modelserving

type Ai21LabsConfig struct {
	// The <Databricks> secret key reference for an AI21 Labs API key. If you prefer
	// to paste your API key directly, see `ai21labs_api_key_plaintext`. You must
	// provide an API key using one of the following fields: `ai21labs_api_key` or
	// `ai21labs_api_key_plaintext`.
	Ai21labsApiKey *string
	// An AI21 Labs API key provided as a plaintext string. If you prefer to
	// reference your key using Databricks Secrets, see `ai21labs_api_key`. You must
	// provide an API key using one of the following fields: `ai21labs_api_key` or
	// `ai21labs_api_key_plaintext`.
	Ai21labsApiKeyPlaintext *string
}

type AiGatewayConfig struct {
	// Configuration to enable usage tracking using system tables. These tables
	// allow you to monitor operational usage on endpoints and their associated
	// costs.
	UsageTrackingConfig *UsageTrackingConfig
	// Configuration for payload logging using inference tables. Use these tables to
	// monitor and audit data being sent to and received from model APIs and to
	// improve model quality.
	InferenceTableConfig *InferenceTableConfig
	// Configuration for rate limits which can be set to limit endpoint traffic.
	RateLimits []AiGatewayRateLimit
	// Configuration for AI Guardrails to prevent unwanted data and unsafe data in
	// requests and responses.
	Guardrails *AiGuardrails
	// Configuration for traffic fallback which auto fallbacks to other served
	// entities if the request to a served entity fails with certain error codes, to
	// increase availability.
	FallbackConfig *FallbackConfig
}

type AiGatewayRateLimit struct {
	// Used to specify how many calls are allowed for a key within the
	// renewal_period.
	Calls *int64
	// Key field for a rate limit. Currently, 'user', 'user_group,
	// 'service_principal', and 'endpoint' are supported, with 'endpoint' being the
	// default if not specified.
	Key *string
	// Renewal period field for a rate limit. Currently, only 'minute' is supported.
	RenewalPeriod *string
	// Principal field for a user, user group, or service principal to apply rate
	// limiting to. Accepts a user email, group name, or service principal
	// application ID.
	Principal *string
	// Used to specify how many tokens are allowed for a key within the
	// renewal_period.
	Tokens *int64
}

type AiGuardrailParameters struct {
	// Indicates whether the safety filter is enabled.
	Safety *bool
	// Configuration for guardrail PII filter.
	Pii *PiiSettings
	// The list of allowed topics. Given a chat request, this guardrail flags the
	// request if its topic is not in the allowed topics.
	ValidTopics []string
	// List of invalid keywords. AI guardrail uses keyword or string matching to
	// decide if the keyword exists in the request or response content.
	InvalidKeywords []string
}

type AiGuardrails struct {
	// Configuration for input guardrail filters.
	Input *AiGuardrailParameters
	// Configuration for output guardrail filters.
	Output *AiGuardrailParameters
}

type AmazonBedrockConfig struct {
	// The AWS region to use. Bedrock has to be enabled there.
	AwsRegion *string
	// The <Databricks> secret key reference for an AWS access key ID with
	// permissions to interact with Bedrock services. If you prefer to paste your
	// API key directly, see `aws_access_key_id_plaintext`. You must provide an API
	// key using one of the following fields: `aws_access_key_id` or
	// `aws_access_key_id_plaintext`.
	AwsAccessKeyId *string
	// The <Databricks> secret key reference for an AWS secret access key paired
	// with the access key ID, with permissions to interact with Bedrock services.
	// If you prefer to paste your API key directly, see
	// `aws_secret_access_key_plaintext`. You must provide an API key using one of
	// the following fields: `aws_secret_access_key` or
	// `aws_secret_access_key_plaintext`.
	AwsSecretAccessKey *string
	// The underlying provider in Amazon Bedrock. Supported values (case
	// insensitive) include: Anthropic, Cohere, AI21Labs, Amazon.
	BedrockProvider *string
	// An AWS access key ID with permissions to interact with Bedrock services
	// provided as a plaintext string. If you prefer to reference your key using
	// Databricks Secrets, see `aws_access_key_id`. You must provide an API key
	// using one of the following fields: `aws_access_key_id` or
	// `aws_access_key_id_plaintext`.
	AwsAccessKeyIdPlaintext *string
	// An AWS secret access key paired with the access key ID, with permissions to
	// interact with Bedrock services provided as a plaintext string. If you prefer
	// to reference your key using Databricks Secrets, see `aws_secret_access_key`.
	// You must provide an API key using one of the following fields:
	// `aws_secret_access_key` or `aws_secret_access_key_plaintext`.
	AwsSecretAccessKeyPlaintext *string
	// ARN of the instance profile that the external model will use to access AWS
	// resources. You must authenticate using an instance profile or access keys. If
	// you prefer to authenticate using access keys, see `aws_access_key_id`,
	// `aws_access_key_id_plaintext`, `aws_secret_access_key` and
	// `aws_secret_access_key_plaintext`.
	InstanceProfileArn *string
}

