public sealed class ProcessOptions.Types.LayoutConfig.Types.ChunkingConfig : IMessage<ProcessOptions.Types.LayoutConfig.Types.ChunkingConfig>, IEquatable<ProcessOptions.Types.LayoutConfig.Types.ChunkingConfig>, IDeepCloneable<ProcessOptions.Types.LayoutConfig.Types.ChunkingConfig>, IBufferMessage, IMessage
Reference documentation and code samples for the Cloud Document AI v1beta3 API class ProcessOptions.Types.LayoutConfig.Types.ChunkingConfig.
public int BreakpointPercentileThreshold { get; set; }
Optional. The percentile of cosine dissimilarity that must be exceeded
between a group of tokens and the next. The smaller this number is, the
more chunks will be generated. THIS FIELD IS NOT YET USED.
[[["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complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07 UTC."],[[["\u003cp\u003eThis documentation covers the \u003ccode\u003eChunkingConfig\u003c/code\u003e class, which is part of the Cloud Document AI v1beta3 API and is used to configure chunking settings for document processing.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eChunkingConfig\u003c/code\u003e 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, indicating its role in message handling and data manipulation within the API.\u003c/p\u003e\n"],["\u003cp\u003eThe class provides properties like \u003ccode\u003eBreakpointPercentileThreshold\u003c/code\u003e, \u003ccode\u003eChunkSize\u003c/code\u003e, \u003ccode\u003eIncludeAncestorHeadings\u003c/code\u003e, and \u003ccode\u003eSemanticChunkingGroupSize\u003c/code\u003e, which allow users to customize how documents are split into chunks based on semantic similarity and size.\u003c/p\u003e\n"],["\u003cp\u003eThe latest version of the class is \u003ccode\u003e2.0.0-beta23\u003c/code\u003e, and it's part of the \u003ccode\u003eGoogle.Cloud.DocumentAI.V1Beta3\u003c/code\u003e namespace within the \u003ccode\u003eGoogle.Cloud.DocumentAI.V1Beta3.dll\u003c/code\u003e assembly.\u003c/p\u003e\n"],["\u003cp\u003eThere are two constructors for the class, a default one and one that allows you to initialize an instance of the class with another pre-existing \u003ccode\u003eChunkingConfig\u003c/code\u003e object.\u003c/p\u003e\n"]]],[],null,[]]
