]byte, error)

func (*ServingEndpointAccessControlRequest) UnmarshalJSON added in v0.23.0 

func (s *ServingEndpointAccessControlRequest) UnmarshalJSON(b []byte) error

type ServingEndpointAccessControlResponse added in v0.15.0 

type ServingEndpointAccessControlResponse struct {
	// All permissions.
	AllPermissions []ServingEndpointPermission `json:"all_permissions,omitempty"`
	// Display name of the user or service principal.
	DisplayName string `json:"display_name,omitempty"`
	// name of the group
	GroupName string `json:"group_name,omitempty"`
	// Name of the service principal.
	ServicePrincipalName string `json:"service_principal_name,omitempty"`
	// name of the user
	UserName string `json:"user_name,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServingEndpointAccessControlResponse) MarshalJSON added in v0.23.0 

func (s ServingEndpointAccessControlResponse) MarshalJSON() ([]byte, error)

func (*ServingEndpointAccessControlResponse) UnmarshalJSON added in v0.23.0 

func (s *ServingEndpointAccessControlResponse) UnmarshalJSON(b []byte) error

type ServingEndpointDetailed 

type ServingEndpointDetailed struct {
	// The config that is currently being served by the endpoint.
	Config *EndpointCoreConfigOutput `json:"config,omitempty"`
	// The timestamp when the endpoint was created in Unix time.
	CreationTimestamp int64 `json:"creation_timestamp,omitempty"`
	// The email of the user who created the serving endpoint.
	Creator string `json:"creator,omitempty"`
	// System-generated ID of the endpoint. This is used to refer to the
	// endpoint in the Permissions API
	Id string `json:"id,omitempty"`
	// The timestamp when the endpoint was last updated by a user in Unix time.
	LastUpdatedTimestamp int64 `json:"last_updated_timestamp,omitempty"`
	// The name of the serving endpoint.
	Name string `json:"name,omitempty"`
	// The config that the endpoint is attempting to update to.
	PendingConfig *EndpointPendingConfig `json:"pending_config,omitempty"`
	// The permission level of the principal making the request.
	PermissionLevel ServingEndpointDetailedPermissionLevel `json:"permission_level,omitempty"`
	// Information corresponding to the state of the serving endpoint.
	State *EndpointState `json:"state,omitempty"`
	// Tags attached to the serving endpoint.
	Tags []EndpointTag `json:"tags,omitempty"`
	// The task type of the serving endpoint.
	Task string `json:"task,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServingEndpointDetailed) MarshalJSON added in v0.23.0 

func (s ServingEndpointDetailed) MarshalJSON() ([]byte, error)

func (*ServingEndpointDetailed) UnmarshalJSON added in v0.23.0 

func (s *ServingEndpointDetailed) UnmarshalJSON(b []byte) error

type ServingEndpointDetailedPermissionLevel 

type ServingEndpointDetailedPermissionLevel string

The permission level of the principal making the request. 

const ServingEndpointDetailedPermissionLevelCanManage ServingEndpointDetailedPermissionLevel = `CAN_MANAGE`
const ServingEndpointDetailedPermissionLevelCanQuery ServingEndpointDetailedPermissionLevel = `CAN_QUERY`
const ServingEndpointDetailedPermissionLevelCanView ServingEndpointDetailedPermissionLevel = `CAN_VIEW`

func (*ServingEndpointDetailedPermissionLevel) Set 

func (f *ServingEndpointDetailedPermissionLevel) Set(v string) error

Set raw string value and validate it against allowed values

func (*ServingEndpointDetailedPermissionLevel) String 

func (f *ServingEndpointDetailedPermissionLevel) String() string

String representation for fmt.Print

func (*ServingEndpointDetailedPermissionLevel) Type 

func (f *ServingEndpointDetailedPermissionLevel) Type() string

Type always returns ServingEndpointDetailedPermissionLevel to satisfy [pflag.Value] interface

type ServingEndpointPermission added in v0.15.0 

type ServingEndpointPermission struct {
	Inherited bool `json:"inherited,omitempty"`