type AnthropicConfig struct {
	// The <Databricks> secret key reference for an Anthropic API key. If you prefer
	// to paste your API key directly, see `anthropic_api_key_plaintext`. You must
	// provide an API key using one of the following fields: `anthropic_api_key` or
	// `anthropic_api_key_plaintext`.
	AnthropicApiKey *string
	// The Anthropic API key provided as a plaintext string. If you prefer to
	// reference your key using Databricks Secrets, see `anthropic_api_key`. You
	// must provide an API key using one of the following fields:
	// `anthropic_api_key` or `anthropic_api_key_plaintext`.
	AnthropicApiKeyPlaintext *string
}

type ApiKeyAuth struct {
	// The name of the API key parameter used for authentication.
	Key *string
	// The <Databricks> secret key reference for an API Key. If you prefer to paste
	// your token directly, see `value_plaintext`.
	Value *string
	// The API Key provided as a plaintext string. If you prefer to reference your
	// token using Databricks Secrets, see `value`.
	ValuePlaintext *string
}

type AutoCaptureState struct {
	PayloadTable *PayloadTable
}

type BearerTokenAuth struct {
	// The <Databricks> secret key reference for a token. If you prefer to paste
	// your token directly, see `token_plaintext`.
	Token *string
	// The token provided as a plaintext string. If you prefer to reference your
	// token using Databricks Secrets, see `token`.
	TokenPlaintext *string
}

type Behavior string

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

type CohereConfig struct {
	// The <Databricks> secret key reference for a Cohere API key. If you prefer to
	// paste your API key directly, see `cohere_api_key_plaintext`. You must provide
	// an API key using one of the following fields: `cohere_api_key` or
	// `cohere_api_key_plaintext`.
	CohereApiKey *string
	// The Cohere API key provided as a plaintext string. If you prefer to reference
	// your key using Databricks Secrets, see `cohere_api_key`. You must provide an
	// API key using one of the following fields: `cohere_api_key` or
	// `cohere_api_key_plaintext`.
	CohereApiKeyPlaintext *string
	// This is an optional field to provide a customized base URL for the Cohere
	// API. If left unspecified, the standard Cohere base URL is used.
	CohereApiBase *string
}

type CreateInferenceEndpointRequest struct {
	// The name of the serving endpoint. This field is required and must be unique
	// across a <Workspace>. An endpoint name can consist of alphanumeric
	// characters, dashes, and underscores.
	Name *string
	// The core config of the serving endpoint.
	Config *EndpointCoreConfig
	// Tags to be attached to the serving endpoint and automatically propagated to
	// billing logs.
	Tags []EndpointTag
	// Enable route optimization for the serving endpoint.
	RouteOptimized *bool
	// Rate limits to be applied to the serving endpoint. NOTE: this field is
	// deprecated, please use AI Gateway to manage rate limits.
	RateLimits []RateLimit
	// The AI Gateway configuration for the serving endpoint. NOTE: External model,
	// provisioned throughput, and pay-per-token endpoints are fully supported;
	// agent endpoints currently only support inference tables.
	AiGateway *AiGatewayConfig
	// The budget policy to be applied to the serving endpoint.
	BudgetPolicyId *string
	// Email notification settings.
	EmailNotifications *EmailNotifications
	Description        *string
	// Configuration for persisting endpoint telemetry (logs, traces, and metrics)
	// to Unity Catalog tables.
	TelemetryConfig *TelemetryConfig
}

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

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

type CreatePtEndpointRequest struct {
	// The name of the serving endpoint. This field is required and must be unique
	// across a <Workspace>. An endpoint name can consist of alphanumeric
	// characters, dashes, and underscores.
	Name *string
	// The core config of the serving endpoint.
	Config *PtEndpointCoreConfig
	// Tags to be attached to the serving endpoint and automatically propagated to
	// billing logs.
	Tags []EndpointTag
	// The AI Gateway configuration for the serving endpoint.
	AiGateway *AiGatewayConfig
	// The budget policy associated with the endpoint.
	BudgetPolicyId *string
	// Email notification settings.
	EmailNotifications *EmailNotifications
}

type CustomProviderConfig struct {
	// This is a field to provide the URL of the custom provider API.
	CustomProviderUrl *string
	// This is a field to provide bearer token authentication for the custom
	// provider API. You can only specify one authentication method.
	BearerTokenAuth *BearerTokenAuth
	// This is a field to provide API key authentication for the custom provider
	// API. You can only specify one authentication method.
	ApiKeyAuth *ApiKeyAuth
}

type DataPlaneInfo struct {
	// The URL of the endpoint for this operation in the dataplane.
	EndpointUrl *string
	// Authorization details as a string.
	AuthorizationDetails *string
}

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. If you prefer to paste
	// your API key directly, see `databricks_api_token_plaintext`. You must provide
	// an API key using one of the following fields: `databricks_api_token` or
	// `databricks_api_token_plaintext`.
	DatabricksApiToken *string
	// The URL of the <Databricks> workspace containing the model serving endpoint
	// pointed to by this external model.
	DatabricksWorkspaceUrl *string
	// The 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 provided as a plaintext string. If you prefer to reference your key
	// using Databricks Secrets, see `databricks_api_token`. You must provide an API
	// key using one of the following fields: `databricks_api_token` or
	// `databricks_api_token_plaintext`.
	DatabricksApiTokenPlaintext *string
}

type DeleteInferenceEndpointRequest struct {
	Name *string
}

type DeleteInferenceEndpointResponse struct {
}

type EmailNotifications struct {
	// A list of email addresses to be notified when an endpoint successfully
	// updates its configuration or state.
	OnUpdateSuccess []string
	// A list of email addresses to be notified when an endpoint fails to update its
	// configuration or state.
	OnUpdateFailure []string
}

type EndpointCoreConfig struct {
	// The list of served entities under the serving endpoint config.
	ServedEntities []ServedModel
	// (Deprecated, use served_entities instead) The list of served models under the
	// serving endpoint config.
	ServedModels []ServedModel
	// The traffic configuration associated with the serving endpoint config.
	TrafficConfig *TrafficConfig
	// Configuration for legacy Inference Tables which automatically log requests
	// and responses to Unity Catalog. Deprecated: please use AI Gateway inference
	// tables instead. See
	// https://docs.databricks.com/aws/en/ai-gateway/inference-tables.
	AutoCaptureConfig *AutoCaptureConfig
}

type EndpointCoreConfigOutput struct {
	// The config version that the serving endpoint is currently serving.
	ConfigVersion *int64
	// The list of served entities under the serving endpoint config.
	ServedEntities []ServedModel
	// (Deprecated, use served_entities instead) The list of served models under the
	// serving endpoint config.
	ServedModels []ServedModel
	// The traffic configuration associated with the serving endpoint config.
	TrafficConfig *TrafficConfig
	// Configuration for legacy Inference Tables which automatically log requests
	// and responses to Unity Catalog. Deprecated: please use AI Gateway inference
	// tables instead. See
	// https://docs.databricks.com/aws/en/ai-gateway/inference-tables.
	AutoCaptureConfig *AutoCaptureConfig
}

type EndpointCoreConfigSummary struct {
	// The list of served entities under the serving endpoint config.
	ServedEntities []ServedModelLite
	// (Deprecated, use served_entities instead) The list of served models under the
	// serving endpoint config.
	ServedModels []ServedModelLite
}

type EndpointTag struct {
	// Key field for a serving endpoint tag.
	Key *string
	// Optional value field for a serving endpoint tag.
	Value *string
}

type ExportMetricsResponse struct {
	Contents io.ReadCloser
}

type ExternalFunctionRequest struct {
	// The connection name to use. This is required to identify the external
	// connection.
	ConnectionName *string
	// The HTTP method to use (e.g., 'GET', 'POST').
	Method ExternalFunctionRequest_HttpMethod
	// The relative path for the API endpoint. This is required.
	Path *string
	// The JSON payload to send in the request body.
	Json *string
	// Additional headers for the request. If not provided, only auth headers from
	// connections would be passed.
	Headers *string
	// Query parameters for the request.
	Params *string
	// Optional subdomain to prepend to the connection URL's host. If provided, this
	// will be added as a prefix to the connection URL's host. For example, if the
	// connection URL is `https://api.example.com/v1` and `sub_domain` is
	// `"custom"`, the resulting URL will be `https://custom.api.example.com/v1`.
	SubDomain *string
}

