Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
While MLflow's automatic tracing provides instant observability for supported frameworks, manual tracing gives you complete control over how your GenAI applications are instrumented. This flexibility is essential for building production-ready applications that require detailed monitoring and debugging capabilities.
When to use manual tracing
Manual tracing is the right choice when you need:
Fine-grained control over trace structure
- Define exactly which parts of your code to trace
- Create custom hierarchies of spans
- Control span boundaries and relationships
Custom framework instrumentation
- Instrument proprietary or internal frameworks
- Add tracing to custom LLM wrappers
- Support new libraries before official integration
Advanced workflow scenarios
- Multi-threaded or async operations
- Streaming responses with custom aggregation
- Complex nested operations
- Custom trace metadata and attributes
Which API should I use?
Choose the right manual tracing approach for your needs:
| Feature | Function decorators | Span tracing | Low-Level APIs |
|---|---|---|---|
| Use case | Trace entire functions with one-line decorator. Minimal code changes required. | Trace arbitrary code blocks within functions for fine-grained control. | Direct control over trace lifecycle for complex scenarios. |
| Automatic Parent-Child | Yes | Yes | No - manual management |
| Exception Handling | Automatic | Automatic | Manual |
| Works with Auto-trace | Yes | Yes | No |
| Thread Safety | Automatic | Automatic | Manual |
| Custom Trace IDs | No | No | Yes |