Adding New Fields

Follow the interactive tutorial below and learn how to add new fields for extraction with super.AI Intelligent Document Processing (IDP).

Summary: How to add a new field

Preparation

  1. Access Project Settings:
    • Navigate to the dashboard and select the project to add a new field to.
    • Click Project Settings > Add new field.

Field Settings

  1. Name:
    • Provide a name. An ID is generated automatically.
  2. Data Type:
    • Choose the data type from the dropdown. E.g., String.
    • 📌 Data type options are defined below this tutorial.
  3. Annotation Requirement:
    • Toggle: Decide if the field needs annotation.
    • Type: If toggled on, select the annotation type: BoundingBox or Table.
      • BoundingBox: Draws a box around the field.
      • Table: Uses table editing for document review.
    • 🚫 Annotations may affect data extraction accuracy.
  4. Redaction Requirement:
    • Toggle: Decide if the field needs redaction.
    • Type: If toggled on, select redaction type: Blacken or Blur.
      • Blacken: Draws black marks over the new field when it is detected in documents. Useful for redacting text.
      • Blur: Automatically blurs the new field in documents. Useful for faces, objects, etc.
  5. Description:
    • Briefly describe the field for reference in Job Settings.

Advanced Settings (Optional)

  1. Status:
    • Toggle new field on/off for data processing.
  2. Aliases:
    • Provide alternate names to enhance AI recognition.
    • 💡 The platform uses Large Language Models (LLM) for recognition. Aliases can improve accuracy, especially with varied naming.
  3. Instructions:
    • Clearly describe how to extract the field.
  4. Additional Advice:
  • Offer optional tips for improved field extraction.
  1. Examples:
  • Provide valid examples of the extracted outputs.
  1. Anti Examples:
  • Show what the extracted output should NOT look like.
  1. Validation Rules:
  • Constrain valid output types.

Finalization

  1. Add Field:
  • Click Add field to add the new field to the project. After doing so, you will be redirected to the Job Settings page.
  1. Reorder Fields (Optional):
  • Drag to rearrange.
  1. Save:
  • Click Save changes for the new field.
  1. Pop-up Selections (Optional):
  • Unprocessed: Search unprocessed documents for the new field.
  • In Progress: Extract the new field from ongoing processes.
  • Completed: Reprocess all completed documents to extract the new field.
    • 🚫 This will require reprocessing all completed documents.
  1. Confirm Changes:
  • Click Save changes and await the confirmation message.

Data Type Definitions

Data TypeDescription
Single ChoiceSelect one from predefined options.
Multiple ChoiceSelect multiple from given options with set limit.
StringSequence of characters, including spaces and numbers.
IntegerWhole numbers, including negatives.
FloatNumber with a decimal place
BooleanLogical value: True or False.
DateCalendar date in DD-MM-YYYY format.
EntityDistinct data object representing a real-world item.
TableData arranged in rows and columns.
CalculatedMatch values with databases (e.g., Excel).
StampData marker or label for verification or categorization.