type ExternalFunctionRequest_HttpMethod string

type ExternalFunctionResponse struct {
	Contents io.ReadCloser
}

type ExternalModel struct {
	// The name of the provider for the external model. Currently, the supported
	// providers are 'ai21labs', 'anthropic', 'amazon-bedrock', 'cohere',
	// 'databricks-model-serving', 'google-cloud-vertex-ai', 'openai', 'palm', and
	// 'custom'.
	Provider *string
	// The name of the external model.
	Name *string
	// The task type of the external model.
	Task *string
	// external model config. The config corresponding to the provider will be used.
	Config isExternalModel_Config
}

type ExternalModel_Config_Ai21labsConfig struct {
	Ai21labsConfig Ai21LabsConfig
}

type ExternalModel_Config_AmazonBedrockConfig struct {
	AmazonBedrockConfig AmazonBedrockConfig
}

type ExternalModel_Config_AnthropicConfig struct {
	AnthropicConfig AnthropicConfig
}

type ExternalModel_Config_CohereConfig struct {
	CohereConfig CohereConfig
}

type ExternalModel_Config_CustomProviderConfig struct {
	CustomProviderConfig CustomProviderConfig
}

type ExternalModel_Config_DatabricksModelServingConfig struct {
	DatabricksModelServingConfig DatabricksModelServingConfig
}

type ExternalModel_Config_GoogleCloudVertexAiConfig struct {
	GoogleCloudVertexAiConfig GoogleCloudVertexAiConfig
}

type ExternalModel_Config_OpenaiConfig struct {
	OpenaiConfig OpenAiConfig
}

type ExternalModel_Config_PalmConfig struct {
	PalmConfig PaLmConfig
}

type FallbackConfig struct {
	// Whether to enable traffic fallback. When a served entity in the serving
	// endpoint returns specific error codes (e.g. 500), the request will
	// automatically be round-robin attempted with other served entities in the same
	// endpoint, following the order of served entity list, until a successful
	// response is returned. If all attempts fail, return the last response with the
	// error code.
	Enabled *bool
}

type FoundationModel struct {
	Name        *string
	DisplayName *string
	Docs        *string
	Description *string
}

type GetExportEndpointMetricsRequest struct {
	// The name of the serving endpoint to retrieve metrics for. This field is
	// required.
	Name *string
}

type GetInferenceEndpointRequest struct {
	// The name of the serving endpoint. This field is required.
	Name *string
}

type GetInferenceEndpointSchemaRequest struct {
	// The name of the serving endpoint that the served model belongs to. This field
	// is required.
	Name *string
}

type GetOpenApiResponse struct {
	Contents io.ReadCloser
}

type GetServedModelBuildLogsRequest struct {
	// The name of the serving endpoint that the served model belongs to. This field
	// is required.
	Name *string
	// The name of the served model that build logs will be retrieved for. This
	// field is required.
	ServedModelName *string
}

type GetServedModelBuildLogsResponse struct {
	// The logs associated with building the served entity's environment.
	Logs *string
}

type GetServedModelLogsRequest struct {
	// The name of the serving endpoint that the served model belongs to. This field
	// is required.
	Name *string
	// The name of the served model that logs will be retrieved for. This field is
	// required.
	ServedModelName *string
}

type GetServedModelLogsResponse struct {
	// The most recent log lines of the model server processing invocation requests.
	Logs *string
}

type GoogleCloudVertexAiConfig struct {
	// The <Databricks> secret key reference for a private key for the service
	// account which has access to the Google Cloud Vertex AI Service. See [Best
	// practices for managing service account keys]. If you prefer to paste your API
	// key directly, see `private_key_plaintext`. You must provide an API key using
	// one of the following fields: `private_key` or `private_key_plaintext`
	//
	// [Best practices for managing service account keys]:
	// https://cloud.google.com/iam/docs/best-practices-for-managing-service-account-keys
	PrivateKey *string
	// This is the Google Cloud project id that the service account is associated
	// with.
	ProjectId *string
	// This is the region for the Google Cloud Vertex AI Service. See [supported
	// regions] for more details. Some models are only available in specific
	// regions.
	//
	// [supported regions]:
	// https://cloud.google.com/vertex-ai/docs/general/locations
	Region *string
	// The private key for the service account which has access to the Google Cloud
	// Vertex AI Service provided as a plaintext secret. See [Best practices for
	// managing service account keys]. If you prefer to reference your key using
	// Databricks Secrets, see `private_key`. You must provide an API key using one
	// of the following fields: `private_key` or `private_key_plaintext`.
	//
	// [Best practices for managing service account keys]:
	// https://cloud.google.com/iam/docs/best-practices-for-managing-service-account-keys
	PrivateKeyPlaintext *string
}

