public sealed class TopNMetrics : IMessage<SmartReplyMetrics.Types.TopNMetrics>, IEquatable<SmartReplyMetrics.Types.TopNMetrics>, IDeepCloneable<SmartReplyMetrics.Types.TopNMetrics>, IBufferMessage, IMessage
Evaluation metrics when retrieving n smart replies with the model.
Number of retrieved smart replies. For example, when n is 3, this
evaluation contains metrics for when Dialogflow retrieves 3 smart replies
with the model.
Defined as number of queries whose top n smart replies have at least one
similar (token match similarity above the defined threshold) reply as the
real reply divided by number of queries with at least one smart reply.
Value ranges from 0.0 to 1.0 inclusive.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-03-21 UTC."],[[["The `TopNMetrics` class provides evaluation metrics for retrieving a specified number (`n`) of smart replies from a Dialogflow model."],["This page documents the `TopNMetrics` class across multiple versions, ranging from 3.2.0 to the latest version 4.26.0, of the `Google.Cloud.Dialogflow.V2` package."],["The `TopNMetrics` class inherits from `Object` and implements interfaces such as `IMessage`, `IEquatable`, `IDeepCloneable`, and `IBufferMessage`, defining its functionality and integration."],["The class has two constructors, a default one and one that takes another `TopNMetrics` instance for creating copies, and it includes properties for `N` (number of retrieved smart replies) and `Recall` (a measure of the quality of the smart replies)."],["The `Recall` value of `TopNMetrics` provides a quality metric ranging from 0.0 to 1.0 inclusive, derived from `number of queries whose top n smart replies have at least one similar reply as the real reply` divided by `number of queries with at least one smart reply`."]]],[]]
