Quick Start

Get observability on your LLM calls in under 2 minutes.

1. Install the SDK

   pip install weflayr
   

2. Set environment variables

   Your Flare credentials are in the Weflayr dashboard under Settings → Flares.

   export WEFLAYR_INTAKE_URL="https://api.weflayr.com"
   export WEFLAYR_CLIENT_ID="your-client-id"
   export WEFLAYR_CLIENT_SECRET="your-client-secret"
   

   You can also pass them directly to the client constructor (intake_url, client_id, bearer_token).

3. Replace your import — one line change

   before

   from openai import OpenAI
   client = OpenAI(api_key="sk-...")
   

   after

   from weflayr.sdk.openai.client import OpenAI  # ← only this line changes
   client = OpenAI(api_key="sk-...")
   

   The Weflayr client is a subclass of the official SDK client. All existing method signatures, return types, and exceptions are identical.

4. Make a call — telemetry is automatic

   response = client.chat.completions.create(
       model="gpt-4o-mini",
       messages=[{"role": "user", "content": "Hello!"}],
       tags={"feature": "onboarding", "env": "production"},  # optional
   )
   # response is the standard ChatCompletion object — unchanged
   

   The tags argument is stripped before forwarding to OpenAI. See the Tags guide for more.