Skip to main content
  1. Sign up — Create an account at platform.respan.ai
  2. Create an API key — Generate one on the API keys page
  3. Add credits or a provider key — Add credits on the Credits page or connect your own provider key on the Integrations page

​
What is Respan Tracing?

The Respan tracing SDK uses OpenTelemetry under the hood. Add the respan_tracing package to your project and annotate your workflows with @workflow and @task decorators to get full trace visibility.

​
Setup

1

Install the SDK

pip install respan-tracing
Python Requirement: This package requires Python 3.9 or later.
2

Set environment variables

RESPAN_BASE_URL="https://api.respan.ai/api"
RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
3

Initialize and run a workflow

import os
from openai import OpenAI
from respan_tracing.decorators import workflow, task
from respan_tracing.main import RespanTelemetry

# Initialize Respan Telemetry
os.environ["RESPAN_API_KEY"] = "YOUR_RESPAN_API_KEY"
k_tl = RespanTelemetry()

# Initialize OpenAI client
client = OpenAI()

@task(name="joke_creation")
def create_joke():
    completion = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": "Tell me a joke about AI"}],
        temperature=0.7,
        max_tokens=100,
    )
    return completion.choices[0].message.content

@workflow(name="simple_joke_workflow")
def joke_workflow():
    joke = create_joke()
    return joke

if __name__ == "__main__":
    result = joke_workflow()
    print(result)
4

View your trace

Open the Traces page in the Respan dashboard.
Agent tracing visualization
Optional HTTP instrumentation: if you see logs like Failed to initialize Requests instrumentation, install the OpenTelemetry instrumentations:
pip install opentelemetry-instrumentation-requests opentelemetry-instrumentation-urllib3
This is optional; tracing works without them. Add only if your app uses requests or urllib3.

​
Observability

With this integration, Respan auto-captures:
  • Workflows — each @workflow-decorated function as a root trace
  • Tasks — each @task-decorated function as a span
  • LLM calls — model, input/output messages, token usage
  • Performance metrics — latency per step
  • Errors — failed tasks and error details
View traces on the Traces page.