public sealed class StreamingPredictRequest : IMessage<StreamingPredictRequest>, IEquatable<StreamingPredictRequest>, IDeepCloneable<StreamingPredictRequest>, IBufferMessage, IMessage
Reference documentation and code samples for the Vertex AI v1beta1 API class StreamingPredictRequest.
Request message for
[PredictionService.StreamingPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamingPredict].
The first message must contain
[endpoint][google.cloud.aiplatform.v1beta1.StreamingPredictRequest.endpoint]
field and optionally [input][]. The subsequent messages must contain
[input][].
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-14 UTC."],[[["\u003cp\u003eThis document provides reference information for the \u003ccode\u003eStreamingPredictRequest\u003c/code\u003e class within the Vertex AI v1beta1 API, specifically for the .NET environment.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eStreamingPredictRequest\u003c/code\u003e is used to send streaming prediction requests to the \u003ccode\u003ePredictionService\u003c/code\u003e, requiring an \u003ccode\u003eendpoint\u003c/code\u003e in the first message and subsequent \u003ccode\u003einput\u003c/code\u003e messages.\u003c/p\u003e\n"],["\u003cp\u003eThe class inherits from \u003ccode\u003eobject\u003c/code\u003e and implements multiple interfaces including \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eKey properties of \u003ccode\u003eStreamingPredictRequest\u003c/code\u003e include \u003ccode\u003eEndpoint\u003c/code\u003e (a string representing the endpoint name), \u003ccode\u003eEndpointAsEndpointName\u003c/code\u003e (an \u003ccode\u003eEndpointName\u003c/code\u003e-typed view), \u003ccode\u003eInputs\u003c/code\u003e (a \u003ccode\u003eRepeatedField\u003c/code\u003e for prediction input), and \u003ccode\u003eParameters\u003c/code\u003e (a \u003ccode\u003eTensor\u003c/code\u003e governing the prediction).\u003c/p\u003e\n"]]],[],null,[]]
