Databricks SDK for JavaScript
    Preparing search index...

    Interface EndpointThroughputInfo

    Throughput information for an AI Search endpoint, including requested and current concurrency settings.

    interface EndpointThroughputInfo {
        changeRequestMessage?: string;
        changeRequestState?: ThroughputChangeRequestState;
        currentConcurrency?: number;
        currentConcurrencyUtilizationPercentage?: number;
        currentNumReplicas?: number;
        maximumConcurrencyAllowed?: number;
        minimalConcurrencyAllowed?: number;
        requestedConcurrency?: number;
        requestedNumReplicas?: number;
    }
    Index

    Properties

    changeRequestMessage?: string

    Additional information about the throughput change request

    changeRequestState?: ThroughputChangeRequestState

    The state of the most recent throughput change request

    currentConcurrency?: number

    The current concurrency (total CPU) allocated to the endpoint

    currentConcurrencyUtilizationPercentage?: number

    The current utilization of concurrency as a percentage (0-100)

    currentNumReplicas?: number

    The current number of replicas allocated to the endpoint

    maximumConcurrencyAllowed?: number

    The maximum concurrency allowed for this endpoint

    minimalConcurrencyAllowed?: number

    The minimum concurrency allowed for this endpoint

    requestedConcurrency?: number

    The requested concurrency (total CPU) for the endpoint

    requestedNumReplicas?: number

    The requested number of replicas for the endpoint