From 12a5816b5d0981720ee513b5cc2d35382b2ff401 Mon Sep 17 00:00:00 2001 From: KARTHIKA-SF4773 Date: Mon, 31 Aug 2026 19:44:45 +0530 Subject: [PATCH 1/5] 1050181-DocumentChunking --- .../Chunking-Library/NET/Chunking-Modes.md | 329 ++++++++++++++++++ .../Chunking-Library/NET/Chunking-Options.md | 46 +++ .../NET/NuGet-Packages-Required.md | 50 +++ .../Chunking-Library/NET/Overview.md | 50 +++ 4 files changed, 475 insertions(+) create mode 100644 Document-Processing/Document-Chunking/Chunking-Library/NET/Chunking-Modes.md create mode 100644 Document-Processing/Document-Chunking/Chunking-Library/NET/Chunking-Options.md create mode 100644 Document-Processing/Document-Chunking/Chunking-Library/NET/NuGet-Packages-Required.md create mode 100644 Document-Processing/Document-Chunking/Chunking-Library/NET/Overview.md diff --git a/Document-Processing/Document-Chunking/Chunking-Library/NET/Chunking-Modes.md b/Document-Processing/Document-Chunking/Chunking-Library/NET/Chunking-Modes.md new file mode 100644 index 0000000000..414ee5bab1 --- /dev/null +++ b/Document-Processing/Document-Chunking/Chunking-Library/NET/Chunking-Modes.md @@ -0,0 +1,329 @@ +--- +title: Chunking Modes in .NET Document Chunking Library | Syncfusion +description: Learn about the chunking modes supported for Excel, Word, PDF, PowerPoint, and Markdown documents using the Syncfusion® .NET Document Chunking Library. +platform: document-processing +control: Chunking +documentation: UG +--- + +# Chunking Modes in .NET Document Chunking Library + +The Syncfusion® .NET Document Chunking Library provides different modes for chunking Excel, Word, PDF, PowerPoint, and Markdown documents. The supported modes vary depending on the source document format. + +Set the `ChunkingMode` property of the corresponding format-specific chunking options class to select the required mode. + +## Excel Chunking Modes + +The following table lists the chunking modes supported for Excel documents. + + + + + + + + + + + + + + + + + + +
ModeDescription
AutoAutomatically selects a suitable chunking approach based on the content and structure of the Excel document.
TableCreates chunks from tables in the Excel document.
WorksheetCreates chunks based on individual worksheets in the Excel document.
+ +### Mode Configuration + +The following code snippet illustrates how to chunk an Excel document using Auto mode. + +{% tabs %} +{% highlight c# tabtitle="C# [Cross-platform]" %} + +IChunkingResult result = chunkingService.Chunk( fileStream, "ExcelSample.xlsx", + new ChunkingOptions + { + MaxTokens = 50, + OverlapTokens = 0, + IncludeMetadata = true, + IncludeCitation = true, + SourceOptions = + new ExcelChunkingOptions + { + ChunkingMode = + ExcelChunkingMode.Auto + } + }); + +{% endhighlight %} +{% endtabs %} + +N> To use another Excel chunking mode, replace `ExcelChunkingMode.Auto` with `ExcelChunkingMode.Table` or `ExcelChunkingMode.Worksheet`. + +## Word Chunking Modes + +The following table lists the chunking modes supported for Word documents. + + + + + + + + + + + + + + + + + + + + + + +
ModeDescription
AutoAutomatically selects a suitable chunking approach based on the content and structure of the Word document.
TableCreates chunks from tables in the Word document.
ParagraphCreates chunks based on paragraphs in the Word document.
SectionCreates chunks based on sections in the Word document.
+ +### Mode Configuration + +The following code snippet illustrates how to chunk a Word document using Section mode. + +{% tabs %} +{% highlight c# tabtitle="C# [Cross-platform]" %} + +IChunkingResult result = chunkingService.Chunk("Data/WordSample.docx", + new ChunkingOptions + { + MaxTokens = 500, + OverlapTokens = 0, + IncludeMetadata = true, + IncludeCitation = true, + SourceOptions = + new WordChunkingOptions + { + ChunkingMode = + WordChunkingMode.Section + } + }); + +{% endhighlight %} +{% endtabs %} + +N> To use another Word chunking mode, replace `WordChunkingMode.Section` with `WordChunkingMode.Auto`, `WordChunkingMode.Table`, or `WordChunkingMode.Paragraph`. + +## PDF Chunking Modes + +The following table lists the chunking modes supported for PDF documents. + + + + + + + + + + + + + + + + + + + + + + +
ModeDescription
AutoAutomatically selects a suitable chunking approach based on the content and structure of the PDF document.
