› Integration › Generative AI › Integrate Generative AI with TotalAgility

Integrate Generative AI with TotalAgility

Use the following procedure to integrate TotalAgility with Generative AI. You can add, modify, or delete a provider.

By default, the Generative AI provider integration is not available on a clean TotalAgility installation and upgrade.

  1. Navigate to Integration > Generative AI.

    The Generative AI providers page appears.

  2. Click New.

    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. If you clear the check box, TotalAgility makes use of the latest "tools" function syntax to send the request.

      When you execute the Copilot, Generative AI Activity, or a Generative AI action using the Data objects, the legacy or latest function syntax is used depending on the setting configured. If the model does not support the syntax, an error occurs.

      Use provider as:

      Copilot for development

      If selected, the AI provider is used as the Copilot for development. (Default: Clear)

      You can have multiple AI providers but use only one AI provider (ChatGPT OpenAI or Azure OpenAI) as the Copilot for development.

      Copilot for extraction

      If selected, the AI provider is used as an Extraction provider. (Default: Clear)

      When multiple AI providers are configured, you can use only one AI provider (ChatGPT OpenAI or Azure OpenAI) as Copilot 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

      Enter the API key.

      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.

    • Custom LLM

      Configuration settings

      Description

      ID

      Enter an ID for the AI provider.

      The system identifies the AI provider with this ID.

      Display name

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

      Process

      select the custom service or synchronous process that has the following variables.

      Variable name

      Variable type

      Initialization

      Inputs:

      Input Prompt

      String

      Yes

      Temperature

      Double

      Yes

      Outputs:

      Output

      String

      No

      If the required process is not available, click the Create new process link to automatically create a synchronous process with the correct input and output variables.

      You cannot delete a process if it is configured as a custom LLM AI provider.

  4. Click Save.
    The configured AI provider appears on the Generative AI providers page. You can update or delete an existing Generative AI provider.

    You can add more than one integration for Generative AI providers.

How to: Maintain a Generative AI integration