Configuring integration with AI

Introduced in 2024.2

Alloy Navigator offers built-in AI-assisted features to help users with essential text-processing tasks. To enable AI assistance, you need to provide your organization’s API key and configure additional settings in the desktop Settings App, under AI Integration > AI Configuration. This page guides you through setting up AI integration.

Turn AI assistance on or off

The Enable AI features checkbox on the AI Integration > AI Configuration page controls the availability of all AI features in Alloy Navigator. Use this option to enable or disable AI assistance with a single click.

"AI features" include AI actions (both system and custom) and AI-assisted voice capabilities (Text-to-Speech and speech recognition).

Depending on your configuration, there are three possible scenarios:

• Initial setup

  Initially, AI features are enabled, while your API key and other configuration settings have not been provided yet. To complete the setup, you will need to configure the AI integration as described in Configure AI integration below.

  

• AI features are enabled, AI integration is set up

  Once the API key is provided and the integration is configured, AI features are activated and ready for users.

  

• AI features are disabled

  If you disable AI features, they will be hidden from users, regardless of whether the API key or other configuration settings are provided.

  

Configure AI integration

To configure AI integration in Alloy Navigator, you will need a verified account in your AI provider and a generated secret API key. Alloy Navigator supports language AI models from the most trusted providers and gives you complete control over AI usage and the flexibility to manage associated costs.

To configure AI integration:

1. Go to AI Integration > AI Configuration and, under AP Provider, choose your provider:

   • OpenAI API: Use this option for direct integration with OpenAI’s models, offering flexible and powerful AI capabilities for various text-processing tasks.

   • Azure OpenAI Service: Choose this option if you prefer to use OpenAI’s models hosted on Microsoft Azure, providing additional integration with Azure’s cloud services and security features.

2. For Azure OpenAI Service, use the Endpoint URL field to enter your unique URL provided by Azure to communicate with the API. You can obtain this URL in the Azure portal, it typically looks like this: https://<resource-name>.openai.azure.com/

3. In the API key field, provide your secure key for authenticating requests to your AI provider’s API.

   For OpenAI, you can find or generate your API key in your OpenAI account dashboard, under the API Keys section. For Azure OpenAI Service, you can obtain your API key from the Azure OpenAI resource, under the Keys and Endpoint page.

4. In the Completion model/Completion deployment name field, specify the completion model you want to use. For Azure OpenAI Service, this completion model must be deployed in your Azure OpenAI, and you need to enter the name of this instance.

5. If you want to enable Text-to-Speech feature, select the Enable Text-to-Speech checkbox.

   Then specify the Text-to-Speach (TTS) model you want to use. For Azure OpenAI Service, this TTS model must be deployed in your Azure OpenAI, and you need to enter the instance name.

6. If you want to enable speech recognition, select the Enable speech recognition checkbox.

   Then specify the transcription model you want to use to transcribe spoken language into text. For Azure OpenAI Service, enter the name of a deployed transcription model.

   TIP: For speech recognition to work, the site hosting the Web App must permit access to audio input devices. Ensure that no restrictions, such as a Permissions-Policy: microphone header, block microphone access.

7. Click Save to apply your changes.

Related Information:

Managing AI actions