Analyze Document
Description
The Analyze Document activity uses Azure AI Document Intelligence to analyze documents such as PDFs, scanned images, invoices, receipts, contracts, identity documents, and forms.
The activity extracts structured information including text, tables, key-value pairs, document fields, layout information, and other document-specific entities depending on the selected document model.
Common settings
Use Process Data to bind supported inputs to workflow values or upstream outputs. See Common Activity Features for shared execution, error-handling, and output-persistence settings. Availability depends on the activity.
Design-Time Configuration
Display Text
The label for this activity as it appears on the workflow canvas.
Connection Name
Select one of the following:
- An Azure AI Document Intelligence connection configured in AI Command Center using customer-provided Azure credentials.
- IB-X Azure Document Intelligence Credits to use the IntelliBuddies Integration Gateway.
When using IB-X Azure Document Intelligence Credits, document analysis requests are processed through the Integration Gateway and consume IB-X Currency based on the request volume and processing requirements.
Select Document By
Specifies how the document is provided.
File
Analyze a document provided as a File Reference.
This option is typically used with:
- Email attachments
- Files downloaded from cloud storage
- Files generated by previous workflow activities
URL
Analyze a document available through a publicly accessible URL.
Document File
The File Reference of the document to analyze.
Used when Select Document By is set to File.
Document URL
The URL of the document to analyze.
Used when Select Document By is set to URL.
Document Type
Selects the Azure Document Intelligence model used for analysis.
| Document Type | Description |
|---|---|
| Invoice | Extracts invoice fields and line items |
| Receipt | Extracts receipt information |
| Business Card | Extracts contact details from business cards |
| Identity Document | Extracts identity document fields |
| Contract | Extracts contract content and structure |
| US Health Insurance Card | Extracts insurance card information |
| US W2 Tax | Extracts W-2 tax form data |
| US 1098 Tax | Extracts IRS Form 1098 data |
| US 1098-E Tax | Extracts IRS Form 1098-E data |
| US 1098-T Tax | Extracts IRS Form 1098-T data |
| Layout | Extracts text, tables, and document structure without field recognition |
Detect Key-Value Pairs
Detects general form fields and key-value pairs throughout the document.
Detect Formulas
Detects mathematical formulas and expressions.
Detect Languages
Detects the language used within the document.
Detect Barcodes
Detects and extracts barcode information.
Detect Font Styling
Detects font properties such as style, weight, and emphasis where supported.
Perform High Resolution OCR
Uses higher-resolution optical character recognition for improved accuracy on documents containing small text or complex layouts.
Execution settings
Configure Wait All Incoming when execution paths converge, and On Error for failure handling. Select Inherit where available to use the workflow-level error policy.
Outputs
Analyze Result
A structured document analysis result containing extracted information such as:
- Document fields
- Key-value pairs
- Tables
- Text content
- Pages
- Languages
- Barcodes
- Confidence scores
Raw Response
The complete JSON response returned by Azure AI Document Intelligence.
Notes
- Supported file types depend on Azure AI Document Intelligence capabilities.
- Processing time varies based on document size, page count, and selected analysis options.
- When using IB-X Azure Document Intelligence Credits, IB-X Currency is consumed through the Integration Gateway.
Example: Extract invoice data
Select an Azure Document Analysis connection or the credits option. Choose File, bind a PDF file reference to Document File, and select Invoice.
Run with a representative invoice and inspect Analyze Result → Documents for recognized fields and confidence values. Use Tables for table extraction. The returned fields depend on the document model and the document content; check a field is present before binding its value to required downstream inputs. See AnalyzeResult.
Enable optional analysis features only when supported by the selected model and service configuration. Use Layout for text and structure when invoice-specific fields are not required.