PdfOcrAgentTools Class

Provides AI agent tools for performing OCR operations on PDF documents.

Inheritance
System.Object
AgentToolBase
AgentToolBase<PdfDocumentBase>
PdfOcrAgentTools
Inherited Members
Namespace: Syncfusion.AI.AgentTools.PDF
Assembly: Syncfusion.DocumentSDK.AI.AgentTools.dll
Syntax
public class PdfOcrAgentTools : AgentToolBase<PdfDocumentBase>

Constructors

PdfOcrAgentTools(DocumentStorageManager)

Initializes a new instance of the PdfOcrAgentTools class (Mode 2 � DocumentStorage).

Declaration
public PdfOcrAgentTools(DocumentStorageManager manager)
Parameters
Type Name Description
DocumentStorageManager manager

The document storage manager.

PdfOcrAgentTools(PdfDocumentManager)

Initializes a new instance of the PdfOcrAgentTools class (Mode 1 � InMemory).

Declaration
public PdfOcrAgentTools(PdfDocumentManager manager)
Parameters
Type Name Description
PdfDocumentManager manager

The PDF document manager.

Methods

PerformOcr(String, String, String, String)

Performs Optical Character Recognition (OCR) on a PDF document, making scanned or image-based text selectable and searchable.

Declaration
[Tool(Name = "PerformOcr", Description = "Performs Optical Character Recognition (OCR) on a PDF document. documentIdOrFilePath: The document ID (InMemory mode) or input file path (DocumentStorage mode).")]
public AgentToolResult PerformOcr([ToolParameter(Description = "The document ID (InMemory mode) or input file path (DocumentStorage mode)")] string documentIdOrFilePath, [ToolParameter(Description = "Path to the Tesseract tessdata folder (required when language is not 'eng')")] string dataPath = null, [ToolParameter(Description = "OCR language code (e.g., eng, fra, deu, tam). Default is eng")] string language = "eng", [ToolParameter(Description = "Output file path for saving the result (DocumentStorage mode only).")] string outputFilePath = null)
Parameters
Type Name Description
System.String documentIdOrFilePath

The document ID (InMemory mode) or input file path (DocumentStorage mode).
System.String dataPath

Path to the Tesseract tessdata folder (required when language is not 'eng').
System.String language

OCR language code (e.g., eng, fra, deu, tam). Default is eng.
System.String outputFilePath

Output file path for saving the result (DocumentStorage mode only).
Returns
Type Description
AgentToolResult

Result containing the document ID, language used, and data path.