	InheritedFromObject []string `json:"inherited_from_object,omitempty"`
	// Permission level
	PermissionLevel ServingEndpointPermissionLevel `json:"permission_level,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServingEndpointPermission) MarshalJSON added in v0.23.0 

func (s ServingEndpointPermission) MarshalJSON() ([]byte, error)

func (*ServingEndpointPermission) UnmarshalJSON added in v0.23.0 

func (s *ServingEndpointPermission) UnmarshalJSON(b []byte) error

type ServingEndpointPermissionLevel added in v0.15.0 

type ServingEndpointPermissionLevel string

Permission level 

const ServingEndpointPermissionLevelCanManage ServingEndpointPermissionLevel = `CAN_MANAGE`
const ServingEndpointPermissionLevelCanQuery ServingEndpointPermissionLevel = `CAN_QUERY`
const ServingEndpointPermissionLevelCanView ServingEndpointPermissionLevel = `CAN_VIEW`

func (*ServingEndpointPermissionLevel) Set added in v0.15.0 

func (f *ServingEndpointPermissionLevel) Set(v string) error

Set raw string value and validate it against allowed values

func (*ServingEndpointPermissionLevel) String added in v0.15.0 

func (f *ServingEndpointPermissionLevel) String() string

String representation for fmt.Print

func (*ServingEndpointPermissionLevel) Type added in v0.15.0 

func (f *ServingEndpointPermissionLevel) Type() string

Type always returns ServingEndpointPermissionLevel to satisfy [pflag.Value] interface

type ServingEndpointPermissions added in v0.15.0 

type ServingEndpointPermissions struct {
	AccessControlList []ServingEndpointAccessControlResponse `json:"access_control_list,omitempty"`

	ObjectId string `json:"object_id,omitempty"`

	ObjectType string `json:"object_type,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServingEndpointPermissions) MarshalJSON added in v0.23.0 

func (s ServingEndpointPermissions) MarshalJSON() ([]byte, error)

func (*ServingEndpointPermissions) UnmarshalJSON added in v0.23.0 

func (s *ServingEndpointPermissions) UnmarshalJSON(b []byte) error

type ServingEndpointPermissionsDescription added in v0.15.0 

type ServingEndpointPermissionsDescription struct {
	Description string `json:"description,omitempty"`
	// Permission level
	PermissionLevel ServingEndpointPermissionLevel `json:"permission_level,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (ServingEndpointPermissionsDescription) MarshalJSON added in v0.23.0 

func (s ServingEndpointPermissionsDescription) MarshalJSON() ([]byte, error)

func (*ServingEndpointPermissionsDescription) UnmarshalJSON added in v0.23.0 

func (s *ServingEndpointPermissionsDescription) UnmarshalJSON(b []byte) error

type ServingEndpointPermissionsRequest added in v0.15.0 

type ServingEndpointPermissionsRequest struct {
	AccessControlList []ServingEndpointAccessControlRequest `json:"access_control_list,omitempty"`
	// The serving endpoint for which to get or manage permissions.
	ServingEndpointId string `json:"-" url:"-"`
}

type ServingEndpointsAPI 

type ServingEndpointsAPI struct {
	// contains filtered or unexported fields
}

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 entities. A serving endpoint can have at most ten served entities. You can configure traffic settings to define how requests should be routed to your served entities behind an endpoint. Additionally, you can configure the scale of resources that should be applied to each served entity.

func NewServingEndpoints 

func NewServingEndpoints(client *client.DatabricksClient) *ServingEndpointsAPI

func (*ServingEndpointsAPI) BuildLogs 

func (a *ServingEndpointsAPI) BuildLogs(ctx context.Context, request BuildLogsRequest) (*BuildLogsResponse, error)

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.

func (*ServingEndpointsAPI) BuildLogsByNameAndServedModelName 

func (a *ServingEndpointsAPI) BuildLogsByNameAndServedModelName(ctx context.Context, name string, servedModelName string) (*BuildLogsResponse, error)

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.

func (*ServingEndpointsAPI) Create 

func (a *ServingEndpointsAPI) Create(ctx context.Context, createServingEndpoint CreateServingEndpoint) (*WaitGetServingEndpointNotUpdating[ServingEndpointDetailed], error)

Create a new serving endpoint.

func (*ServingEndpointsAPI) CreateAndWait deprecated 

func (a *ServingEndpointsAPI) CreateAndWait(ctx context.Context, createServingEndpoint CreateServingEndpoint, options ...retries.Option[ServingEndpointDetailed]) (*ServingEndpointDetailed, error)

Calls ServingEndpointsAPI.Create and waits to reach NOT_UPDATING state

You can override the default timeout of 20 minutes by calling adding retries.Timeout[ServingEndpointDetailed](60*time.Minute) functional option.

