Azure OpenAI is the AI service used by Copilot, which is provided by Microsoft. Follow the steps provided here to set up the service. Then, fill in the following configuration fields:

• AI Connection Name: This name is always used when a specific AI connection is used.
• Azure OpenAI Endpoint: This is the URL generated from the AI resource in Azure
• Azure OpenAI Deployment: A deployment is created for a specific AI model, such as gpt-4o. When creating a deployment, a custom name can be set and must be used here to access this model.
• API Version: The Azure OpenAI API version (e.g. 2024-02-15-preview). You can find supported versions in the Azure portal or API documentation.
• System Prompt: A preset system prompt to instruct ChatGPT to answer with a specific behavior.
• API Key: This is one of the two secret keys created during AI resource-creation in Azure
• Max Context Length (tokens): Maximum number of tokens (input and output combined) the model can process. Exceeding this may cause errors or truncation.

Important: The Azure OpenAI Deployment is not necessarily the model name. It is a custom name that you can define when creating the deployment.

Note: You can find Azure OpenAI model pricing information here.