TableCreates chunks from tables detected in the PDF document.
ParagraphCreates chunks based on paragraphs in the PDF document.
PageCreates chunks based on individual pages in the PDF document.
+ +### Mode Configuration + +The following code snippet illustrates how to chunk a PDF document using Table mode. + +{% tabs %} +{% highlight c# tabtitle="C# [Cross-platform]" %} + +IChunkingResult result = chunkingService.Chunk("Data/PdfSample.pdf", + new ChunkingOptions + { + MaxTokens = 500, + OverlapTokens = 0, + IncludeMetadata = true, + IncludeCitation = true, + SourceOptions = + new PdfChunkingOptions + { + ChunkingMode = + PdfChunkingMode.Table + } + }); + +{% endhighlight %} +{% endtabs %} + +N> To use another PDF chunking mode, replace `PdfChunkingMode.Table` with `PdfChunkingMode.Auto`, `PdfChunkingMode.Paragraph`, or `PdfChunkingMode.Page`. + +## PowerPoint Chunking Modes + +The following table lists the chunking modes supported for PowerPoint presentations. + + + + + + + + + + + + + + + + + + + + + + +
ModeDescription
AutoAutomatically selects a suitable chunking approach based on the content and structure of the PowerPoint presentation.
TableCreates chunks from tables in the PowerPoint presentation.
NotesCreates chunks from speaker notes in the PowerPoint presentation.
SlideCreates chunks based on individual slides in the PowerPoint presentation.
+ +### Mode Configuration + +The following code snippet illustrates how to chunk a PowerPoint presentation using Auto mode. + +{% tabs %} +{% highlight c# tabtitle="C# [Cross-platform]" %} + +IChunkingResult result = chunkingService.Chunk("Data/PowerPointSample.pptx", + new ChunkingOptions + { + MaxTokens = 500, + OverlapTokens = 0, + IncludeMetadata = true, + IncludeCitation = true, + SourceOptions = + new PowerPointChunkingOptions + { + ChunkingMode = + PowerPointChunkingMode.Auto + } + }); + +{% endhighlight %} +{% endtabs %} + +N> To use another PowerPoint chunking mode, replace `PowerPointChunkingMode.Auto` with `PowerPointChunkingMode.Table`, `PowerPointChunkingMode.Notes`, or `PowerPointChunkingMode.Slide`. + +## Markdown Chunking Modes + +The following table lists the chunking modes supported for Markdown documents. + + + + + + + + + + + + + + + + + + + + + + +
ModeDescription
AutoAutomatically selects a suitable chunking approach based on the content and structure of the Markdown document.
TableCreates chunks from tables in the Markdown document.
HeadingCreates chunks based on the heading hierarchy in the Markdown document.
ParagraphCreates chunks based on paragraphs in the Markdown document.
+ +### Mode Configuration + +The following code snippet illustrates how to chunk a Markdown document using Table mode. + +{% tabs %} +{% highlight c# tabtitle="C# [Cross-platform]" %} + +IChunkingResult result = chunkingService.Chunk("Data/MarkdownSample.md", + new ChunkingOptions + { + MaxTokens = 500, + OverlapTokens = 0, + IncludeMetadata = true, + IncludeCitation = true, + SourceOptions = + new MarkdownChunkingOptions + { + ChunkingMode = + MarkdownChunkingMode.Table + } + }); + +{% endhighlight %} +{% endtabs %} + +N> To use another Markdown chunking mode, replace `MarkdownChunkingMode.Table` with `MarkdownChunkingMode.Auto`, `MarkdownChunkingMode.Heading`, or `MarkdownChunkingMode.Paragraph`. + +## Expected Output + +The chunking result contains the total number of generated chunks and information about each chunk. When metadata and citations are enabled, the output also contains information about the source document and the original location of the chunk content. + +The following output shows a shortened example of an Excel document processed using Auto mode: + +```text +Chunk Count: 23 +ChunkId: chunk_febb0882c5609fba +ChunkIndex: 0 +Content: +Enterprise Sales Summary +Citation: ExcelSample.xlsx - Summary +Citation Location Details +Location Key: blockType, Location Value: Cell +Location Key: blockId, Location Value: worksheet:1:cell:A1 +Location Key: worksheetNumber, Location Value: 1 +Location Key: worksheetName, Location Value: Summary +Location Key: cellAddress, Location Value: A1 +Location Key: rowIndex, Location Value: 1 +Location Key: columnIndex, Location Value: 1 +Location Key: cellIndex, Location Value: 1 +Location Key: displayText, Location Value: Enterprise Sales Summary +Location Key: rawValue, Location Value: Enterprise Sales Summary +Location Key: calculatedValue, Location Value: Enterprise Sales Summary +Location Key: numberFormat, Location Value: General +Location Key: isFormula, Location Value: False +Location Key: isMerged, Location Value: True +Location Key: mergeRange, Location Value: 'Summary'!A1:D1 +Location Key: isHidden, Location Value: False +Location Key: sourceFile, Location Value: ExcelSample.xlsx +Metadata: Syncfusion.DocumentChunking.Models.ChunkMetadata +Metadata SourceDocumentId: doc_6da758f792fc72a4 +Metadata File Name: ExcelSample.xlsx +Metadata File Type: xlsx +Metadata Token Count: 4 +Metadata Character Count: 24 +Metadata Attributes +Attribute Key: SourceFileName, Attribute Value: ExcelSample.xlsx +Attribute Key: FileExtension, Attribute Value: .xlsx +Attribute Key: WorksheetCount, Attribute Value: 5 +Attribute Key: LastModified, Attribute Value: 8/27/2026 4:05:36 PM +Attribute Key: Created, Attribute Value: 8/16/2026 9:52:12 PM +Attribute Key: Author, Attribute Value: Vinothkumar Sampath +``` + +Each generated chunk contains a unique identifier, index, and extracted content. When citations are enabled, the output identifies the original location of the chunk content. When metadata is enabled, the output provides information about the source document and generated chunk. + +N> The chunk count, extracted content, metadata, and citation details vary depending on the source document, selected chunking mode, and configured chunking options. \ No newline at end of file diff --git a/Document-Processing/Document-Chunking/Chunking-Library/NET/Chunking-Options.md b/Document-Processing/Document-Chunking/Chunking-Library/NET/Chunking-Options.md new file mode 100644 index 0000000000..dcf2987c8e --- /dev/null +++ b/Document-Processing/Document-Chunking/Chunking-Library/NET/Chunking-Options.md @@ -0,0 +1,46 @@ +--- +title: Chunking Options in .NET Document Chunking Library | Syncfusion +description: Learn how to configure maximum tokens, overlapping tokens, metadata, and citations using the Syncfusion® .NET Document Chunking Library. +platform: document-processing +control: Chunking +documentation: UG +--- + +# Chunking Options in .NET Document Chunking Library + +The Syncfusion® .NET Document Chunking Library provides options to control the size and overlap of generated chunks. It also allows you to include metadata and citation details in the chunking results. + +Use the `ChunkingOptions` class to configure these options when processing a document with the `ChunkingService` class. + +## Configure Max Tokens and Overlap + +The `MaxTokens` property specifies the maximum token count allowed in each generated chunk. + +The `OverlapTokens` property specifies the number of tokens shared between consecutive chunks. Token overlap helps retain contextual continuity across chunk boundaries. + +The value of `OverlapTokens` must be less than the value of `MaxTokens`. + +## Include Metadata in Chunks + +Set the `IncludeMetadata` property to `true` to include metadata in each generated chunk. + +The metadata includes information about the source document and generated chunk, such as: + +- Source document ID +- File name +- File type +- Token count +- Character count +- Format-specific attributes + +The available attributes can vary depending on the source document format and selected chunking mode. + +## Include Citations in Chunks + +Set the `IncludeCitation` property to `true` to include citation information in each generated chunk. + +A citation shows where the chunk content is located in the original document. For example, it can identify a page in a PDF document, a worksheet or cell range in an Excel document, a slide in a PowerPoint presentation, a section in a Word document, or a heading in a Markdown document. + +Each citation contains display text and location details. The display text provides a readable source reference, while the location details provide additional information about the exact location of the content in the source document. + +N> The citation details vary depending on the source document format, selected chunking mode, and content type. \ No newline at end of file diff --git a/Document-Processing/Document-Chunking/Chunking-Library/NET/NuGet-Packages-Required.md b/Document-Processing/Document-Chunking/Chunking-Library/NET/NuGet-Packages-Required.md new file mode 100644 index 0000000000..a64f4529a6 --- /dev/null +++ b/Document-Processing/Document-Chunking/Chunking-Library/NET/NuGet-Packages-Required.md @@ -0,0 +1,50 @@ +--- +title: NuGet Package Required for .NET Document Chunking Library | Syncfusion +description: Learn about the NuGet package required to use the Syncfusion® .NET Document Chunking Library. +platform: document-processing +control: Chunking +documentation: UG +--- + +# NuGet Package Required for .NET Document Chunking Library + +## Installing the Document Chunking Library through NuGet + +NuGet provides a convenient way to download and install the Syncfusion® .NET Document Chunking Library. Install the following NuGet package in your application. + + + + + + + + + + + + +