Deprecated: use ServingEndpointsAPI.Create.Get() or ServingEndpointsAPI.WaitGetServingEndpointNotUpdating

func (*ServingEndpointsAPI) Delete 

func (a *ServingEndpointsAPI) Delete(ctx context.Context, request DeleteServingEndpointRequest) error

Delete a serving endpoint.

func (*ServingEndpointsAPI) DeleteByName 

func (a *ServingEndpointsAPI) DeleteByName(ctx context.Context, name string) error

Delete a serving endpoint.

func (*ServingEndpointsAPI) ExportMetrics 

func (a *ServingEndpointsAPI) ExportMetrics(ctx context.Context, request ExportMetricsRequest) error

Retrieve the metrics associated with a serving endpoint.

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

func (*ServingEndpointsAPI) ExportMetricsByName 

func (a *ServingEndpointsAPI) ExportMetricsByName(ctx context.Context, name string) error

Retrieve the metrics associated with a serving endpoint.

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

func (*ServingEndpointsAPI) Get 

func (a *ServingEndpointsAPI) Get(ctx context.Context, request GetServingEndpointRequest) (*ServingEndpointDetailed, error)

Get a single serving endpoint.

Retrieves the details for a single serving endpoint.

func (*ServingEndpointsAPI) GetByName 

func (a *ServingEndpointsAPI) GetByName(ctx context.Context, name string) (*ServingEndpointDetailed, error)

Get a single serving endpoint.

Retrieves the details for a single serving endpoint.

func (*ServingEndpointsAPI) GetPermissionLevels added in v0.19.0 

func (a *ServingEndpointsAPI) GetPermissionLevels(ctx context.Context, request GetServingEndpointPermissionLevelsRequest) (*GetServingEndpointPermissionLevelsResponse, error)

Get serving endpoint permission levels.

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

func (*ServingEndpointsAPI) GetPermissionLevelsByServingEndpointId added in v0.19.0 

func (a *ServingEndpointsAPI) GetPermissionLevelsByServingEndpointId(ctx context.Context, servingEndpointId string) (*GetServingEndpointPermissionLevelsResponse, error)

Get serving endpoint permission levels.

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

func (*ServingEndpointsAPI) GetPermissions added in v0.19.0 

func (a *ServingEndpointsAPI) GetPermissions(ctx context.Context, request GetServingEndpointPermissionsRequest) (*ServingEndpointPermissions, error)

Get serving endpoint permissions.

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

func (*ServingEndpointsAPI) GetPermissionsByServingEndpointId added in v0.19.0 

func (a *ServingEndpointsAPI) GetPermissionsByServingEndpointId(ctx context.Context, servingEndpointId string) (*ServingEndpointPermissions, error)

Get serving endpoint permissions.

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

func (*ServingEndpointsAPI) Impl 

func (a *ServingEndpointsAPI) Impl() ServingEndpointsService

Impl returns low-level ServingEndpoints API implementation Deprecated: use MockServingEndpointsInterface instead.

func (*ServingEndpointsAPI) List 

func (a *ServingEndpointsAPI) List(ctx context.Context) *listing.PaginatingIterator[struct{}, *ListEndpointsResponse, ServingEndpoint]

Retrieve all serving endpoints.

This method is generated by Databricks SDK Code Generator.

func (*ServingEndpointsAPI) ListAll added in v0.10.0 

func (a *ServingEndpointsAPI) ListAll(ctx context.Context) ([]ServingEndpoint, error)

Retrieve all serving endpoints.

