Configuration of a Generative AI chat control

Configure the Generative AI chat control to enter an input for the AI provider to provide the response.

Use the Display rule action to hide or show the control.

The Generative AI chat control is supported only on the Desktop forms.

Name	Description
Header label	The header label to be displayed at runtime.
Provider	Select a Generative AI provider. The Provider list includes the AI providers configured in Integration > Generative AI. See Integrate Generative AI with TotalAgility. If a Generative AI provider is not already configured, a warning message appears when you add the Generative AI chat control to the form.
Source	Select one of the following options: None (default) : The response from the AI provider is based on the input provided (plain text or variables). Image: The response is generated based on the image provided. On the Document list, select a Web capture control and then select the file type on the Mime type list. The following mime types are supported: GIF, JPEG, and PNG (default). All the Generative AI models do not support the use of images. Text: If the document has layout text, such as a semi-structured document (invoice, purchase order, and more) or a fixed form, the document text can provide better results when compared to the results returned using a Custom LLM provider. On the Document list, select a Web capture control. The response is generated based on the text passed as an input at runtime. The text is provided to the AI provider in an optimized (narrated) order. When you set the source format as text, the standard model configuration is used. The following file types that are supported in the Transformation Designer are supported for the text source format in TotalAgility: TIFF (.tif), JPEG (.jpg), PNG (*.png), and PDF. When you set the source format as text, the standard model configuration is used. If the Web capture control was used as a source in TotalAgility 8.0, on upgrading, the Source format is set to Image; otherwise, the source format is set to None.

Name

Description

Header label

The header label to be displayed at runtime.

Provider

Select a Generative AI provider.

The Provider list includes the AI providers configured in Integration > Generative AI. See Integrate Generative AI with TotalAgility.

If a Generative AI provider is not already configured, a warning message appears when you add the Generative AI chat control to the form.

Source

Select one of the following options:

None (default) : The response from the AI provider is based on the input provided (plain text or variables).
Image: The response is generated based on the image provided. On the Document list, select a Web capture control and then select the file type on the Mime type list.

The following mime types are supported: GIF, JPEG, and PNG (default).
All the Generative AI models do not support the use of images.
Text: If the document has layout text, such as a semi-structured document (invoice, purchase order, and more) or a fixed form, the document text can provide better results when compared to the results returned using a Custom LLM provider.

On the Document list, select a Web capture control. The response is generated based on the text passed as an input at runtime. The text is provided to the AI provider in an optimized (narrated) order.

When you set the source format as text, the standard model configuration is used.
- The following file types that are supported in the Transformation Designer are supported for the text source format in TotalAgility: TIFF (*.tif), JPEG (*.jpg), PNG (*.png), and PDF.
- When you set the source format as text, the standard model configuration is used.
- If the Web capture control was used as a source in TotalAgility 8.0, on upgrading, the Source format is set to Image; otherwise, the source format is set to None.

When you view the control at runtime:

A welcome message appears in the Generative AI chat control, such as "Welcome <username>, how can I help you today?".
When you enter any input, a response is returned. If you add an image or provide the document text as part of the input, such as upload an image of car registration, and request the AI provider to get the registration number, the response is returned accordingly.

You need not save the document in the Web capture control to have the Document ID populated.
Make sure the EDoc rendering option is selected in a Web capture control to be able to upload different document types, such as Microsoft Word document.