Add traces to applications: automatic and manual tracing

Learn about the different approaches you can take to add traces to Python and TypeScript generative AI application.

MLflow has three approaches to tracing for Python and TypeScript.

Automatic - Add one line mlflow.<library>.autolog() to automatically capture app logic for 20+ supported libraries.
Manual - Designed for custom logic and complex workflows, control what gets traced using Function Decorator APIs or low-level APIs.
Combined - Mix both approaches for complete coverage.

Which approach should I use?

Start with automatic tracing. It's the fastest way to get traces working. Add manual tracing later if you need more control.

Scenario	Recommendations
Use one GenAI library	Use automatic tracing for your selected library
Use LLM SDKs directly	Use automatic tracing for the API library Add manual tracing decorators to combine multiple LLM calls into a single trace
Use multiple GenAI libraries or SDKs	Enable automatic tracing for each framework / SDK Add manual tracing decorators to combine calls to multiple frameworks or SDKs into a single trace
All other scenarios or you need more control	Use manual tracing: Start with the Function Decorator APIs Use the low-level APIs only if the Function Decorator APIs don't give you enough control

Was this page helpful?