This method is generated by Databricks SDK Code Generator.

func (*ServingEndpointsAPI) Logs 

func (a *ServingEndpointsAPI) Logs(ctx context.Context, request LogsRequest) (*ServerLogsResponse, error)

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.

func (*ServingEndpointsAPI) LogsByNameAndServedModelName 

func (a *ServingEndpointsAPI) LogsByNameAndServedModelName(ctx context.Context, name string, servedModelName string) (*ServerLogsResponse, error)

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.

func (*ServingEndpointsAPI) Patch added in v0.20.0 

func (a *ServingEndpointsAPI) Patch(ctx context.Context, request PatchServingEndpointTags) ([]EndpointTag, error)

Patch the tags of a serving endpoint.

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

func (*ServingEndpointsAPI) Put added in v0.27.0 

func (a *ServingEndpointsAPI) Put(ctx context.Context, request PutRequest) (*PutResponse, error)

Update the rate limits of a serving endpoint.

Used to update the rate limits of a serving endpoint. NOTE: only external and foundation model endpoints are supported as of now.

func (*ServingEndpointsAPI) Query 

func (a *ServingEndpointsAPI) Query(ctx context.Context, request QueryEndpointInput) (*QueryEndpointResponse, error)

Query a serving endpoint with provided model input.

func (*ServingEndpointsAPI) SetPermissions added in v0.19.0 

func (a *ServingEndpointsAPI) SetPermissions(ctx context.Context, request ServingEndpointPermissionsRequest) (*ServingEndpointPermissions, error)

Set serving endpoint permissions.

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

func (*ServingEndpointsAPI) UpdateConfig 

func (a *ServingEndpointsAPI) UpdateConfig(ctx context.Context, endpointCoreConfigInput EndpointCoreConfigInput) (*WaitGetServingEndpointNotUpdating[ServingEndpointDetailed], error)

Update a serving endpoint with a new config.

Updates any combination of the serving endpoint's served entities, the compute configuration of those served entities, 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.

func (*ServingEndpointsAPI) UpdateConfigAndWait deprecated 

func (a *ServingEndpointsAPI) UpdateConfigAndWait(ctx context.Context, endpointCoreConfigInput EndpointCoreConfigInput, options ...retries.Option[ServingEndpointDetailed]) (*ServingEndpointDetailed, error)

Calls ServingEndpointsAPI.UpdateConfig and waits to reach NOT_UPDATING state

You can override the default timeout of 20 minutes by calling adding retries.Timeout[ServingEndpointDetailed](60*time.Minute) functional option.

Deprecated: use ServingEndpointsAPI.UpdateConfig.Get() or ServingEndpointsAPI.WaitGetServingEndpointNotUpdating

func (*ServingEndpointsAPI) UpdatePermissions added in v0.19.0 

func (a *ServingEndpointsAPI) UpdatePermissions(ctx context.Context, request ServingEndpointPermissionsRequest) (*ServingEndpointPermissions, error)

Update serving endpoint permissions.

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

func (*ServingEndpointsAPI) WaitGetServingEndpointNotUpdating added in v0.10.0 

func (a *ServingEndpointsAPI) WaitGetServingEndpointNotUpdating(ctx context.Context, name string,
	timeout time.Duration, callback func(*ServingEndpointDetailed)) (*ServingEndpointDetailed, error)

WaitGetServingEndpointNotUpdating repeatedly calls ServingEndpointsAPI.Get and waits to reach NOT_UPDATING state

func (*ServingEndpointsAPI) WithImpl 

func (a *ServingEndpointsAPI) WithImpl(impl ServingEndpointsService) ServingEndpointsInterface

WithImpl could be used to override low-level API implementations for unit testing purposes with github.com/golang/mock or other mocking frameworks. Deprecated: use MockServingEndpointsInterface instead.

type ServingEndpointsInterface added in v0.29.0 

type ServingEndpointsInterface interface {
	// WithImpl could be used to override low-level API implementations for unit
	// testing purposes with [github.com/golang/mock] or other mocking frameworks.
	// Deprecated: use MockServingEndpointsInterface instead.
	WithImpl(impl ServingEndpointsService) ServingEndpointsInterface

