IAIDocProcessingService.AskAIAsync(RichEditDocumentServer, String, RagOptions, CancellationToken) Method

SECURITY-RELATED CONSIDERATIONS

This API includes automatic prompt-injection protection for text and document-based AI-powered extensions. The system appends security instructions to each AI request to ensure that external or user-provided content is treated as untrusted data.

Prompt Injection Protection in AI Extensions

Returns a response to a custom question about the document content.

Namespace: DevExpress.AIIntegration.Docs

Assembly: DevExpress.AIIntegration.Docs.v26.1.dll

Declaration

C#

Task<string> AskAIAsync(
    RichEditDocumentServer wordProcessor,
    string question,
    RagOptions options,
    CancellationToken cancellationToken = default(CancellationToken)
)

VB.NET

Function AskAIAsync(
    wordProcessor As RichEditDocumentServer,
    question As String,
    options As RagOptions,
    cancellationToken As CancellationToken = Nothing
) As Task(Of String)

Parameters

Name	Type	Description
wordProcessor	RichEditDocumentServer	The RichEditDocumentServer instance that contains the content to be questioned.
question	String	The question about the document content.
options	RagOptions	An object that contains retrieval-augmented generation (RAG) options.

Optional Parameters

Name	Type	Default	Description
cancellationToken	CancellationToken	null	The token that cancels the task.

Returns

Type	Description
Task<String>	The response that contains an AI-generated answer.

Example

How to: Ask Contextual Question about a Word Document

The following code snippet asks a question about the document content, configures RAG options (chunk size, collection name, chunk count), and inserts the AI‑generated answer as a comment about the first paragraph:

C#

using DevExpress.AIIntegration;
using DevExpress.AIIntegration.Docs;
using DevExpress.XtraRichEdit;
using Microsoft.Extensions.AI;

// See "Register AI extension service" section for implementation code
var docProcessingService = 
    defaultAIExtensionsContainer.CreateAIDocProcessingService();

var options = new RagOptions {
    VectorCollectionName = "document_embeddings",
    ChunkSize = 800,
    AugmentationChunkCount = 8
};

using (var wordProcessor = new RichEditDocumentServer()) {
    wordProcessor.LoadDocument(@"Documents/Document1.docx");
    string answer = await docProcessingService.AskAIAsync(
        wordProcessor,
        "Does this document contain any confidential information?",
        options
    );

    wordProcessor.Document.Comments.Create(
        wordProcessor.Document.Paragraphs[0].Range, 
        "AI Summary:\n" + answer);
    wordProcessor.SaveDocument("Documents/Document_commented.docx", DocumentFormat.Docx);
}

VB.NET

vbnet
Imports DevExpress.AIIntegration
Imports DevExpress.AIIntegration.Docs
Imports DevExpress.XtraRichEdit
Imports Microsoft.Extensions.AI

' See "Register AI extension service" section for implementation code
Dim docProcessingService = defaultAIExtensionsContainer.CreateAIDocProcessingService()

Dim options As New RagOptions With {
    .VectorCollectionName = "document_embeddings",
    .ChunkSize = 800,
    .AugmentationChunkCount = 8
}

Using wordProcessor As New RichEditDocumentServer()
    wordProcessor.LoadDocument("Documents/Document1.docx")
    Dim answer As String = Await docProcessingService.AskAIAsync(
        wordProcessor,
        "Does this document contain any confidential information?",
        options
    )

    wordProcessor.Document.Comments.Create(
        wordProcessor.Document.Paragraphs(0).Range,
        "AI Summary:" & vbLf & answer)
    wordProcessor.SaveDocument("Documents/Document_commented.docx", DocumentFormat.Docx)
End Using