This assumes that an Azure deployment has already been created. If you’re adding a new Azure hosted model for the first time, start with Deploying a GPT Model in Microsoft Foundry
| Name | Value |
|---|---|
| Provider adapter name | azure (for OpenAI models on Azure) |
| Model | The model that was deployed |
| Pretty Name | Name that will show in the provider dropdown on the main page (usually ChatGPT) |
| Pretty Model | The model that will show in the provider dropdown (usually the same as model) |
| Category | Set the model as Internal (Within your existing data governance) or External (Outside your existing data governance) |
| Endpoint | The endpoint. Usually: |
| https://{NAME}-aiportal.cognitiveservices.azure.com/openai/v1/ |
| | Deployment | The name of the deployment | | Model Deployment Quota | The rate limit for the model deployment | | Tags | Features of that provider disabled → will disable selection in the chat dropdown upload → Allow file uploads (discouraged for External models) dlp → enable dlp (encouraged for External models) hidden → do not display the selection in the chat dropdown | | RAG Search | OPTIONAL Set this to the Provider Config to a RAG Search Config. Responses from the model will include context from your RAG configuration. |
