- In Azure, go to Azure AI Services > select your deployment > open Azure OpenAI Studio.
- On the left menu, click Deployments. If you don’t have one, create a deployment with your desired model.
- Once created, select your deployment and locate the Target URI and Key on the right side of the page. Keep this page open, as you’ll need this information.
- In another tab, open CrewAI Enterprise > LLM Connections. Name your LLM Connection, select Azure as the provider, and choose the same model you selected in Azure.
- On the same page, add environment variables from step 3:
- One named
AZURE_DEPLOYMENT_TARGET_URL(using the Target URI). The URL should look like this:https://your-deployment.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-08-01-preview - Another named
AZURE_API_KEY(using the Key).
- One named
- Click Add Connection to save your LLM Connection.
- In CrewAI Enterprise > Settings > Defaults > Crew Studio LLM Settings, set the new LLM Connection and model as defaults.
- Ensure network access settings:
- In Azure, go to Azure OpenAI > select your deployment.
- Navigate to Resource Management > Networking.
- Ensure that Allow access from all networks is enabled. If this setting is restricted, CrewAI may be blocked from accessing your Azure OpenAI endpoint.
You're all set! Crew Studio will now use your Azure OpenAI connection.