type InferenceEndpoint struct {
	// The name of the serving endpoint.
	Name *string
	// The email of the user who created the serving endpoint.
	Creator *string
	// The timestamp when the endpoint was created in Unix time.
	CreationTimestamp *int64
	// The timestamp when the endpoint was last updated by a user in Unix time.
	LastUpdatedTimestamp *int64
	// Information corresponding to the state of the serving endpoint.
	State *InferenceEndpointState
	// The config that is currently being served by the endpoint.
	Config *EndpointCoreConfigSummary
	// Tags attached to the serving endpoint.
	Tags []EndpointTag
	// System-generated ID of the endpoint, included to be used by the Permissions
	// API.
	Id *string
	// The task type of the serving endpoint.
	Task *string
	// The AI Gateway configuration for the serving endpoint. NOTE: External model,
	// provisioned throughput, and pay-per-token endpoints are fully supported;
	// agent endpoints currently only support inference tables.
	AiGateway *AiGatewayConfig
	// The budget policy associated with the endpoint.
	BudgetPolicyId *string
	// Description of the endpoint
	Description *string
	// The usage policy associated with serving endpoint.
	UsagePolicyId *string
	// Telemetry configuration for the endpoint, including inference-table payload
	// logging.
	TelemetryConfig *TelemetryConfig
}

type InferenceEndpointDetailed struct {
	// The name of the serving endpoint.
	Name *string
	// The email of the user who created the serving endpoint.
	Creator *string
	// The timestamp when the endpoint was created in Unix time.
	CreationTimestamp *int64
	// The timestamp when the endpoint was last updated by a user in Unix time.
	LastUpdatedTimestamp *int64
	// Information corresponding to the state of the serving endpoint.
	State *InferenceEndpointState
	// The config that is currently being served by the endpoint.
	Config *EndpointCoreConfigOutput
	// The config that the endpoint is attempting to update to.
	PendingConfig *PendingConfig
	// System-generated ID of the endpoint. This is used to refer to the endpoint in
	// the Permissions API
	Id *string
	// The permission level of the principal making the request.
	PermissionLevel ServingEndpointDetailedPermissionLevel
	// Tags attached to the serving endpoint.
	Tags []EndpointTag
	// The task type of the serving endpoint.
	Task *string
	// Boolean representing if route optimization has been enabled for the endpoint
	RouteOptimized *bool
	// Endpoint invocation url if route optimization is enabled for endpoint
	EndpointUrl *string
	// Information required to query DataPlane APIs.
	DataPlaneInfo *ModelDataPlaneInfo
	// The AI Gateway configuration for the serving endpoint. NOTE: External model,
	// provisioned throughput, and pay-per-token endpoints are fully supported;
	// agent endpoints currently only support inference tables.
	AiGateway *AiGatewayConfig
	// The budget policy associated with the endpoint.
	BudgetPolicyId *string
	// Email notification settings.
	EmailNotifications *EmailNotifications
	// Description of the serving model
	Description *string
	// Telemetry configuration for the endpoint, including inference-table payload
	// logging.
	TelemetryConfig *TelemetryConfig
}

type InferenceEndpointState struct {
	// 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 InferenceEndpointState_ReadyState
	// 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 InferenceEndpointState_ConfigUpdateState
}

type InferenceEndpointState_ConfigUpdateState string

type InferenceEndpointState_ReadyState string

type InferenceTableConfig struct {
	// The name of the catalog in Unity Catalog. Required when enabling inference
	// tables. NOTE: On update, you have to disable inference table first in order
	// to change the catalog name.
	CatalogName *string
	// The name of the schema in Unity Catalog. Required when enabling inference
	// tables. NOTE: On update, you have to disable inference table first in order
	// to change the schema name.
	SchemaName *string
	// The prefix of the table in Unity Catalog. NOTE: On update, you have to
	// disable inference table first in order to change the prefix name.
	TableNamePrefix *string
	// Indicates whether the inference table is enabled.
	Enabled *bool
}

type ListInferenceEndpointsRequest struct {
}

type ListInferenceEndpointsResponse struct {
	// The list of endpoints.
	Endpoints []InferenceEndpoint
}

type ModelDataPlaneInfo struct {
	// Information required to query DataPlane API 'query' endpoint.
	QueryInfo *DataPlaneInfo
}

