Using OpenAI with Hudini

Integration Features

• Generate AI responses from prompts anywhere in your Hudu environment. Prompt Hudini to provide a write up that you can copy directly into a KB article. 

What Hudu needs from OpenAI

• API Token

Model Selection

Hudu by default will pre-select the latest version of ChatGPT for you to use unless otherwise specified.

Generation

Once Hudini is enabled in Hudu Admin:

• Click on the Hudini Icon on the toolbar next to your profile. 
• Ask Hudini a question. If you have preconfigured prompts, select the desired one before asking. 

• Insert your prompt of choice into the provided field and click the arrow icon to generate.
  • Depending on the prompt, this can take a few minutes to generate.
• When you're happy with the response, you can click either copy icon (copy text or copy HTML) down at the bottom, and paste it into your desired location. 

What Hudu needs from Azure OpenAI:

• Endpoint
• API Key
• Deployment name
• API Version

Configuring Azure OpenAI

These steps use the New Foundry interface in Azure AI Foundry. If your portal shows a "New Foundry" toggle in the top right, leave it on to match the steps below.

What Hudu needs from Azure OpenAI

• Endpoint
• API Key
• Deployment name
• API Version

In Azure

Create the resource

• In the Azure portal, create an Azure AI Foundry (Azure OpenAI) resource.
• Choose your subscription, resource group, and region, then work through the network, tags, and review steps and select Create.
• When it finishes, select Go to resource, then open the Azure AI Foundry portal.

Deploy a model

• In the left panel, select Models.
• Select Deploy model, then Deploy base model.
• Choose a model (for example, gpt-5), then select Deploy.

Find your Endpoint, Key, and Deployment name

• Select your deployment, then open the Details tab.
• Your Key is shown at the top of this tab.
• Your Deployment name is listed under Deployment info > Name.

In Hudu

• Navigate to Admin -> Hudini
• Enable Hudini
• Find and select Azure OpenAI from the list
• Enter your API Key from the deployment Details tab
• Enter your Endpoint, built in this format using your own resource name and deployment name:
  • https://your-resource-name.openai.azure.com/openai/deployments/your-deployment-name
• Enter API Version:
  • Use 2025-04-01-preview. Current Azure models (the GPT-5 family) require this version or newer. Older versions such as 2023-05-15 will return a "resource not found" error.
  • This is the Azure API version, not the model version listed under Deployment info. The two are different, and entering the model version here will cause the same error.
• Select Save

In Hudu:

• Navigate to Admin -> Hudini
• Enable Hudini
• Find and select Azure OpenAI from the list
• Input your API Key and Endpoint from your deployment
  • The endpoint will need to be edited to look like the following, where the deployment name matches the name of your deployment:
    • https://example.openai.azure.com/openai/deployments/gpt-5
• Enter API Version:
  • Use 2025-04-01-preview. Current Azure models (the GPT-5 family) require this version or newer. Older versions such as 2023-05-15 will return a "resource not found" error.
  • This is the Azure API version, not the model version listed under Deployment info. The two are different, and entering the model version here will cause the same error.

FAQ