Azure
Integrating Azure (Azure OpenAI Service) with Lakehousecat enables Chat and Speech-to-Text (STT) capabilities. This page describes how to configure Azure as a Provider Model.
Prerequisites
- Access to Lakehousecat as an Administrator
- An active Azure subscription with Azure OpenAI resources
- Azure Endpoint URL, API Key, Region, Deployment ID, and API Version
Configuration
Navigate to Workspace → Models → Provider Models and click the + icon.
Step 1: Select Provider Type
From the Provider Type dropdown, select Azure.
Step 2: Select Model Type
Choose the appropriate model type: Chat or STT.
Step 3: Enter Configuration Details
All Azure configurations require the following base fields:
| Field | Description |
|---|---|
| Configuration Name | A unique name for this configuration (e.g. azure-gpt4o-chat). |
| Azure Endpoint URL | Your Azure resource endpoint (e.g. https://YOUR_RESOURCE_NAME.openai.azure.com/). |
| Azure Region | The Azure region of your resource (e.g. swedencentral). |
| Azure API Key | Your Azure API key from the Azure Portal. |
| Azure API Version | The API version for your deployed model (available in the Azure Portal). |
| Azure Model ID (Deployment ID) | The Deployment ID for your Azure model. |
Additional Fields for STT
| Field | Description |
|---|---|
| STT Language Locales (optional) | Comma-separated locale codes (e.g. en-US, de-DE). Leave blank for auto-detection. |
Step 4: Save
Click Save. After saving, you can optionally set this configuration as the default UI model or default Backend model.
Tested Configurations
Azure has not gone through a dedicated model-by-model test round the way the other providers have (see There is no single "right" provider). It is used internally as a known-good baseline via a GPT-4-class deployment, which has been reliable in practice. If you're evaluating specific Azure OpenAI deployment models, the same GPT-family guidance from the OpenAI provider page generally applies, since Azure OpenAI serves the same underlying models.
Best Practices
- Use a consistent naming convention that identifies the Azure resource and model type.
- Consult the Microsoft Azure documentation for the correct API version for your deployment.
Troubleshooting
- Validation Errors: Verify the Endpoint URL, API Key, Deployment ID, Region, and API Version.
- Access Issues: Confirm that your Azure role has the necessary permissions for the OpenAI resource.