Layout Objects

Can be one of the following types:

The 'Quote Extractor' property allows you to select a Value Extractor to identify specific content within the document that should be included in the layout data supplied to the AI.

• When set, only the content matched by the selected Value Extractor—along with its layout information—will be included in the output.
• If left blank, the layout data for the entire document is provided, including all text, lines, barcodes, and checkboxes.

Usage Guidance

Use this property to focus the AI's attention on relevant regions such as the first or last N pages..

The 'Document Level' property controls the scope at which the Quote Extractor runs.

• When enabled (true), the extractor runs against the entire document.
• When disabled (false), the extractor runs against the content of the current Data Element Container.

Usage Guidance

• Enable this property to target content outside the scope of the current Data Element Container.
• Disable to focus the AI on a specific region, reducing prompt size and emphasizing only the relevant content.

Impact

• Enabling 'Document Level' may increase the size of the input data but can improve extraction accuracy for tasks that require full-page or multi-region context.
• Disabling it is recommended for targeted extraction or when working with very large documents.

The 'Include Plain Text' property controls whether a plain text representation of the document's content is supplied alongside the structured layout data.

• When enabled (true), the output will include a plain text version of the document, in addition to the JSON schema and layout data.
• When disabled (false), only the structured layout data is provided.

Usage Guidance

Enable this property if you want the AI to have access to both the spatially-structured layout and a linear, plain text version of the content. This can be helpful for tasks where both the visual arrangement and the raw text are relevant, such as text extraction, summarization, or hybrid workflows.

The 'Include Schema' property controls whether the JSON schema describing the layout data structure is provided to the AI model along with the actual data.

Usage Guidance

• Enable this property to supply the AI with a formal schema, improving its ability to interpret and utilize the layout data.
• Disabling this property omits the schema, which may be appropriate if the AI is already familiar with the expected structure or if prompt size is a concern.

Impact

• Including the schema is recommended for most scenarios, as it clarifies the structure and field definitions for the AI.
• Omitting the schema may reduce prompt size but can lead to less reliable extraction or misinterpretation of the data.

A combination of the following flags:

{ "content": "Invoice Number", "bounds": "1.25 2.00 0.75 0.25" }

"lines": [ "0.00 1.00 8.50 1.00", "2.00 0.00 2.00 11.00" ]

{ "type": "Code128", "value": "123456789", "bounds": "0.50 0.50 1.00 0.25" }

{ "checked": true, "bounds": "3.00 4.00 0.20 0.20" }

The LayoutComponentTypes enumeration defines the set of visual and structural elements that can be included in the layout data generated by the Layout Objects quoting method. This allows you to precisely control which aspects of the document's visual structure are supplied to the AI model for extraction, analysis, or understanding.

Use this enumeration to enable or disable the inclusion of text segments, lines, barcodes, and checkboxes in the generated layout data. The LayoutComponentTypes enum supports bitwise combination, so you can select any combination of components to match your extraction requirements.

Usage and Configuration

• Set the 'Layout Components' property to specify which layout elements are included in the output.
• Combine multiple values using the bitwise OR operator (e.g., Text | Lines | Barcodes) to include several types.
• Use the All value to include every supported layout component in the output.

Considerations

• Including more components provides the AI with richer context but may increase prompt size.
• Exclude components that are not relevant to your extraction scenario to streamline processing and focus the AI's attention on the most important elements.

Adjust the selection based on the structure and requirements of your documents and extraction workflow.

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.