PlatformPackage NamePackage Manager Console Command
ASP.NET CoreSyncfusion.DocumentChunkingInstall-Package Syncfusion.DocumentChunking
+ +N> The `Syncfusion.DocumentChunking` package is available in the [Syncfusion Nexus Repository](https://nexus.syncfusioninternal.com/#browse/browse:nuget-hosted:Syncfusion.DocumentChunking). + +## NuGet Package Installation and Uninstallation + +The `Syncfusion.DocumentChunking` package can be installed and uninstalled using Package Manager Console. + +In Visual Studio, select **Tools > NuGet Package Manager > Package Manager Console**, and run the appropriate command. + +**NuGet package:** `Syncfusion.DocumentChunking` + +The package provides the APIs required to divide supported documents into structured chunks. + +### Install the NuGet Package + +```powershell +Install-Package Syncfusion.DocumentChunking +``` + +### Uninstall the NuGet Package + +```powershell +Uninstall-Package Syncfusion.DocumentChunking -RemoveDependencies +``` \ No newline at end of file diff --git a/Document-Processing/Document-Chunking/Chunking-Library/NET/Overview.md b/Document-Processing/Document-Chunking/Chunking-Library/NET/Overview.md new file mode 100644 index 0000000000..eb9e8578ce --- /dev/null +++ b/Document-Processing/Document-Chunking/Chunking-Library/NET/Overview.md @@ -0,0 +1,50 @@ +--- +title: About Syncfusion .NET Document Chunking Library | Syncfusion +description: Learn about the Syncfusion® .NET Document Chunking Library for preparing enterprise documents for Retrieval-Augmented Generation (RAG) workflows using structural block parsing. +platform: document-processing +control: Chunking +documentation: UG +--- + +# About Syncfusion .NET Document Chunking Library + +The Syncfusion® .NET Document Chunking Library divides Excel, Word, PDF, PowerPoint, and Markdown documents into meaningful chunks for Retrieval-Augmented Generation (RAG) workflows. The generated chunks are suitable for embedding generation, semantic search, vector indexing, hybrid search, document Q&A, grounded AI responses, citation-based retrieval, and enterprise RAG ingestion pipelines. + +The library processes documents based on their native structure to retain relevant elements such as worksheets, paragraphs, tables, pages, slides, sections, and headings. Using the unified `ChunkingService` API, you can select an appropriate chunking mode, configure the chunk size and overlap, and optionally include metadata and citation details in the generated chunks. + +## Key Features + +- Supports structural chunking of Excel, Word, PDF, PowerPoint, and Markdown documents. +- Provides Auto, Table, Paragraph, Worksheet, Section, Page, Slide, Notes, and Heading modes based on the selected document format. +- Supports configuring chunk size and overlap using `MaxTokens` and `OverlapTokens`. +- Supports including metadata and source citations in the generated chunks. +- Preserves relevant document structures and location details during chunking. + +## Supported File Formats + + + + + + + + + + + + + + + + + + + + + + + + + + +
FormatExtensions
Excel.xlsx, .xls, .xlsm, .xltx, .xltm, .csv, .tsv
Word.docx, .doc, .dotx, .dotm, .rtf
PDF.pdf
PowerPoint.pptx
Markdown.md
\ No newline at end of file From 3955ca2c961676d9bd20f613a6fc8720fae7cb22 Mon Sep 17 00:00:00 2001 From: KARTHIKA-SF4773 Date: Mon, 31 Aug 2026 19:58:24 +0530 Subject: [PATCH 2/5] 1050181-DocumentChunking --- .../NET/Assemblies-Required.md | 25 ++ .../NET/Document-Chunking-in-ASP-NET-Core.md | 243 ++++++++++++++++++ 2 files changed, 268 insertions(+) create mode 100644 Document-Processing/Document-Chunking/Chunking-Library/NET/Assemblies-Required.md create mode 100644 Document-Processing/Document-Chunking/Chunking-Library/NET/Document-Chunking-in-ASP-NET-Core.md diff --git a/Document-Processing/Document-Chunking/Chunking-Library/NET/Assemblies-Required.md b/Document-Processing/Document-Chunking/Chunking-Library/NET/Assemblies-Required.md new file mode 100644 index 0000000000..69b2e85f5e --- /dev/null +++ b/Document-Processing/Document-Chunking/Chunking-Library/NET/Assemblies-Required.md @@ -0,0 +1,25 @@ +--- +title: Assemblies Required for .NET Document Chunking Library | Syncfusion +description: Learn about the assembly required to use the Syncfusion® .NET Document Chunking Library in .NET applications. +platform: document-processing +control: Chunking +documentation: UG +--- + +# Assemblies Required for .NET Document Chunking Library + +The following assembly must be referenced in your application to use the Syncfusion® .NET Document Chunking Library. + + + + + + + + + + +