	// Impl returns low-level ServingEndpoints API implementation
	// Deprecated: use MockServingEndpointsInterface instead.
	Impl() ServingEndpointsService

	// WaitGetServingEndpointNotUpdating repeatedly calls [ServingEndpointsAPI.Get] and waits to reach NOT_UPDATING state
	WaitGetServingEndpointNotUpdating(ctx context.Context, name string,
		timeout time.Duration, callback func(*ServingEndpointDetailed)) (*ServingEndpointDetailed, error)

	// 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.
	BuildLogs(ctx context.Context, request BuildLogsRequest) (*BuildLogsResponse, error)

	// 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.
	BuildLogsByNameAndServedModelName(ctx context.Context, name string, servedModelName string) (*BuildLogsResponse, error)

	// Create a new serving endpoint.
	Create(ctx context.Context, createServingEndpoint CreateServingEndpoint) (*WaitGetServingEndpointNotUpdating[ServingEndpointDetailed], error)

	// Calls [ServingEndpointsAPIInterface.Create] and waits to reach NOT_UPDATING state
	//
	// You can override the default timeout of 20 minutes by calling adding
	// retries.Timeout[ServingEndpointDetailed](60*time.Minute) functional option.
	//
	// Deprecated: use [ServingEndpointsAPIInterface.Create].Get() or [ServingEndpointsAPIInterface.WaitGetServingEndpointNotUpdating]
	CreateAndWait(ctx context.Context, createServingEndpoint CreateServingEndpoint, options ...retries.Option[ServingEndpointDetailed]) (*ServingEndpointDetailed, error)

	// Delete a serving endpoint.
	Delete(ctx context.Context, request DeleteServingEndpointRequest) error

	// Delete a serving endpoint.
	DeleteByName(ctx context.Context, name string) error

	// Retrieve the metrics associated with a serving endpoint.
	//
	// Retrieves the metrics associated with the provided serving endpoint in either
	// Prometheus or OpenMetrics exposition format.
	ExportMetrics(ctx context.Context, request ExportMetricsRequest) error

	// Retrieve the metrics associated with a serving endpoint.
	//
	// Retrieves the metrics associated with the provided serving endpoint in either
	// Prometheus or OpenMetrics exposition format.
	ExportMetricsByName(ctx context.Context, name string) error

	// Get a single serving endpoint.
	//
	// Retrieves the details for a single serving endpoint.
	Get(ctx context.Context, request GetServingEndpointRequest) (*ServingEndpointDetailed, error)

	// Get a single serving endpoint.
	//
	// Retrieves the details for a single serving endpoint.
	GetByName(ctx context.Context, name string) (*ServingEndpointDetailed, error)

	// Get serving endpoint permission levels.
	//
	// Gets the permission levels that a user can have on an object.
	GetPermissionLevels(ctx context.Context, request GetServingEndpointPermissionLevelsRequest) (*GetServingEndpointPermissionLevelsResponse, error)

	// Get serving endpoint permission levels.
	//
	// Gets the permission levels that a user can have on an object.
	GetPermissionLevelsByServingEndpointId(ctx context.Context, servingEndpointId string) (*GetServingEndpointPermissionLevelsResponse, error)

	// Get serving endpoint permissions.
	//
	// Gets the permissions of a serving endpoint. Serving endpoints can inherit
	// permissions from their root object.
	GetPermissions(ctx context.Context, request GetServingEndpointPermissionsRequest) (*ServingEndpointPermissions, error)

	// Get serving endpoint permissions.
	//
	// Gets the permissions of a serving endpoint. Serving endpoints can inherit
	// permissions from their root object.
	GetPermissionsByServingEndpointId(ctx context.Context, servingEndpointId string) (*ServingEndpointPermissions, error)

	// Retrieve all serving endpoints.
	//
	// This method is generated by Databricks SDK Code Generator.
	List(ctx context.Context) *listing.PaginatingIterator[struct{}, *ListEndpointsResponse, ServingEndpoint]

	// Retrieve all serving endpoints.
	//
	// This method is generated by Databricks SDK Code Generator.
	ListAll(ctx context.Context) ([]ServingEndpoint, error)

