public sealed class TrajectoryInOrderMatchSpec : IMessage<TrajectoryInOrderMatchSpec>, IEquatable<TrajectoryInOrderMatchSpec>, IDeepCloneable<TrajectoryInOrderMatchSpec>, IBufferMessage, IMessage
Reference documentation and code samples for the Vertex AI v1beta1 API class TrajectoryInOrderMatchSpec.
Spec for TrajectoryInOrderMatch metric - returns 1 if tool calls in the
reference trajectory appear in the predicted trajectory in the same order,
else 0.
[[["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complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-14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\u003eThe \u003ccode\u003eTrajectoryInOrderMatchSpec\u003c/code\u003e class is part of the Vertex AI v1beta1 API and is used to define a metric for evaluating the order of tool calls in predicted trajectories compared to reference trajectories.\u003c/p\u003e\n"],["\u003cp\u003eThis class implements several interfaces, including \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e, providing functionalities for message handling, equality comparisons, deep cloning, and buffer operations.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eTrajectoryInOrderMatchSpec\u003c/code\u003e inherits from the base \u003ccode\u003eobject\u003c/code\u003e class and includes constructors for creating new instances, either empty or by cloning an existing \u003ccode\u003eTrajectoryInOrderMatchSpec\u003c/code\u003e object.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eTrajectoryInOrderMatchSpec\u003c/code\u003e metric assigns a score of 1 if tool calls in the reference trajectory are found in the predicted trajectory in the same order, otherwise it assigns a score of 0.\u003c/p\u003e\n"],["\u003cp\u003eThe current latest version is 1.0.0-beta21, with documentation also available for version 1.0.0-beta20.\u003c/p\u003e\n"]]],[],null,[]]