PlatformAssembly
ASP.NET CoreSyncfusion.DocumentChunking
+ +N> 1. Using NuGet packages provides frequent bug fixes and simplifies package upgrades. +N> 2. Refer to [NuGet Package Required](https://help.syncfusion.com/document-processing/document-chunking/chunking-library/net/nuget-packages-required) for more information about the required NuGet package. \ No newline at end of file diff --git a/Document-Processing/Document-Chunking/Chunking-Library/NET/Document-Chunking-in-ASP-NET-Core.md b/Document-Processing/Document-Chunking/Chunking-Library/NET/Document-Chunking-in-ASP-NET-Core.md new file mode 100644 index 0000000000..0ffa29d7da --- /dev/null +++ b/Document-Processing/Document-Chunking/Chunking-Library/NET/Document-Chunking-in-ASP-NET-Core.md @@ -0,0 +1,243 @@ +--- +title: Get Started with .NET Document Chunking Library in ASP.NET Core | Syncfusion +description: Learn how to use the Syncfusion® .NET Document Chunking Library to chunk Excel, Word, PDF, PowerPoint, and Markdown documents in an ASP.NET Core application. +platform: document-processing +control: Chunking +documentation: UG +--- + +# Get Started with .NET Document Chunking Library in ASP.NET Core + +The Syncfusion® .NET Document Chunking Library allows you to divide Excel, Word, PDF, PowerPoint, and Markdown documents into meaningful chunks in an ASP.NET Core application. + +This section explains how to create an ASP.NET Core application, install the required NuGet package, upload a supported document, and generate chunks using a format-specific chunking mode. + +## Prerequisites + +- Visual Studio 2022 with the **ASP.NET and web development** workload installed. +- .NET 8.0 SDK or later. +- A supported Excel, Word, PDF, PowerPoint, or Markdown document. +- Access to the Syncfusion Nexus Repository containing the `Syncfusion.DocumentChunking` package. + +## Create an ASP.NET Core Application + +The following steps illustrate how to create an ASP.NET Core application and chunk a supported document. + +{% tabcontents %} + +{% tabcontent Visual Studio %} + +Step 1: Create a new **ASP.NET Core Web App (Model-View-Controller)** project. + +Step 2: Select **.NET 8.0** or a later framework version, and create the project. + +Step 3: Configure the Syncfusion Nexus Repository as a package source and install the `Syncfusion.DocumentChunking` NuGet package in the application. + +```powershell +Install-Package Syncfusion.DocumentChunking +``` + +Step 4: Add the following namespace to the `HomeController.cs` file. + +{% capture codesnippet1 %} +{% tabs %} +{% highlight c# tabtitle="C#" %} +using Syncfusion.DocumentChunking; +{% endhighlight %} +{% endtabs %} +{% endcapture %} +{{ codesnippet1 | OrderList_Indent_Level_1 }} + +Step 5: Open `Views/Home/Index.cshtml` and add the following form to upload a supported document. + +{% capture codesnippet2 %} +{% tabs %} +{% highlight CSHTML %} +@{ + ViewData["Title"] = "Document Chunking"; +} + +

Document Chunking

+ +
+ +
+ + + +
+
+ +
+ +{% endhighlight %} +{% endtabs %} +{% endcapture %} +{{ codesnippet2 | OrderList_Indent_Level_1 }} + +Step 6: Add the following `ChunkDocument` action and helper methods to `HomeController.cs`. + +The following code snippet illustrates how to chunk Excel, Word, PDF, PowerPoint, and Markdown documents. The example selects the appropriate source options and chunking mode based on the uploaded document format. + +{% capture codesnippet3 %} +{% tabs %} +{% highlight c# tabtitle="C#" %} +public IActionResult ChunkDocument(IFormFile document) +{ + if (document == null || document.Length == 0) + { + return BadRequest("Select a document to chunk."); + } + + string fileName = document.FileName; + string extension = Path.GetExtension(fileName).ToLowerInvariant(); + + ChunkingService chunkingService = new ChunkingService(); + + using Stream fileStream = document.OpenReadStream(); + + ChunkingOptions options = + new ChunkingOptions + { + MaxTokens = 500, + OverlapTokens = 0, + IncludeMetadata = true, + IncludeCitation = true + }; + + switch (extension) + { + case ".xlsx": + case ".xls": + case ".xlsm": + case ".xltx": + case ".xltm": + case ".csv": + case ".tsv": + options.MaxTokens = 50; + options.SourceOptions = + new ExcelChunkingOptions + { + ChunkingMode = + ExcelChunkingMode.Auto + }; + break; + + case ".docx": + case ".doc": + case ".dotx": + case ".dotm": + case ".rtf": + options.SourceOptions = + new WordChunkingOptions + { + ChunkingMode = + WordChunkingMode.Section + }; + break; + + case ".pdf": + options.SourceOptions = + new PdfChunkingOptions + { + ChunkingMode = + PdfChunkingMode.Auto + }; + break; + + case ".pptx": + options.SourceOptions = + new PowerPointChunkingOptions + { + ChunkingMode = + PowerPointChunkingMode.Auto + }; + break; + + case ".md": + options.SourceOptions = + new MarkdownChunkingOptions + { + ChunkingMode = + MarkdownChunkingMode.Table + }; + break; + + default: + return BadRequest( + $"The file format '{extension}' is not supported."); + } + + IChunkingResult result = chunkingService.Chunk(fileStream, fileName, options); + + DisplayChunkingResult(result); + + return Content("The document was chunked successfully. " + "See the application console for the chunking results."); +} + +private static void DisplayChunkingResult( IChunkingResult result) +{ + Console.WriteLine( $"Chunk Count: {result.Chunks.Count}"); + + foreach (IChunk chunk in result.Chunks) + { + Console.WriteLine("================================"); + + Console.WriteLine($"ChunkId: {chunk.ChunkId}"); + + Console.WriteLine($"ChunkIndex: {chunk.ChunkIndex}"); + + Console.WriteLine($"Content:{Environment.NewLine}{chunk.Content}"); + + Console.WriteLine($"Citation: {chunk.Citation?.DisplayText}"); + + Console.WriteLine("Citation Location Details"); + + if (chunk.Citation?.LocationDetails != null) + { + foreach (KeyValuePair item in chunk.Citation.LocationDetails) + { + Console.WriteLine($"Location Key: {item.Key}, " + $"Location Value: {item.Value}"); + } + } + + Console.WriteLine($"Metadata: {chunk.Metadata}"); + + Console.WriteLine($"Metadata SourceDocumentId: " + $"{chunk.Metadata?.SourceDocumentId}"); + + Console.WriteLine($"Metadata File Name: " + $"{chunk.Metadata?.FileName}"); + + Console.WriteLine($"Metadata File Type: " + $"{chunk.Metadata?.FileType}"); + + Console.WriteLine($"Metadata Token Count: " + $"{chunk.Metadata?.TokenCount}"); + + Console.WriteLine($"Metadata Character Count: " + $"{chunk.Metadata?.CharacterCount}"); + + Console.WriteLine("Metadata Attributes"); + + if (chunk.Metadata?.Attributes != null) + { + foreach (KeyValuePair item in chunk.Metadata.Attributes) + { + Console.WriteLine($"Attribute Key: {item.Key}, " + $"Attribute Value: {item.Value}"); + } + } + } +} +{% endhighlight %} +{% endtabs %} +{% endcapture %} +{{ codesnippet3 | OrderList_Indent_Level_1 }} + +Step 7: Run the application, select a supported document, and click **Chunk Document**. + +The application selects a source option and chunking mode based on the uploaded document format. The generated chunk content, metadata, and citation details are displayed in the application console. + +N> To use a different chunking mode, replace the format-specific `ChunkingMode` value in the `switch` statement. For more information about the supported modes, see [Chunking modes](https://help.syncfusion.com/document-processing/document-chunking/chunking-library/net/chunking-modes). \ No newline at end of file From 858fea72d87bbad69ad93eab804aa4d119b0bf20 Mon Sep 17 00:00:00 2001 From: KARTHIKA-SF4773 Date: Mon, 31 Aug 2026 20:34:32 +0530 Subject: [PATCH 3/5] 1050181-DocumentChunking --- Document-Processing-toc.html | 38 ++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/Document-Processing-toc.html b/Document-Processing-toc.html index 37c293bfdf..faa85e0bb9 100644 --- a/Document-Processing-toc.html +++ b/Document-Processing-toc.html @@ -8467,6 +8467,44 @@ +
  • + Document Chunking + +
  • Common
      From 2457afbfdd21fb981f42bb21982b5eb6a0ecea04 Mon Sep 17 00:00:00 2001 From: KARTHIKA-SF4773 Date: Wed, 2 Sep 2026 19:51:20 +0530 Subject: [PATCH 4/5] 1050181-DocumentChunking --- Document-Processing-toc.html | 17 +++++++------ .../Chunking-Library/Overview.md | 24 +++++++++++++++++++ .../Document-Chunking/Overview.md | 23 ++++++++++++++++++ 3 files changed, 55 insertions(+), 9 deletions(-) create mode 100644 Document-Processing/Document-Chunking/Chunking-Library/Overview.md create mode 100644 Document-Processing/Document-Chunking/Overview.md diff --git a/Document-Processing-toc.html b/Document-Processing-toc.html index faa85e0bb9..905698bc20 100644 --- a/Document-Processing-toc.html +++ b/Document-Processing-toc.html @@ -8468,10 +8468,10 @@
  • - Document Chunking + Document Chunking
    • - Chunking Library + Chunking Library