	// 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.
	Logs(ctx context.Context, request LogsRequest) (*ServerLogsResponse, error)

	// 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.
	LogsByNameAndServedModelName(ctx context.Context, name string, servedModelName string) (*ServerLogsResponse, error)

	// Patch the tags of a serving endpoint.
	//
	// Used to batch add and delete tags from a serving endpoint with a single API
	// call.
	Patch(ctx context.Context, request PatchServingEndpointTags) ([]EndpointTag, error)

	// Update the rate limits of a serving endpoint.
	//
	// Used to update the rate limits of a serving endpoint. NOTE: only external and
	// foundation model endpoints are supported as of now.
	Put(ctx context.Context, request PutRequest) (*PutResponse, error)

	// Query a serving endpoint with provided model input.
	Query(ctx context.Context, request QueryEndpointInput) (*QueryEndpointResponse, error)

	// Set serving endpoint permissions.
	//
	// Sets permissions on a serving endpoint. Serving endpoints can inherit
	// permissions from their root object.
	SetPermissions(ctx context.Context, request ServingEndpointPermissionsRequest) (*ServingEndpointPermissions, error)

	// Update a serving endpoint with a new config.
	//
	// Updates any combination of the serving endpoint's served entities, the
	// compute configuration of those served entities, 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.
	UpdateConfig(ctx context.Context, endpointCoreConfigInput EndpointCoreConfigInput) (*WaitGetServingEndpointNotUpdating[ServingEndpointDetailed], error)

	// Calls [ServingEndpointsAPIInterface.UpdateConfig] and waits to reach NOT_UPDATING state
	//
	// You can override the default timeout of 20 minutes by calling adding
	// retries.Timeout[ServingEndpointDetailed](60*time.Minute) functional option.
	//
	// Deprecated: use [ServingEndpointsAPIInterface.UpdateConfig].Get() or [ServingEndpointsAPIInterface.WaitGetServingEndpointNotUpdating]
	UpdateConfigAndWait(ctx context.Context, endpointCoreConfigInput EndpointCoreConfigInput, options ...retries.Option[ServingEndpointDetailed]) (*ServingEndpointDetailed, error)

	// Update serving endpoint permissions.
	//
	// Updates the permissions on a serving endpoint. Serving endpoints can inherit
	// permissions from their root object.
	UpdatePermissions(ctx context.Context, request ServingEndpointPermissionsRequest) (*ServingEndpointPermissions, error)
}

type ServingEndpointsService 

type ServingEndpointsService interface {

	// 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.
	BuildLogs(ctx context.Context, request BuildLogsRequest) (*BuildLogsResponse, error)

	// Create a new serving endpoint.
	Create(ctx context.Context, request CreateServingEndpoint) (*ServingEndpointDetailed, error)

	// Delete a serving endpoint.
	Delete(ctx context.Context, request DeleteServingEndpointRequest) error

	// Retrieve the metrics associated with a serving endpoint.
	//
	// Retrieves the metrics associated with the provided serving endpoint in
	// either Prometheus or OpenMetrics exposition format.
	ExportMetrics(ctx context.Context, request ExportMetricsRequest) error

	// Get a single serving endpoint.
	//
	// Retrieves the details for a single serving endpoint.
	Get(ctx context.Context, request GetServingEndpointRequest) (*ServingEndpointDetailed, error)

	// Get serving endpoint permission levels.
	//
	// Gets the permission levels that a user can have on an object.
	GetPermissionLevels(ctx context.Context, request GetServingEndpointPermissionLevelsRequest) (*GetServingEndpointPermissionLevelsResponse, error)

	// Get serving endpoint permissions.
	//
	// Gets the permissions of a serving endpoint. Serving endpoints can inherit
	// permissions from their root object.
	GetPermissions(ctx context.Context, request GetServingEndpointPermissionsRequest) (*ServingEndpointPermissions, error)

	// Retrieve all serving endpoints.
	//
	// Use ListAll() to get all ServingEndpoint instances
	List(ctx context.Context) (*ListEndpointsResponse, error)

	// 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.
	Logs(ctx context.Context, request LogsRequest) (*ServerLogsResponse, error)

