DI Layout

Specifies which Azure model's results will be quoted by this method.
Set 'Model Name' to match the model used in the DI Analyze activity (e.g., prebuilt-layout or a custom model name). Changing this value determines which set of analysis results are loaded and quoted for the document or page.

Example:

• prebuilt-layout for general document layout extraction.

Ensure the selected model matches the one configured in DI Analyze to avoid file not found errors.

Can be one of the following values:

Determines how the quoted content is structured in the AI prompt.
Choose between Markdown, JSON, or both, depending on the requirements of your extraction or spatial grounding workflow.

• Markdown: Formats results for human-readable extraction and review.
• JSON: Structures results for spatial grounding or programmatic consumption.
• Both: Includes both formats for comprehensive quoting.

Select the format that best matches your downstream AI or data extraction needs.

Enables quoting of layout analysis results from each Batch Page separately, rather than from the merged Batch Folder results. Use this option when DI Analyze was configured to save results per page, or when you need page-specific quoting for multi-page documents.

• Set to true to load and quote results from each page.
• Set to false to quote merged results from the folder.

This setting affects which files are loaded and how content is injected into the prompt.

Restricts quoting to only those regions explicitly defined on the Data Instance, enabling location-based quoting for targeted extraction. Use this option to focus the quoted content on specific areas of interest, such as fields, tables, or labeled regions.

• Enable when you want to supply only region-specific content to the AI.
• Disable to quote the entire page or folder content.

If no regions are defined, an error will be reported and no content will be quoted.

Controls which document pages are included in the quoted results by specifying a page filter expression. Page filters use a flexible syntax to select pages by number, range, or position from the end of the document.

Syntax

• Enter page numbers as a comma-separated list (e.g., 1,3,5).
• Specify ranges using to or - (e.g., 2 to 5, 4-6).
• Use negative numbers to count from the end (-1 is last page, -2 is second-to-last).
• Combine multiple entries (e.g., 1, -1, 1 to 2, -2 to -1).

Examples (for a 10-page document)

• 1 — first page
• 1 to 5 — pages 1 through 5
• -1 — last page
• -5 to -1 — last 5 pages
• 1, -1 — first and last pages
• 1, 2, 4 — pages 1, 2, and 4
• 1 to -2 — all but the last page

Usage Notes

• Leave blank to include all pages.
• Page numbers are 1-based.
• Ranges and negative numbers are supported for flexible selection.
• Invalid ranges (start greater than end) will cause an error.
• This property is hidden when 'Use Location' is enabled.

Displays the expected filename for the Azure Document Intelligence results, based on the selected 'Model Name'. The file must exist on the Batch Folder or Batch Page and is generated by the DI Analyze activity.

• Example: AzureDI_prebuilt-layout.json

Ensure that DI Analyze has been run and the results file is present before quoting.

Overview

The 'Name' property provides a concise, human-readable label for the quoting method. This value is used in Grooper’s user interface to help users identify, select, and configure quoting strategies. It is also injected into the prompt context sent to the large language model (LLM), where it serves as a section header or explicit label for the quoted content.

LLM Context Injection

• When the output of multiple quoting methods is combined (as in Multi Quote), the 'Name' is used to clearly distinguish each section of quoted content for the LLM. This helps the model understand that different representations or perspectives of the same document are being provided.
• In quoting methods such as Layout Objects, the 'Name' may be included in the prompt to clarify the structure or intent of the data, guiding the LLM’s interpretation and extraction logic.
• A descriptive and unambiguous name improves the LLM’s ability to reference, compare, and utilize the quoted data accurately, especially in complex or multi-view prompts.

Configuration and Usage

• Choose a name that reflects the quoting method’s purpose, formatting, or the type of content it produces.
• If left blank, the quoting method’s type name will be used as a default.
• Use consistent naming conventions to support clarity for both users and the LLM.

Example

• Claim Data
• Table Headers
• Layout Objects (JSON)

Best Practices

• Use names that are meaningful to both users and the LLM.
• When using Multi Quote, ensure each quoting method has a unique and descriptive name to maximize clarity in the combined prompt.
• Avoid generic names; be specific about the quoting method’s approach or output.

Overview

The 'Description' property provides a detailed, plain-language explanation of the content or data injected by this quoting method. It is intended to help the LLM understand the structure, semantics, and intended use of the quoted content, as well as to guide the model’s behavior when processing or extracting information from it.

LLM Context Injection

• The description is included directly in the prompt context sent to the LLM, typically as a prefix or annotation before the quoted data.
• In Multi Quote, each quoting method’s description is presented alongside its output, giving the LLM explicit instructions or context for interpreting each section.
• In Layout Objects, the description can clarify the meaning of structured layout data, JSON schemas, or other specialized formats, helping the LLM understand how to use the data for extraction or analysis.
• A well-crafted description can specify the format, highlight important features, explain relationships, or instruct the LLM on how to process the data (e.g., “This section contains a JSON array of line items, each with fields for description, quantity, and price. Extract each item as a separate record.”).

Configuration and Usage

• Write the description for the LLM, focusing on what the data is, how it is structured, and what the model should do with it.
• Include details about formatting, delimiters, field names, or any special conventions used in the quoted content.
• Use markdown formatting, examples, or sample data to illustrate the structure or intent.
• Update the description if the quoting method’s configuration or output changes.

Example

This section contains a table of invoice line items, formatted as plain text with tab-separated columns.
Each line represents a single item, with columns for description, quantity, and unit price.
Extract each line as a separate record and map the columns to their corresponding fields.

Best Practices

• Be explicit and unambiguous; avoid assumptions about the LLM’s prior knowledge.
• Tailor the description to the specific quoting method and output format.
• When using Multi Quote or Layout Objects, ensure each description is distinct and clearly describes the associated data.
• Use examples to illustrate complex or non-standard formats.