Prompt tags in generative AI prompts are used by the Document Extraction engine to enable specific extraction logic that helps to accurately extract data from complex layouts.

Note: Ensure that you are using the Document Extraction package version 3.35.14 or later to use prompt tags in generative AI prompts.

Using prompt tags might be useful in specific scenarios where you do not have to experiment using complex prompts to extract specific information. Prompt tags are used in the format @Tagname and are added at the end of the generative AI prompts.

Benefits

Using prompt tags in the generative AI prompts for data extraction provides the following benefits:

  • Improved efficiency: You can use prompt tags to easily extract information from separate detectable tables and from specified tables.
  • Predefined prompt tags: These tags are specifically introduced to handle data extraction in complex scenarios such as linked tables, signatures, and field relationships.

Prompt tags support matrix

The following table provides the list of prompt tags supported in Document Automation:

Note: Prompt tags are not case sensitive. For example, you can use @GenAIVision or @genaivision to use vision-powered generative AI models for data extraction.
Prompt tag Description Prompt tag used in Example prompt Supported package version
@AdvancedExtraction Use this tag to indicate to the Document Extraction engine to use advanced vision-powered generative AI models for better data extraction in scenarios such as table spanning across multiple pages with headers only on the first page, tables with a table, and tables without a proper structure.
Note: Using this prompt tag might impact the processing time.

You must add this tag at the end of a single table field per table or in the table prompt to use vision-powered generative AI models for data extraction.
  • Table field
  • Table prompt

The following prompt uses advanced vision-powered generative AI models to extract product information from documents containing tables spanning across multiple pages with headers only on the first page.

What is the Product Information? @GenAIVision @AdvancedExtraction		 3.36.10
@GenAIVision Use this tag to indicate to the Document Extraction engine to use vision-powered generative AI models for data extraction.

This tag is particularly useful to extract data in complex scenarios such as linked tables, tables spanning multiple pages, nested tables, and merged cells.

Use the following guidelines to add this tag to form and table fields that requires vision-powered generative AI model:

  • Form fields: You must add this tag at the end of each form field.
  • Table fields: You must add this tag at the end of at least one of the table fields for each table.
Note: Vision-powered generative AI models are not supported for form fields in the unstructured document type.
  • Form field
  • Table prompt
  • The following prompt used in a form field uses vision-powered generative AI models to extract benefits number from documents:

    What is the explanation of benefits number? @GenAIVision

  • The following prompt used in a table field uses vision-powered generative AI models to extract claim number from documents:

    What is the Claim Number? @GenAIVision

 3.35.14
@LinkingField Use this tag to indicate to the Document Extraction engine that a table field can be used to link separate detectable tables.

Adding this tag ensure that a new column is created in the output file for the linking field.

 Table field

The following prompt uses vision-powered generative AI models to extract patient names from documents that contain separate tables for each patient containing patient information. In this case, the patient names are extracted in a separate column in the output file.

What is the Patient Name? @GenAIVision @LinkingField		 3.35.14
@TableIdentifier *Table title* Use this tag to indicate to the Document Extraction engine to differentiate specific tables. The table title is as defined in the document to be extracted and not the table name defined in the learning instance.

You must add this tag at the end of a single table field per table to use vision-powered generative AI models for data extraction.

 Table prompt
  • The following prompt uses vision-powered generative AI models to extract information about herbicides from the table named "Herbicides" as specified in the document:

    What is herbicides? @GenAIVision @TableIdentifier *Herbicides*

  • The following prompt uses vision-powered generative AI models to extract information about insecticides from the table named "Insecticides" as specified in the document:

    What is the insecticides product name? @GenAIVision @TableIdentifier *Insecticides*

 3.35.14