type OpenAiConfig struct {
	// The <Databricks> secret key reference for an OpenAI API key using the OpenAI
	// or Azure service. If you prefer to paste your API key directly, see
	// `openai_api_key_plaintext`. You must provide an API key using one of the
	// following fields: `openai_api_key` or `openai_api_key_plaintext`.
	OpenaiApiKey *string
	// 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
	// This is a field to provide a customized base URl for the OpenAI API. For
	// Azure OpenAI, this field is required, and is the base URL for the Azure
	// OpenAI API service provided by Azure. For other OpenAI API types, this field
	// is optional, and if left unspecified, the standard OpenAI base URL is used.
	OpenaiApiBase *string
	// 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
	// This field is only required for Azure OpenAI and is the name of the
	// deployment resource for the Azure OpenAI service.
	OpenaiDeploymentName *string
	// This is an optional field to specify the organization in OpenAI or Azure
	// OpenAI.
	OpenaiOrganization *string
	// This field is only required for Azure AD OpenAI and is the Microsoft Entra
	// Tenant ID.
	MicrosoftEntraTenantId *string
	// This field is only required for Azure AD OpenAI and is the Microsoft Entra
	// Client ID.
	MicrosoftEntraClientId *string
	// The <Databricks> secret key reference for a client secret used for Microsoft
	// Entra ID authentication. If you prefer to paste your client secret directly,
	// see `microsoft_entra_client_secret_plaintext`. You must provide an API key
	// using one of the following fields: `microsoft_entra_client_secret` or
	// `microsoft_entra_client_secret_plaintext`.
	MicrosoftEntraClientSecret *string
	// The OpenAI API key using the OpenAI or Azure service provided as a plaintext
	// string. If you prefer to reference your key using Databricks Secrets, see
	// `openai_api_key`. You must provide an API key using one of the following
	// fields: `openai_api_key` or `openai_api_key_plaintext`.
	OpenaiApiKeyPlaintext *string
	// The client secret used for Microsoft Entra ID authentication provided as a
	// plaintext string. If you prefer to reference your key using Databricks
	// Secrets, see `microsoft_entra_client_secret`. You must provide an API key
	// using one of the following fields: `microsoft_entra_client_secret` or
	// `microsoft_entra_client_secret_plaintext`.
	MicrosoftEntraClientSecretPlaintext *string
}

type PaLmConfig struct {
	// The <Databricks> secret key reference for a PaLM API key. If you prefer to
	// paste your API key directly, see `palm_api_key_plaintext`. You must provide
	// an API key using one of the following fields: `palm_api_key` or
	// `palm_api_key_plaintext`.
	PalmApiKey *string
	// The PaLM API key provided as a plaintext string. If you prefer to reference
	// your key using Databricks Secrets, see `palm_api_key`. You must provide an
	// API key using one of the following fields: `palm_api_key` or
	// `palm_api_key_plaintext`.
	PalmApiKeyPlaintext *string
}

type PatchInferenceEndpointTagsRequest struct {
	// The name of the serving endpoint who's tags to patch. This field is required.
	Name *string
	// List of endpoint tags to add
	AddTags []EndpointTag
	// List of tag keys to delete
	DeleteTags []string
}

type PatchInferenceEndpointTagsResponse struct {
	Tags []EndpointTag
}

type PatchInferenceEndpointTelemetryConfigRequest struct {
	// The name of the serving endpoint whose telemetry configuration is being
	// updated. This field is required.
	Name *string
	// The telemetry configuration to be applied to the serving endpoint. Can
	// specify either a telemetry_profile_id to use an existing profile, or
	// table_names to create a new profile with the specified Unity Catalog tables.
	// If not provided, the telemetry configuration will be removed from the
	// endpoint.
	TelemetryConfig *TelemetryConfig
}

type PayloadTable struct {
	Name          *string
	Status        *string
	StatusMessage *string
}

type PendingConfig struct {
	// The list of served entities belonging to the last issued update to the
	// serving endpoint.
	ServedEntities []ServedModel
	// (Deprecated, use served_entities instead) The list of served models belonging
	// to the last issued update to the serving endpoint.
	ServedModels []ServedModel
	// The traffic config defining how invocations to the serving endpoint should be
	// routed.
	TrafficConfig *TrafficConfig
	// The config version that the serving endpoint is currently serving.
	ConfigVersion *int
	// The timestamp when the update to the pending config started.
	StartTime *int64
	// Configuration for legacy Inference Tables which automatically log requests
	// and responses to Unity Catalog. Deprecated: please use AI Gateway inference
	// tables instead. See
	// https://docs.databricks.com/aws/en/ai-gateway/inference-tables.
	AutoCaptureConfig *AutoCaptureConfig
}

