› Configure the Generative AI provider

Configure the Generative AI provider

To start using Copilot, you must have already configured the AI provider integration in the TotalAgility Designer. If you do not have the Generative AI integration, configure the AI provider in Kofax Copilot.

  1. On the TotalAgility Apps Home page, click the Kofax Copilot card.

    You are prompted to configure a Generative AI provider.

  2. Click Configure.

    The New AI provider configuration dialog box is displayed.

  3. On the Type list, select one of the AI providers and configure it to use as a standard model or vision model.

    Configure the standard model settings when you make use of an AI provider and do not use an image to generate an item.

    Configure the vision model settings when you make use of an AI provider and use an image to generate an item. If the vision settings are not configured or the model specified does not support the use of images, an error occurs.

    • ChatGPT OpenAI (default)

      Configuration settings

      Description

      ID

      Provide a unique ID for the AI provider.

      Display name

      Enter the AI provider name to help in identifying the server's name in the list.

      Use legacy function syntax

      The "function" syntax used by TotalAgility to send the request to the AI provider. (Default: Selected and read-only)

      Use as Copilot provider

      The read-only field is selected by default as there should be at least one AI provider used as the Copilot.

      Use as Extraction provider

      The read-only field is not selected by default. If this option is selected in the TotalAgility Designer while configuring the Generative AI provider, the AI provider is used as an Extraction provider.

      When multiple AI providers are configured, you can use only one AI provider (ChatGPT or OpenAI) for data extraction.

      Standard Model
      API URL

      The default API URL (https://api.openai.com/v1/chat/completions) for the selected provider appears.

      API key

      Provide the free text that allows to specify any model.

      Model

      The system displays the AI provider model as gpt-3.5-turbo (default). However, you can change the model to align with your requirement.

      Temperature

      Set the process Temperature for the AI provider. (Default: 0.2, Minimum value: 0, and Maximum value: 2)

      Temperature is a parameter that controls the level of creativity in the AI-generated text. You get a more focused or diverse text based on the temperature set. A higher temperature means the model takes more risks, giving you a mixed response.

      Vision Model
      API URL

      Enter the API URL for the vision model.

      API key

      Enter the API key.

      Model

      Optional. The AI provider model when an image is used as input. For example, gpt-4-vision-preview. However, you can change the model to align with your requirement.

      Token limit

      By default, the token limit for the provider is 3000.

      The tokens are word fragments that are generated when the AI provider processes the input. The token limits restrict the number of tokens (usually words) sent to a model per request.

    • Azure OpenAI

      The Azure OpenAI provider type has the same configuration options as ChatGPT OpenAI except that the default API URL is displayed as empty. You must provide the URL.

  4. Click Save and click OK.
    The AI provider is configured and you are redirected to the Copilot.

    The AI provider configured here appears on the Integration menu > Generative AI providers page in the TotalAgility Designer.