      • diff --git a/Document-Processing/Document-Chunking/Chunking-Library/Overview.md b/Document-Processing/Document-Chunking/Chunking-Library/Overview.md new file mode 100644 index 0000000000..1b83eb50ae --- /dev/null +++ b/Document-Processing/Document-Chunking/Chunking-Library/Overview.md @@ -0,0 +1,24 @@ +--- +title: Syncfusion Document Chunking Library Overview | Syncfusion +description: Learn about the Syncfusion® Document Chunking Library for dividing Excel, Word, PDF, PowerPoint, and Markdown documents into meaningful and structured chunks. +platform: document-processing +control: Chunking +documentation: UG +--- + +# Syncfusion Document Chunking Library + +The Syncfusion® Document Chunking Library provides a unified solution for dividing Excel, Word, PDF, PowerPoint, and Markdown documents into meaningful and structured chunks. + +The library processes documents based on their native structure and supports format-specific chunking modes. It also allows you to configure the chunk size and overlap and optionally include metadata and citation information in the generated chunks. + +The generated chunks can be used for embedding generation, semantic search, vector indexing, hybrid search, document Q&A, grounded AI responses, citation-based retrieval, and enterprise Retrieval-Augmented Generation (RAG) workflows. + +## Key Capabilities + +- Supports Excel, Word, PDF, PowerPoint, and Markdown documents. +- Provides chunking modes based on the structure of each supported document format. +- Supports configuring the maximum token count and token overlap. +- Supports including source metadata in generated chunks. +- Supports including citations that identify the original location of the chunk content. +- Provides structured chunks for search, retrieval, and AI-based document-processing workflows. \ No newline at end of file diff --git a/Document-Processing/Document-Chunking/Overview.md b/Document-Processing/Document-Chunking/Overview.md new file mode 100644 index 0000000000..bb3e319eb5 --- /dev/null +++ b/Document-Processing/Document-Chunking/Overview.md @@ -0,0 +1,23 @@ +--- +title: Document Chunking Overview | Syncfusion +description: Learn about document chunking and how it prepares document content for Retrieval-Augmented Generation, semantic search, vector indexing, and other AI workflows. +platform: document-processing +control: Chunking +documentation: UG +--- + +# Document Chunking + +Document chunking is the process of dividing a document into smaller, meaningful units while retaining the context and structure of its content. These chunks can be used in Retrieval-Augmented Generation (RAG), embedding generation, semantic search, vector indexing, hybrid search, document Q&A, grounded AI responses, citation-based retrieval, and enterprise RAG ingestion pipelines. + +The Syncfusion® Document Chunking solution processes documents based on their native structure. This enables meaningful document elements, such as worksheets, tables, paragraphs, pages, slides, sections, and headings, to be identified and processed as chunks. + +The Document Chunking Library supports structured chunking of Excel, Word, PDF, PowerPoint, and Markdown documents. + +## Benefits of Document Chunking + +- Divides large documents into smaller and manageable chunks. +- Retains the context and structure of the source content. +- Supports metadata and citations for tracing chunks to their source. +- Prepares document content for search, retrieval, and AI workflows. +- Provides format-specific chunking modes for supported document types. \ No newline at end of file From 93a8999b6dd54429b39c301370431ad7bf3f0852 Mon Sep 17 00:00:00 2001 From: KARTHIKA-SF4773 Date: Wed, 2 Sep 2026 21:00:03 +0530 Subject: [PATCH 5/5] 1050181-DocumentChunking --- .../Chunking-Library/NET/Assemblies-Required.md | 2 +- .../Chunking-Library/NET/Document-Chunking-in-ASP-NET-Core.md | 4 ++-- .../Chunking-Library/NET/NuGet-Packages-Required.md | 2 +- .../Document-Chunking/Chunking-Library/NET/Overview.md | 2 +- Document-Processing/Document-Chunking/Overview.md | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) diff --git a/Document-Processing/Document-Chunking/Chunking-Library/NET/Assemblies-Required.md b/Document-Processing/Document-Chunking/Chunking-Library/NET/Assemblies-Required.md index 69b2e85f5e..2e15a562ea 100644 --- a/Document-Processing/Document-Chunking/Chunking-Library/NET/Assemblies-Required.md +++ b/Document-Processing/Document-Chunking/Chunking-Library/NET/Assemblies-Required.md @@ -22,4 +22,4 @@ The following assembly must be referenced in