type PiiSettings struct {
	// Configuration for input guardrail filters.
	Behavior Behavior
}

type PtEndpointCoreConfig struct {
	// The list of served entities under the serving endpoint config.
	ServedEntities []PtServedModel
	TrafficConfig  *TrafficConfig
}

type PtServedModel struct {
	// 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
	// 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
	EntityVersion *string
	// The number of model units to be provisioned.
	ProvisionedModelUnits *int64
	// Whether burst scaling is enabled. When enabled (default), the endpoint can
	// automatically scale up beyond provisioned capacity to handle traffic spikes.
	// When disabled, the endpoint maintains fixed capacity at
	// provisioned_model_units.
	BurstScalingEnabled *bool
}

type PutInferenceEndpointAiGatewayRequest struct {
	// The name of the serving endpoint whose AI Gateway is being updated. This
	// field is required.
	Name *string
	// Configuration to enable usage tracking using system tables. These tables
	// allow you to monitor operational usage on endpoints and their associated
	// costs.
	UsageTrackingConfig *UsageTrackingConfig
	// Configuration for payload logging using inference tables. Use these tables to
	// monitor and audit data being sent to and received from model APIs and to
	// improve model quality.
	InferenceTableConfig *InferenceTableConfig
	// Configuration for rate limits which can be set to limit endpoint traffic.
	RateLimits []AiGatewayRateLimit
	// Configuration for AI Guardrails to prevent unwanted data and unsafe data in
	// requests and responses.
	Guardrails *AiGuardrails
	// Configuration for traffic fallback which auto fallbacks to other served
	// entities if the request to a served entity fails with certain error codes, to
	// increase availability.
	FallbackConfig *FallbackConfig
}

type PutInferenceEndpointAiGatewayResponse struct {
	// Configuration to enable usage tracking using system tables. These tables
	// allow you to monitor operational usage on endpoints and their associated
	// costs.
	UsageTrackingConfig *UsageTrackingConfig
	// Configuration for payload logging using inference tables. Use these tables to
	// monitor and audit data being sent to and received from model APIs and to
	// improve model quality.
	InferenceTableConfig *InferenceTableConfig
	// Configuration for rate limits which can be set to limit endpoint traffic.
	RateLimits []AiGatewayRateLimit
	// Configuration for AI Guardrails to prevent unwanted data and unsafe data in
	// requests and responses.
	Guardrails *AiGuardrails
	// Configuration for traffic fallback which auto fallbacks to other served
	// entities if the request to a served entity fails with certain error codes, to
	// increase availability.
	FallbackConfig *FallbackConfig
}

type PutInferenceEndpointConfigRequest struct {
	// The name of the serving endpoint to update. This field is required.
	Name *string
	// The list of served entities under the serving endpoint config.
	ServedEntities []ServedModel
	// (Deprecated, use served_entities instead) The list of served models under the
	// serving endpoint config.
	ServedModels []ServedModel
	// The traffic configuration associated with the serving endpoint config.
	TrafficConfig *TrafficConfig
	// Configuration for legacy Inference Tables which automatically log requests
	// and responses to Unity Catalog. Deprecated: please use AI Gateway inference
	// tables instead. See
	// https://docs.databricks.com/aws/en/ai-gateway/inference-tables.
	AutoCaptureConfig *AutoCaptureConfig
}

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

type PutInferenceEndpointRateLimitsRequest struct {
	// The name of the serving endpoint whose rate limits are being updated. This
	// field is required.
	Name *string
	// The list of endpoint rate limits.
	RateLimits []RateLimit
}

type PutInferenceEndpointRateLimitsResponse struct {
	// The list of endpoint rate limits.
	RateLimits []RateLimit
}

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

type PutPtEndpointConfigRequest struct {
	// The name of the pt endpoint to update. This field is required.
	Name   *string
	Config *PtEndpointCoreConfig
}

type RateLimit struct {
	// Used to specify how many calls are allowed for a key within the
	// renewal_period.
	Calls *int64
	// Key field for a serving endpoint rate limit. Currently, only 'user' and
	// 'endpoint' are supported, with 'endpoint' being the default if not specified.
	Key *string
	// Renewal period field for a serving endpoint rate limit. Currently, only
	// 'minute' is supported.
	RenewalPeriod *string
}

