Package tensorflow.serving

Interface Predict.PredictRequest.RequestOptionsOrBuilder

All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
All Known Implementing Classes:
Predict.PredictRequest.RequestOptions, Predict.PredictRequest.RequestOptions.Builder
Enclosing class:
Predict.PredictRequest
public static interface Predict.PredictRequest.RequestOptionsOrBuilder extends com.google.protobuf.MessageOrBuilder

  • Method Summary

    Modifier and Type
    Method
    Description
    com.google.protobuf.ByteString
    getClientId()
    Client identifier to group requests belonging to a specific entity.
    Predict.PredictRequest.RequestOptions.DeterministicMode
    getDeterministicMode()
    optional .tensorflow.serving.PredictRequest.RequestOptions.DeterministicMode deterministic_mode = 2;
    int
    getDeterministicModeValue()
    optional .tensorflow.serving.PredictRequest.RequestOptions.DeterministicMode deterministic_mode = 2;
    boolean
    getReturnAdditionalArraysFromPrefill()
    Only supported in disaggregated serving.
    long
    getReturnStoptokens(int index)
    Returns these stop tokens in response if the model stops at them.
    int
    getReturnStoptokensCount()
    Returns these stop tokens in response if the model stops at them.
    List<Long>
    getReturnStoptokensList()
    Returns these stop tokens in response if the model stops at them.
    boolean
    hasClientId()
    Client identifier to group requests belonging to a specific entity.
    boolean
    hasDeterministicMode()
    optional .tensorflow.serving.PredictRequest.RequestOptions.DeterministicMode deterministic_mode = 2;
    boolean
    hasReturnAdditionalArraysFromPrefill()
    Only supported in disaggregated serving.

    Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder

    isInitialized

    Methods inherited from interface com.google.protobuf.MessageOrBuilder

    findInitializationErrors, getAllFields, getDefaultInstanceForType, getDescriptorForType, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof

  • Method Details

    • hasClientId

      boolean hasClientId()
       Client identifier to group requests belonging to a specific entity.
 Example entities can be product ids, service names, user ids etc.
 Servers can use this to optimize placement, caching and colocation.
      optional bytes client_id = 1;
      Returns:
      Whether the clientId field is set.

    • getClientId

      com.google.protobuf.ByteString getClientId()
       Client identifier to group requests belonging to a specific entity.
 Example entities can be product ids, service names, user ids etc.
 Servers can use this to optimize placement, caching and colocation.
      optional bytes client_id = 1;
      Returns:
      The clientId.

    • hasDeterministicMode

      boolean hasDeterministicMode()
      optional .tensorflow.serving.PredictRequest.RequestOptions.DeterministicMode deterministic_mode = 2;
      Returns:
      Whether the deterministicMode field is set.

    • getDeterministicModeValue

      int getDeterministicModeValue()
      optional .tensorflow.serving.PredictRequest.RequestOptions.DeterministicMode deterministic_mode = 2;
      Returns:
      The enum numeric value on the wire for deterministicMode.

    • getDeterministicMode

      Predict.PredictRequest.RequestOptions.DeterministicMode getDeterministicMode()
      optional .tensorflow.serving.PredictRequest.RequestOptions.DeterministicMode deterministic_mode = 2;
      Returns:
      The deterministicMode.

    • hasReturnAdditionalArraysFromPrefill

      boolean hasReturnAdditionalArraysFromPrefill()
       Only supported in disaggregated serving. When set, additional arrays from
 prefill will be returned if available.
      optional bool return_additional_arrays_from_prefill = 3;
      Returns:
      Whether the returnAdditionalArraysFromPrefill field is set.

    • getReturnAdditionalArraysFromPrefill

      boolean getReturnAdditionalArraysFromPrefill()
       Only supported in disaggregated serving. When set, additional arrays from
 prefill will be returned if available.
      optional bool return_additional_arrays_from_prefill = 3;
      Returns:
      The returnAdditionalArraysFromPrefill.

    • getReturnStoptokensList

      List<Long> getReturnStoptokensList()
       Returns these stop tokens in response if the model stops at them. The
 model may stop at other tokens, but will not return them in the response.
      repeated int64 return_stoptokens = 4;
      Returns:
      A list containing the returnStoptokens.

    • getReturnStoptokensCount

      int getReturnStoptokensCount()
       Returns these stop tokens in response if the model stops at them. The
 model may stop at other tokens, but will not return them in the response.
      repeated int64 return_stoptokens = 4;
      Returns:
      The count of returnStoptokens.

    • getReturnStoptokens

      long getReturnStoptokens(int index)
       Returns these stop tokens in response if the model stops at them. The
 model may stop at other tokens, but will not return them in the response.
      repeated int64 return_stoptokens = 4;
      Parameters:
      index - The index of the element to return.
      Returns:
      The returnStoptokens at the given index.