📋Overview

track_context() allows you to organize and track GenAI consumption at very granular levels within a larger application. Unlike the @track decorator, you can use track_context() any number of times within a function so that you can instrument parameterized metadata that is only available at runtime.

Purpose of the track_context() context manager

track_context() is used to annotate your functions with dynamic metadata such as:

• Use Case Steps
• User/Account IDs
• Custom Properties

Best Suited For

The track_context() context manager is particularly well-suited for:

• Dynamic parameters that are only available at runtime
• Code block-specific annotations where you don't want to create a separate function
• Temporary parameter overrides within a larger function
• Complex workflows with different tracking needs for different sections

Basic Example: Tracking Users

The track_context() function creates a scope that applies to all GenAI calls made within its block. This behavior gives you precise control over context propagation.

Note that before you can use the track_context() context manager, you must initialize payi_instrument().

from payi.lib.instrument import track_context

def my_function(prompt):
    user_id = get_current_user_id()
    
    # Use track_context for runtime values
    with track_context(user_id=user_id):
        response = client.chat.completions.create(
            model="gpt-3.5-turbo",
            messages=[{"role": "user", "content": prompt}]
        )
    return response.choices[0].message.content

Supported Parameters

The track_context() context manager supports the below parameters. All parameters are optional.