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

type ServedModel struct {
	// 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
	// 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. For an existing
	// endpoint with external_model, it cannot 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. The task type of all external
	// models within an endpoint must be the same.
	ExternalModel *ExternalModel
	// 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
	EntityVersion *string
	// The minimum tokens per second that the endpoint can scale down to.
	MinProvisionedThroughput *int
	// The maximum tokens per second that the endpoint can scale up to.
	MaxProvisionedThroughput *int
	// The minimum provisioned concurrency that the endpoint can scale down to. Do
	// not use if workload_size is specified.
	MinProvisionedConcurrency *int
	// The maximum provisioned concurrency that the endpoint can scale up to. Do not
	// use if workload_size is specified.
	MaxProvisionedConcurrency *int
	// 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).
	// Additional custom workload sizes can also be used when available in the
	// workspace. If scale-to-zero is enabled, the lower bound of the provisioned
	// concurrency for each workload size is 0. Do not use if
	// min_provisioned_concurrency and max_provisioned_concurrency are specified.
	WorkloadSize *string
	// The number of model units provisioned.
	ProvisionedModelUnits *int64
	// Whether burst scaling is enabled. When enabled (default), the endpoint can
	// automatically scale up beyond provisioned capacity to handle traffic spikes.
	// When disabled, the endpoint maintains fixed capacity at
	// provisioned_model_units.
	BurstScalingEnabled *bool
	// Whether the compute resources for the served entity should scale down to
	// zero.
	ScaleToZeroEnabled *bool
	ModelName          *string
	ModelVersion       *string
	// 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
	// ARN of the instance profile that the served entity uses to access AWS
	// resources.
	InstanceProfileArn *string
	FoundationModel    *FoundationModel
	State              *ServedModelState
	Creator            *string
	CreationTimestamp  *int64
}

type ServedModelDeploymentState string

type ServedModelLite struct {
	Name *string
	// Only one of model_name and entity_name should be populated
	ModelName  *string
	EntityName *string
	// Only one of model_version and entity_version should be populated
	ModelVersion    *string
	EntityVersion   *string
	ExternalModel   *ExternalModel
	FoundationModel *FoundationModel
}

type ServedModelState struct {
	Deployment             ServedModelDeploymentState
	DeploymentStateMessage *string
}

type ServingEndpointDetailedPermissionLevel string

type TelemetryConfig struct {
	TelemetryProfile isTelemetryConfig_TelemetryProfile
	// Configuration for inference table payload logging, including sampling.
	InferenceTableConfig *TelemetryInferenceTableConfig
	// The telemetry signals to enable for this endpoint. If empty or omitted, all
	// signals are enabled; otherwise only the listed signals are enabled.
	EnabledTelemetryFeatures []TelemetryFeature
}

type TelemetryConfig_TelemetryProfile_TableNames struct {
	TableNames UnityCatalogTableNames
}

type TelemetryConfig_TelemetryProfile_TelemetryProfileId struct {
	TelemetryProfileId string
}

type TelemetryFeature string

type TelemetryInferenceTableConfig struct {
	// Fraction of requests sampled for payload logging, in the range [0.0, 1.0],
	// where 1.0 logs all requests.
	SamplingFraction *float64
	// The full name of the inference table created for this endpoint.
	Name *string
}

type TrafficConfig struct {
	// The list of routes that define traffic to each served entity.
	Routes []Route
}

type UnityCatalogTableNames struct {
	// The full three-level Unity Catalog name (catalog.schema.table) of the table
	// that receives exported logs.
	LogsTable *string
	// The full three-level Unity Catalog name (catalog.schema.table) of the table
	// that receives exported metrics.
	MetricsTable *string
	// The full three-level Unity Catalog name (catalog.schema.table) of the table
	// that receives exported traces (spans).
	TracesTable *string
	// The full three-level Unity Catalog name (catalog.schema.table) of the table
	// that receives exported annotations.
	AnnotationsTable *string
}

type UpdateInferenceEndpointNotificationsRequest struct {
	// The name of the serving endpoint whose notifications are being updated. This
	// field is required.
	Name *string
	// The email notification settings to update. Specify email addresses to notify
	// when endpoint state changes occur.
	EmailNotifications *EmailNotifications
}

type UpdateInferenceEndpointNotificationsResponse struct {
	Name               *string
	EmailNotifications *EmailNotifications
}

type UsageTrackingConfig struct {
	// Whether to enable usage tracking.
	Enabled *bool
}