DI Analyze

Select the Azure model used to analyze document pages. The model determines the types of layout, text, and semantic elements extracted.

• Use prebuilt-layout for most use cases.
• When using prebuilt-layout, the DI Layout quoting method can be used to inject markdown or HTML into AI-powered extraction operations.
• Output from other prebuilt or custom models can be injected using the JSON File quoting method.

Configuration Impact

Choosing a model affects the extraction detail and supported features.
For custom models, ensure the model is trained and published in Azure before use.

Example:

ModelName = "prebuilt-layout"

Can be one of the following types:

Set the language code for OCR extraction (e.g., en for English, es for Spanish). If left blank, multi-language OCR is enabled. Azure does not auto-detect document language. For best results, run the Detect Language activity after extraction to assign the correct culture code.

Configuration Impact:

Setting the correct language improves OCR accuracy and layout recognition.
If documents contain multiple languages, leave blank to enable multi-language support.

Examples:

• en for English
• es for Spanish
• fr for French

Usage Tip:
Use Detect Language to assign the correct culture code after extraction for downstream activities.

A combination of the following flags:

Choose additional Azure features to include in the analysis. Enabling more features may increase processing time, cost, and result detail.

Can be one of the following values:

Specifies the format for the content property in the generated JSON data.

Configuration Impact:

The content format determines how document data is packaged for Azure analysis.
Choose a format compatible with your document types and extraction requirements.

Examples:

• PDF for PDF documents
• TIFF for multi-page TIFF images
• JPEG for single-page images

Usage Tip:

Match the content format to the document's native format for best results.

Enable this option to replace previous analysis results with new output. If disabled, existing results are preserved and the activity will skip processing for pages that already have results.

Usage Tip:

Enable when updating extraction logic or troubleshooting analysis results.

When enabled, the activity will analyze the folder's attachment (PDF, TIFF, JPEG) if available, rather than merging and analyzing individual child pages. This is useful for documents where the attachment is the preferred source for extraction.

Usage Tip:

Enable for imported digital files; disable for scanned or separated pages.

Enable to automatically rotate pages based on detected layout orientation, improving downstream extraction and review accuracy.

• The predominant angle of text lines on the page is used to determine orientation.
• Will rotate PDF pages using PDF rotation, and non-PDF pages by rotating the primary image and saving the rotated version.
• Will not rotate pages inside an attachment. Attachments must be split into individual pages for orientation correction to be applied.

Usage Tip:

Enable for batches with mixed or unknown page orientations.

The results of the Azure analysis are saved to each page as a JSON file. The file name is generated based on the selected model, following the pattern AzureDI_{ModelName}.json. This allows you to easily locate and review the output for each page.

Example:

AzureDI_prebuilt-layout.json for the prebuilt layout model.

Usage Tip:
Use the filename when configuring quoting methods in downstream activities to reference the Azure analysis results for extraction.

A combination of the following flags:

The Error Disposition property determines the system's response to errors that occur while executing the activity.

• Flag: The affected Batch Folder or Batch Page will be flagged for review.
• Log: The error will be written to the Grooper event log.
• Stop: Processing will halt, the Batch will be set to an error state, and all pending tasks will be deleted.

You can combine multiple options using the IssueDisposition flags.
Adjust this property to match your organization's error handling and escalation policies.

If the number of consecutive errors reaches this value, a critical stop will occur and the Activity Processing service will halt further processing.

• Use this property to prevent runaway failures and to ensure that persistent errors are escalated for review.
• Set to a higher value to allow more retries before stopping, or to a lower value for stricter error control.

Can be one of the following values:

The Concurrency Mode property determines whether the activity can be executed in parallel across multiple Batch Objects, or if it must run sequentially.

• This setting affects which Processing Queue the activity is submitted to and how tasks are distributed.
• Choose the appropriate mode based on the activity's thread safety and resource requirements.