JSON File

Specify the filename of the JSON file to inject from the Batch Object.
The file must exist on the folder or page node for content to be included.

Impact

• If the file does not exist and 'Required' is true, an exception is thrown.
• If 'Required' is false, no exception is thrown and content is omitted.

> Example:
> Metadata.json

Set to true to enforce the presence of the file; set to false to allow omission if the file is missing.

Impact

• When enabled, missing files cause an error and halt processing.
• When disabled, missing files are ignored and no content is injected.

Enable to aggregate JSON content from every page within the folder; disable to use only the folder-level file.

Usage

• Use for multi-page documents where each page contains relevant JSON data.
• For single-folder content, leave disabled.

Enter a JSONPath expression to extract only the desired portion of the JSON file.

Example

$.InvoiceData

Impact

• Only the selected content is injected into the prompt.
• If empty, the entire JSON file is used.

Use a JSONPath expression to exclude specific elements from the injected JSON.

Example

$.SensitiveInfo

Impact

• Selected content is removed before injection.
• Multiple selectors can be separated by commas.

Specify a JSONPath to identify polygon objects in the JSON file.
These will be converted to rectangle representations for downstream processing.

Example

$.Shapes[*].Polygon

Impact

• Polygons are replaced with rectangle arrays in the injected content.

Use a JSONPath expression to identify objects or arrays that should be collapsed into their parent object.

Example

$.Details.CollapseMe

Impact

• Collapsed objects are merged into their parent, simplifying the JSON structure.

Indicates the type or category of content being injected, used for formatting or labeling in the prompt.

Usage

• Set automatically based on the 'Content Selector'.
• May be used to wrap or annotate injected content.

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.