Tools that can be used with existing labs:
- Tracing - Invoke AI Foundry model API's with trace enabled and returns the tracing information.
- Streaming - Invoke AI Foundry model API's with stream enabled and returns response in chunks.
- AI-Gateway Mock server is designed to mimic the behavior and responses of the OpenAI API, thereby creating an efficient simulation environment suitable for testing and development purposes on the integration with APIM and other use cases. The app.py can be customized to tailor the Mock server to specific use cases.
- Python 3.12 or later version installed
- VS Code installed with the Jupyter notebook extension enabled
- uv — run
uv syncfrom the repo root to install dependencies - An Azure Subscription with Contributor + RBAC Administrator or Owner roles
- Azure CLI installed and Signed into your Azure subscription