your application to use the Syncfus N> 1. Using NuGet packages provides frequent bug fixes and simplifies package upgrades. -N> 2. Refer to [NuGet Package Required](https://help.syncfusion.com/document-processing/document-chunking/chunking-library/net/nuget-packages-required) for more information about the required NuGet package. \ No newline at end of file +N> 2. Refer to NuGet Package Required for more information about the required NuGet package. \ No newline at end of file diff --git a/Document-Processing/Document-Chunking/Chunking-Library/NET/Document-Chunking-in-ASP-NET-Core.md b/Document-Processing/Document-Chunking/Chunking-Library/NET/Document-Chunking-in-ASP-NET-Core.md index 0ffa29d7da..3aca87cbde 100644 --- a/Document-Processing/Document-Chunking/Chunking-Library/NET/Document-Chunking-in-ASP-NET-Core.md +++ b/Document-Processing/Document-Chunking/Chunking-Library/NET/Document-Chunking-in-ASP-NET-Core.md @@ -1,5 +1,5 @@ --- -title: Get Started with .NET Document Chunking Library in ASP.NET Core | Syncfusion +title: Get Started with .NET Document Chunking | Syncfusion description: Learn how to use the Syncfusion® .NET Document Chunking Library to chunk Excel, Word, PDF, PowerPoint, and Markdown documents in an ASP.NET Core application. platform: document-processing control: Chunking @@ -240,4 +240,4 @@ Step 7: Run the application, select a supported document, and click **Chunk Docu The application selects a source option and chunking mode based on the uploaded document format. The generated chunk content, metadata, and citation details are displayed in the application console. -N> To use a different chunking mode, replace the format-specific `ChunkingMode` value in the `switch` statement. For more information about the supported modes, see [Chunking modes](https://help.syncfusion.com/document-processing/document-chunking/chunking-library/net/chunking-modes). \ No newline at end of file +N> To use a different chunking mode, replace the format-specific `ChunkingMode` value in the `switch` statement. For more information about the supported modes, see Chunking modes. \ No newline at end of file diff --git a/Document-Processing/Document-Chunking/Chunking-Library/NET/NuGet-Packages-Required.md b/Document-Processing/Document-Chunking/Chunking-Library/NET/NuGet-Packages-Required.md index a64f4529a6..01838fec5e 100644 --- a/Document-Processing/Document-Chunking/Chunking-Library/NET/NuGet-Packages-Required.md +++ b/Document-Processing/Document-Chunking/Chunking-Library/NET/NuGet-Packages-Required.md @@ -1,6 +1,6 @@ --- title: NuGet Package Required for .NET Document Chunking Library | Syncfusion -description: Learn about the NuGet package required to use the Syncfusion® .NET Document Chunking Library. +description: Learn about the NuGet package required to install and use the Syncfusion® .NET Document Chunking Library across supported applications. platform: document-processing control: Chunking documentation: UG diff --git a/Document-Processing/Document-Chunking/Chunking-Library/NET/Overview.md b/Document-Processing/Document-Chunking/Chunking-Library/NET/Overview.md index eb9e8578ce..f397843ed7 100644 --- a/Document-Processing/Document-Chunking/Chunking-Library/NET/Overview.md +++ b/Document-Processing/Document-Chunking/Chunking-Library/NET/Overview.md @@ -1,6 +1,6 @@ --- title: About Syncfusion .NET Document Chunking Library | Syncfusion -description: Learn about the Syncfusion® .NET Document Chunking Library for preparing enterprise documents for Retrieval-Augmented Generation (RAG) workflows using structural block parsing. +description: Learn how the Syncfusion® .NET Document Chunking Library prepares structured enterprise content for Retrieval-Augmented Generation workflows. platform: document-processing control: Chunking documentation: UG diff --git a/Document-Processing/Document-Chunking/Overview.md b/Document-Processing/Document-Chunking/Overview.md index bb3e319eb5..da433e1825 100644 --- a/Document-Processing/Document-Chunking/Overview.md +++ b/Document-Processing/Document-Chunking/Overview.md @@ -6,7 +6,7 @@ control: Chunking documentation: UG --- -# Document Chunking +# Overview of Document Chunking Document chunking is the process of dividing a document into smaller, meaningful units while retaining the context and structure of its content. These chunks can be used in Retrieval-Augmented Generation (RAG), embedding generation, semantic search, vector indexing, hybrid search, document Q&A, grounded AI responses, citation-based retrieval, and enterprise RAG ingestion pipelines.