Auto-scale Insights - Intelligent Recommendations

Note: This is a preview feature. Follow the recommendations provided by the feature only if you understand and agree with the implications of the change. Some recommendations may not be valid for your environment. Please report any unexpected results to the Nerdio team using the Data Manager tool.

This article provides a step-by-step guide on how to configure your application to enable auto-scale insights recommendations using OpenAI integration within Azure. It also outlines the process for generating and displaying recommendations for optimizing auto-scale configurations.

Note: Nerdio Manager leverages Azure OpenAI services, which are provisioned as dedicated Azure resources within your organization's Azure tenant. These services operate entirely within the confines of your controlled environment, ensuring that all interactions are isolated from publicly available AI systems. There is no communication or data exchange between Azure OpenAI services and publicly accessible models, such as ChatGPT or other large language models (LLMs) provided by Microsoft or third-party vendors.

In addition, any information included in prompts or queries sent to the Azure OpenAI resources remains securely within your Azure tenant. This design ensures that your data is not exposed to external systems, complies with stringent security and privacy standards, and aligns with organizational governance requirements. By using Azure OpenAI, Nerdio Manager guarantees a secure and private AI experience tailored to meet your operational needs. See Data Security and Privacy with Azure OpenAI in Nerdio Manager for details.

Enable OpenAI Integration

Follow in the instructions in Overview of AI-Powered Description Generation to enable OpenAI integration.

Note: It is highly recommended that you use GPT version 4 or higher for optimal results. Earlier versions of GPT are not recommended for use in this feature.

View Auto-scale Insights Recommendations

The auto-scale insights recommendations can be viewed at any time.

To view auto-scale insights recommendations:

  1. Locate the dynamic host pool you want to work with.

  2. From the action menu, select Auto-scale > Configure.

  3. Select the auto-scale insights pop-up icon , and then select Load Recommendation to generate the AI auto-scale intelligent recommendations.

    Note: Optionally, you can configure the intelligent recommendations to be automatically loaded without the need to select Load Recommendation. See Overview of AI-Powered Description Generation for details.

Auto-scale Insights Recommendation Workflow

Once OpenAI integration is enabled, the system follows a structured workflow to generate auto-scale insights recommendations.

Generate a Request

When the user selects the Load Recommendation button inside the Auto-scale Insights pop-up, a request is automatically generated.

  • Request Template: The request uses a predefined template that includes detailed instructions regarding the structure of the auto-scale system and identifies potential issues that may arise.

  • Data Attachment: The data visualized on the graph is automatically converted into a CSV file in a specific format and appended to the request. A human-readable description of the auto-scale configuration is also included.

Process the Response

Upon receiving the response from OpenAI:

  • The data is parsed and cached in the system’s database.

  • The processed recommendations are then presented to the user in the application’s user interface (UI).

Cache for Future Use

The system stores the parsed data in a cache, allowing it to display the same recommendations when the user selects the same date and host pool in the future. This improves overall user experience by reducing load times for recurring requests.