Compétences Azure.AI.DocumentIntelligence (.NET)
đź“„

Azure.AI.DocumentIntelligence (.NET)

Sûr

Extract Document Data with Azure AI

Process invoices, receipts, and documents automatically using Azure Document Intelligence SDK in .NET. Extract structured data, text, and tables from PDFs and images without manual data entry.

Prend en charge: Claude Codex Code(CC)
🥉 73 Bronze
1

Télécharger le ZIP du skill

2

Importer dans Claude

Allez dans Paramètres → Capacités → Skills → Importer un skill

3

Activez et commencez Ă  utiliser

Tester

Utilisation de "Azure.AI.DocumentIntelligence (.NET)". Analyze invoice from https://example.com/invoice.pdf

Résultat attendu:

Vendor Name: 'Acme Corp', confidence: 0.95
Invoice Total: '$1,234.56'
Line Items:
- Widget A (5 units): $500.00
- Service Fee: $234.56
- Tax: $100.00

Utilisation de "Azure.AI.DocumentIntelligence (.NET)". Extract tables from document

Résultat attendu:

Table 1: 5 rows x 3 columns
Cell (0,0): Product | Quantity | Price
Cell (1,0): Widget A | 5 | $500.00

Audit de sécurité

Sûr
v1 • 2/24/2026

Prompt-only documentation skill containing Azure Document Intelligence SDK code examples. Static analysis scanned 0 files (0 lines) with 0 security issues detected. The skill is purely a reference guide with no executable code, scripts, or network calls. No suspicious patterns or risk factors identified.

0
Fichiers analysés
0
Lignes analysées
0
résultats
1
Total des audits
Aucun problème de sécurité trouvé
Audité par: claude

Score de qualité

38
Architecture
100
Maintenabilité
87
Contenu
50
Communauté
100
Sécurité
83
Conformité aux spécifications

Ce que vous pouvez construire

Automate Invoice Processing

Extract vendor names, invoice numbers, line items, and totals from PDF invoices automatically. Reduce manual data entry and processing time.

Receipt Digitization for Expenses

Capture receipt data including merchant, items purchased, taxes, and totals. Store structured data for expense reporting systems.

Build Custom Document Extraction

Train custom models to extract specific fields from company-specific documents like contracts, forms, or custom reports.

Essayez ces prompts

Analyze Invoice with Azure
Use Azure.AI.DocumentIntelligence to analyze an invoice from URL. Show me how to extract vendor name, invoice total, and line items with confidence scores in C#.
Extract Text and Tables
Show me how to use the prebuilt-layout model to extract all text content and tables from a PDF document using Azure Document Intelligence client in .NET.
Build Custom Model
Help me build a custom document model using Azure.AI.DocumentIntelligenceAdministrationClient. I have labeled training data in Azure Blob storage.
Authenticate with Entra ID
Show me how to authenticate to Azure Document Intelligence using DefaultAzureCredential in a .NET application. What endpoint format is required?

Bonnes pratiques

  • Use DefaultAzureCredential in production for secure Microsoft Entra ID authentication instead of API keys
  • Always check the Confidence property on extracted fields to verify data quality
  • Reuse DocumentIntelligenceClient instances as they are thread-safe and designed for repeated use

Éviter

  • Do not create a new client for each document analysis operation - this is inefficient
  • Avoid using API keys in client-side applications - prefer Entra ID authentication
  • Do not skip confidence score checking - low confidence values may indicate extraction errors

Foire aux questions

What is the difference between DocumentIntelligenceClient and DocumentIntelligenceAdministrationClient?
DocumentIntelligenceClient is used for analyzing documents and classifying them. DocumentIntelligenceAdministrationClient is used for building and managing custom models and classifiers.
How do I authenticate to Azure Document Intelligence?
Use DefaultAzureCredential for production with Microsoft Entra ID, or AzureKeyCredential with an API key for development. Entra ID requires a custom subdomain endpoint.
Can I extract data from scanned images?
Yes, Azure Document Intelligence supports JPEG, PNG, BMP, TIFF, and PDF files including scanned documents. The service performs OCR automatically.
What prebuilt models are available?
Available prebuilt models include: read, layout, invoice, receipt, idDocument, businessCard, tax.us.w2, and healthInsuranceCard.us.
How do I build a custom model?
Use DocumentIntelligenceAdministrationClient with BuildDocumentModelAsync. Provide training documents in Azure Blob storage with SAS URL. You need at least 5 labeled documents.
What is the difference between Template and Neural build modes?
Template mode is for fixed-layout documents like forms. Neural mode handles variable-layout documents like invoices and receipts with better accuracy.

Détails du développeur

Structure de fichiers

đź“„ SKILL.md