Get started with ABV tracing in your Python application in under 5 minutes
If you’re creating a new ABV account, the onboarding flow will guide you through these steps automatically. This guide is for manual setup or reference.
Get your API key
Create an ABV account and generate API credentials:
ABV’s Python SDK offers multiple ways to create traces. Choose based on your use case:
Gateway Auto-Tracing
@observe Decorator
Context Managers
Best for: LLM applications that need automatic tracing with zero manual instrumentationThe ABV Gateway is the fastest way to get complete observability for LLM calls. It automatically captures all metrics without any manual tracing code.
New users get $1 in free credits to test the gateway.
Copy
from dotenv import load_dotenvfrom abvdev import ABV# Load environment variablesload_dotenv()# Initialize the ABV clientabv = ABV() # Uses ABV_API_KEY from environment# Make a gateway request - automatically creates a complete traceresponse = abv.gateway.chat.completions.create( provider='openai', model='gpt-4o-mini', messages=[ {'role': 'user', 'content': 'What is the capital of France?'} ])# Access the responseoutput = response['choices'][0]['message']['content']print(f"Response: {output}")
What gets captured automatically:
Full conversation context (user query and LLM response)
Model and provider information
Token usage (input/output counts)
Cost tracking (deducted from gateway credits)
Latency metrics (total duration and API timing)
Switch providers easily:
Copy
# Try Anthropic's Clauderesponse = abv.gateway.chat.completions.create( provider='anthropic', model='claude-sonnet-4-5', messages=[{'role': 'user', 'content': 'What is the capital of France?'}])# Or try Google's Geminiresponse = abv.gateway.chat.completions.create( provider='gemini', model='gemini-2.0-flash-exp', messages=[{'role': 'user', 'content': 'What is the capital of France?'}])
The gateway requires no additional setup beyond installing abvdev. It automatically handles tracing, cost tracking, and provider switching.
Best for: Simple functions where you want automatic instrumentationThe @observe decorator is the easiest way to add tracing. It automatically captures function name, arguments, return value, and timing.
Copy
from dotenv import load_dotenvfrom abvdev import observe, get_client# Load environment variablesload_dotenv()@observedef my_function(): # Function logic here return "Hello, world!"# Call the function - it's automatically tracedmy_function()# Flush events in short-lived applicationsabv = get_client()abv.flush()
What gets captured:
Function name and arguments
Return value
Execution time
Any exceptions raised
The @observe decorator is perfect for quick instrumentation. Just add it to any function you want to trace!
Best for: Fine-grained control over what you track and whenContext managers give you more control over instrumentation. They’re ideal for complex workflows where you need to track specific operations.
Copy
from dotenv import load_dotenvfrom abvdev import get_clientload_dotenv()abv = get_client()# Create a parent span for the entire requestwith abv.start_as_current_span(name="process-request") as span: span.update(input={"query": "What is the capital of France?"}) # Create a nested generation for an LLM call with abv.start_as_current_observation( as_type='generation', name="llm-call", model="gpt-4o" ) as generation: # Simulate LLM response generation.update(output="The capital of France is Paris.") span.update(output="Processing complete")# Flush events in short-lived applicationsabv.flush()
Key benefits:
Explicit control over what’s tracked
Easy nesting of observations
Update metadata at any point
Automatic cleanup when context exits
Context managers automatically close spans when exiting the with block, preventing memory leaks and ensuring data is sent to ABV.
Execute your Python script to send your first trace to ABV:
Copy
python your_script.py
Navigate to app.abv.dev and click Traces in the sidebar. You should see your trace with:
The function/span name
Input and output data
Nested observation hierarchy (if using context managers or gateway)
Timing information and metrics
If you don’t see traces immediately, wait a few seconds and refresh. Make sure you called abv.flush() for short-lived scripts (not needed for gateway requests).
The abv.flush() call is only needed for short-lived scripts that exit immediately. Long-running applications (web servers, background workers) don’t need it.
