Quick Start

Get ObservIQ monitoring your AI app in under 5 minutes.

You need Python 3.9+ and a Groq/OpenAI API key to follow this guide.

Create Your Account

Go to observ-iq.netlify.app/signup (opens in a new tab) and register a new team.

You'll receive an API key that looks like: oiq_a1b2c3d4e5f6...

Save this key — it's only shown once.

Install the SDK

pip install observiq-sdk

Wrap Your AI Calls

import os
from groq import Groq
from observiq_sdk import ObservIQ
 
# Initialize clients
groq_client = Groq(api_key=os.environ["GROQ_API_KEY"])
client = ObservIQ(api_key="oiq_your_key_here")
 
# Wrap your AI call with the context manager
with client.trace(model="llama-3.3-70b-versatile", feature_name="customer_support"):
    response = groq_client.chat.completions.create(
        model="llama-3.3-70b-versatile",
        messages=[{"role": "user", "content": "Hello!"}]
    )
 
print(response.choices[0].message.content)
# Every call is now automatically tracked ✅

View Your Dashboard

Open your ObservIQ dashboard (opens in a new tab) and log in with your API key. Within seconds you'll see:

✅ The trace appear in the Recent Traces table
✅ Stats cards update with latency and cost
✅ Analytics charts show model and feature breakdown

What Gets Tracked Automatically

Field	Description
`model`	Which AI model was called
`input`	The user's message (first 1000 chars)
`output`	The AI's response (first 1000 chars)
`latency_ms`	Time from request to response
`prompt_tokens`	Input token count
`completion_tokens`	Output token count
`cost_usd`	Estimated cost based on model pricing
`status`	`success` or `error`

⚠️

Sensitive data in prompts is truncated to 1000 characters. Consider masking PII before sending to ObservIQ.

Next Steps

ObservIQ — AI Application Monitoring Installation