Quick Start

Get observability on your LLM calls in under 2 minutes.

1. Install the SDK

   npm install weflayr
   

   pip install weflayr
   

2. Get your credentials

   Your Flayr credentials are in the Weflayr app under My Flayrs. Pass them directly to weflayr_setup, or load them from environment variables via dotenv:

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

3. Configure and instrument your client

   const OpenAI = require('openai');
   const { weflayr_setup, weflayr_instrument } = require('weflayr');
   
   weflayr_setup({
     intake_url:    process.env.WEFLAYR_INTAKE_URL,
     client_id:     process.env.WEFLAYR_CLIENT_ID,
     client_secret: process.env.WEFLAYR_CLIENT_SECRET,
     default_tags: {
       app: 'my-app',
       version: '1.0.0',
     },
     methods: [
       { call: 'chat.completions.create' },
     ],
   });
   
   const client = weflayr_instrument(new OpenAI({ apiKey: process.env.OPENAI_API_KEY }));
   

   import os
   from openai import OpenAI
   from weflayr import weflayr_setup, weflayr_instrument
   
   weflayr_setup({
       "intake_url":    os.environ["WEFLAYR_INTAKE_URL"],
       "client_id":     os.environ["WEFLAYR_CLIENT_ID"],
       "client_secret": os.environ["WEFLAYR_CLIENT_SECRET"],
       "default_tags": {
           "app": "my-app",
           "version": "1.0.0",
       },
       "methods": [
           {"call": "chat.completions.create"},
       ],
   })
   
   client = weflayr_instrument(OpenAI(api_key=os.environ["OPENAI_API_KEY"]))
   

   weflayr_setup must be called before weflayr_instrument. The methods array is the whitelist — only listed call paths are instrumented. default_tags are attached to every event automatically — see Propagate for runtime tagging.

4. Make a call and telemetry will be automatic

   const response = await client.chat.completions.create({
     model: 'gpt-4o-mini',
     messages: [{ role: 'user', content: 'Hello!' }],
     __weflayr_tags: {
         provider: 'openai',
         feature: 'onboarding',
         customer_id: '#3756'
       },
   });
   // response is the standard OpenAI response object — unchanged
   

   response = client.chat.completions.create(
       model="gpt-4o-mini",
       messages=[{"role": "user", "content": "Hello!"}],
       __weflayr_tags={
           "provider": "openai",
           "feature": "onboarding",
           "customer_id": "#3756",
       },
   )
   # response is the standard OpenAI response object — unchanged
   

   __weflayr_tags is stripped before forwarding to OpenAI and attached to the telemetry events.