Rag.NET.Parsers.Pdf.AzureDocumentIntelligence
1.0.0
dotnet add package Rag.NET.Parsers.Pdf.AzureDocumentIntelligence --version 1.0.0
NuGet\Install-Package Rag.NET.Parsers.Pdf.AzureDocumentIntelligence -Version 1.0.0
<PackageReference Include="Rag.NET.Parsers.Pdf.AzureDocumentIntelligence" Version="1.0.0" />
<PackageVersion Include="Rag.NET.Parsers.Pdf.AzureDocumentIntelligence" Version="1.0.0" />
<PackageReference Include="Rag.NET.Parsers.Pdf.AzureDocumentIntelligence" />
paket add Rag.NET.Parsers.Pdf.AzureDocumentIntelligence --version 1.0.0
#r "nuget: Rag.NET.Parsers.Pdf.AzureDocumentIntelligence, 1.0.0"
#:package Rag.NET.Parsers.Pdf.AzureDocumentIntelligence@1.0.0
#addin nuget:?package=Rag.NET.Parsers.Pdf.AzureDocumentIntelligence&version=1.0.0
#tool nuget:?package=Rag.NET.Parsers.Pdf.AzureDocumentIntelligence&version=1.0.0
Rag.NET.Parsers.Pdf.AzureDocumentIntelligence
Azure Document Intelligence OCR engine for Rag.NET's PDF parser: scanned or image-only
PDFs are sent to the prebuilt-read model as whole documents instead of being OCR'd
page-by-page locally.
Install
dotnet add package Rag.NET.Parsers.Pdf.AzureDocumentIntelligence
This package extends Rag.NET.Parsers.Pdf (installed automatically) and registers into
the AddRagNet(...) builder from the core Rag.NET package.
Setup
Inside your AddRagNet(...) builder callback:
using Rag.NET.Parsers.Pdf;
using Rag.NET.Parsers.Pdf.AzureDocumentIntelligence;
// credential: an AzureKeyCredential or TokenCredential (Azure.Core)
rag.AddPdfParser(options => options.UseOcrFallback = true)
.UseAzureDocumentIntelligenceOcr(
new Uri("https://my-resource.cognitiveservices.azure.com/"),
credential);
Example
The options control model, cost guardrails and polling:
rag.UseAzureDocumentIntelligenceOcr(
new Uri("https://my-resource.cognitiveservices.azure.com/"),
credential,
configure: options =>
{
options.ModelId = "prebuilt-read"; // default
options.PricePerPage = 0.0015m; // feeds the cost ledger when enabled
options.Locale = "en";
});
The engine only runs for documents the PDF parser flags as needing OCR
(UseOcrFallback = true and fewer than OcrMinCharacters extractable characters).
Full guide
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net10.0 is compatible. net10.0-android was computed. net10.0-browser was computed. net10.0-ios was computed. net10.0-maccatalyst was computed. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed. |
-
net10.0
- Azure.AI.DocumentIntelligence (>= 1.0.0)
- Microsoft.Extensions.DependencyInjection.Abstractions (>= 10.0.12)
- Microsoft.Extensions.Logging.Abstractions (>= 10.0.12)
- Rag.NET.Parsers.Pdf (>= 1.0.0)
NuGet packages
This package is not used by any NuGet packages.
GitHub repositories
This package is not used by any popular GitHub repositories.