	// Patch the tags of a serving endpoint.
	//
	// Used to batch add and delete tags from a serving endpoint with a single
	// API call.
	Patch(ctx context.Context, request PatchServingEndpointTags) ([]EndpointTag, error)

	// Update the rate limits of a serving endpoint.
	//
	// Used to update the rate limits of a serving endpoint. NOTE: only external
	// and foundation model endpoints are supported as of now.
	Put(ctx context.Context, request PutRequest) (*PutResponse, error)

	// Query a serving endpoint with provided model input.
	Query(ctx context.Context, request QueryEndpointInput) (*QueryEndpointResponse, error)

	// Set serving endpoint permissions.
	//
	// Sets permissions on a serving endpoint. Serving endpoints can inherit
	// permissions from their root object.
	SetPermissions(ctx context.Context, request ServingEndpointPermissionsRequest) (*ServingEndpointPermissions, error)

	// Update a serving endpoint with a new config.
	//
	// Updates any combination of the serving endpoint's served entities, the
	// compute configuration of those served entities, 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.
	UpdateConfig(ctx context.Context, request EndpointCoreConfigInput) (*ServingEndpointDetailed, error)

	// Update serving endpoint permissions.
	//
	// Updates the permissions on a serving endpoint. Serving endpoints can
	// inherit permissions from their root object.
	UpdatePermissions(ctx context.Context, request ServingEndpointPermissionsRequest) (*ServingEndpointPermissions, error)
}

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 entities. A serving endpoint can have at most ten served entities. You can configure traffic settings to define how requests should be routed to your served entities behind an endpoint. Additionally, you can configure the scale of resources that should be applied to each served entity.

type TrafficConfig 

type TrafficConfig struct {
	// The list of routes that define traffic to each served entity.
	Routes []Route `json:"routes,omitempty"`
}

type V1ResponseChoiceElement added in v0.27.0 

type V1ResponseChoiceElement struct {
	// The finish reason returned by the endpoint.
	FinishReason string `json:"finishReason,omitempty"`
	// The index of the choice in the __chat or completions__ response.
	Index int `json:"index,omitempty"`
	// The logprobs returned only by the __completions__ endpoint.
	Logprobs int `json:"logprobs,omitempty"`
	// The message response from the __chat__ endpoint.
	Message *ChatMessage `json:"message,omitempty"`
	// The text response from the __completions__ endpoint.
	Text string `json:"text,omitempty"`

	ForceSendFields []string `json:"-"`
}

func (V1ResponseChoiceElement) MarshalJSON added in v0.27.0 

func (s V1ResponseChoiceElement) MarshalJSON() ([]byte, error)

func (*V1ResponseChoiceElement) UnmarshalJSON added in v0.27.0 

func (s *V1ResponseChoiceElement) UnmarshalJSON(b []byte) error

type WaitGetServingEndpointNotUpdating added in v0.10.0 

type WaitGetServingEndpointNotUpdating[R any] struct {
	Response *R
	Name     string `json:"name"`
	// contains filtered or unexported fields
}

WaitGetServingEndpointNotUpdating is a wrapper that calls ServingEndpointsAPI.WaitGetServingEndpointNotUpdating and waits to reach NOT_UPDATING state.

func (*WaitGetServingEndpointNotUpdating[R]) Get added in v0.10.0 

func (w *WaitGetServingEndpointNotUpdating[R]) Get() (*ServingEndpointDetailed, error)

Get the ServingEndpointDetailed with the default timeout of 20 minutes.

func (*WaitGetServingEndpointNotUpdating[R]) GetWithTimeout added in v0.10.0 

func (w *WaitGetServingEndpointNotUpdating[R]) GetWithTimeout(timeout time.Duration) (*ServingEndpointDetailed, error)

Get the ServingEndpointDetailed with custom timeout.

func (*WaitGetServingEndpointNotUpdating[R]) OnProgress added in v0.10.0 

func (w *WaitGetServingEndpointNotUpdating[R]) OnProgress(callback func(*ServingEndpointDetailed)) *WaitGetServingEndpointNotUpdating[R]

OnProgress invokes a callback every time it polls for the status update.

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.