AI configurations

    Last updated on:

    In this page

    Overview

    To enable Zia Insights, the Investigation Agent, and Ask Zia, an AI provider must be configured within the product console. Log360 Cloud currently supports two AI service providers: Azure OpenAI and OpenAI. This page explains how to set up and integrate your preferred AI provider, covering the steps to create an Azure OpenAI resource, obtain the required credentials, deploy a model, and generate an OpenAI API key.

    Pre-requisites

    Before beginning the setup, ensure the following:

    • You must have an active OpenAI subscription or Azure subscription with access to the Azure OpenAI service.
    • The following credentials are required from your Azure portal:
      • Endpoint URL
      • API key
      • Deployed model name
    • The following credentials are required from OpenAI:
      • Model
      • API key

    Creating an Azure OpenAI resource

    If you do not already have an Azure OpenAI resource, follow these steps:

    NOTE If you already have an Azure OpenAI resource, refer to this to obtain the API key and Endpoint URL.
    1. Log in to Azure portal and click Create a resource.
      Creating a resource in Microsoft Azure
      Figure 1: Creating a resource in Microsoft Azure
      Note If you open the Azure AI Foundry portal directly, the portal may load a different resource by default. In that case, you must manually switch to the Azure OpenAI resource you created before proceeding. To switch resources:
      • In the top-right corner of the Azure AI Foundry portal, click the resource selector, which displays the currently loaded resource name and region.
        Creating a resource in Microsoft Azure
        Figure 2: Locating the resource selector
      • In the Azure OpenAI resource pane, select the correct Directory and Subscription.
        Creating a resource in Microsoft Azure
        Figure 3: Selecting directory and subscription
      • Under Working in, choose the Azure OpenAI resource you created.
        Creating a resource in Microsoft Azure
        Figure 4: Selecting the Azure OpenAI resource
      • Click Switch to load the selected resource.
    2. Select Azure OpenAI as the resource type.
      3. Creating a resource in Microsoft Azure
      Figure 5: Creating an Azure OpenAI resource
    3. Choose a Subscription of your choice.
    4. Select an existing Resource group or create a new one.
      5. Creating a resource group in Microsoft Azure
      Figure 6: Creating a resource group in Microsoft Azure
    5. Pick your desired Region and Pricing Tier.
    6. Enter a suitable Name for the resource.
      7. Instance details for Azure OpenAI service
      Figure 7: Instance details for Azure OpenAI service
    7. Under Networking, select All networks, including the internet, can access this resource.

      NOTE The Azure OpenAI resource must be publicly available on the internet so that Log360 Cloud can access the endpoint.

      8. Configuring network security for Azure AI services resource
      Figure 8: Configuring network security for Azure AI services resource
    8. Click Next to configure Tags (optional).
    9. Click Next again to move to the Review + Submit page.
      10. Final review to create resource
      Figure 9: Final review to create resource
    10. Review your settings and click Create to provision the resource.

    Steps to obtain Endpoint URL and API key

    If you already have an Endpoint URL and API key, skip to the next section. If not:

    1. Log in to Azure portal and navigate to your Azure OpenAI resource.
    2. In the left pane, under the Resource Management section, click on Keys and Endpoint. It will open Keys and Endpoint console.
    3. In this window, you will find the Endpoint URL and API keys for your Azure OpenAI resource. Copy these details for use in the product.
    Obtaining API keys and Endpoint URL for Azure OpenAI resource
    Figure 10: Obtaining API keys and Endpoint URL for Azure OpenAI resource

    Deploying a model in Azure OpenAI

    A deployed model is a version of an AI model (such as GPT-4o or GPT-4.1) that has been activated and made available for use within your Azure OpenAI resource. Log360 Cloud will interact with the deployed model to generate AI-powered insights from your logs and alerts.

    NOTE

    If you already have a deployed model, you can directly use its deployment name when integrating with the product. Ensure that the model is one of the following types:

    1. The Chat Completion API model (models GPT-4o or newer). For better results, use latest available model such as GPT-4.1 or newer.
    2. A non-reasoning model, excluding versions like o1-preview and o1-mini

    If you do not have a deployed model, follow the steps below.

    Steps to deploy a model

    1. Navigate to your Azure OpenAI resource and click Go to Azure AI Foundry portal.
      2. Deploying a model in the Azure AI Foundry portal
      Figure 11: Deploying a model in the Azure AI Foundry portal
    2. On the Azure AI Foundry portal, navigate to the Deployments section, click Deploy model, and select Deploy base model.
      3. Deploying a model in Azure AI Foundry portal
      Figure 9: Deploying a model in Azure AI Foundry portal
    3. Choose a model that meets the following constraints:
      • Must support the Chat Completion API (models GPT-4o or newer). For better results, use latest available model such as GPT-4.1 or newer. Avoid reasoning models like o1-preview and o1-mini because they do not support system prompts.
        • Available models for deployment in Azure AI Foundry portal
        Figure 12: Available models for deployment in Azure AI Foundry portal
    4. Enter a deployment name of your choice (defaults to the model name).
      5. Deployment settings in Azure AI Foundry portal
      Figure 13: Deployment settings in Azure AI Foundry portal
    5. Select the deployment type based on your data processing needs. Learn more about deployment types.
      6. Deployment settings in Azure AI Foundry portal
      Figure 14: Deployment settings in Azure AI Foundry portal
    6. Click Create resource and deploy to complete the model deployment.
      7. Model deployment in Azure AI Foundry portal
      Figure 15: Model deployment in Azure AI Foundry portal

    Generating an OpenAI API key

    1. Log in to your OpenAI account.
    2. Click Create new secret key.
      Model deployment in Azure AI Foundry portal
      Figure 16: Creating a secret key
    3. In the pop-up window, select the You tab.
    4. Enter a Name for the key (optional).
      Model deployment in Azure AI Foundry portal
      Figure 17: Entering a name
    5. Select Default project from the Project drop-down.
      Model deployment in Azure AI Foundry portal
      Figure 18: Selecting a project
    6. Choose the appropriate Permissions based on your requirement.
      NOTE For product integration, the key must have permission to read and write API resources.
    7. Click Create secret key.
      Model deployment in Azure AI Foundry portal
      Figure 19: Creating a secret key
    8. Copy the generated API key displayed in the Save your key pop-up.
      Model deployment in Azure AI Foundry portal
      Figure 20: Copying the secret key
    9. Use this API key in the product console when configuring the OpenAI option in Setting up Zia Insights or Setting up Investigation Agent or Accessing Ask Zia.

    Read also:

    This page explained the steps required to configure an AI provider in ManageEngine Log360 Cloud. To enable and use the individual Zia capabilities, refer to the following articles: