Quick Setup - 5 Minute Start

Welcome to Noveum.ai! This guide will get you tracing your AI applications in just 5 minutes. Follow these simple steps to start monitoring your LLM calls, RAG pipelines, and agent workflows.

✅ Prerequisites

Before you begin, make sure you have:

• Python 3.9+ installed on your system
• Noveum.ai account (we'll help you create one)
• Basic Python knowledge (you'll be adding just a few lines of code)
• An AI application to trace (or we'll provide a simple example)

Step 1: Get Your API Key

Create Your Account

1. Visit noveum.ai
2. Sign up with your email or GitHub account
3. Verify your email address

Generate API Key

1. Navigate to the API Keys section in your dashboard
2. Click "Create New API Key"
3. Name your key (e.g., "My AI App")
4. Copy the generated API key (you'll need this in Step 3)

Step 2: Install the SDK

Open your terminal and install the Noveum Trace SDK:

pip install noveum-trace

Expected output:

Collecting noveum-trace
  Downloading noveum_trace-1.0.0-py3-none-any.whl (45 kB)
Installing collected packages: noveum-trace
Successfully installed noveum-trace-1.0.0

Step 3: Initialize Noveum

Create a new Python file or add to your existing application:

import os
import noveum_trace
from noveum_trace import trace_llm_call
import openai

# Initialize Noveum (add this once at the start of your app)
noveum_trace.init(
    api_key=os.getenv("NOVEUM_API_KEY"),  
    project="my-first-trace",
    environment="development"
)

When you initialize with noveum_trace.init(), the following happens automatically:

• Project Creation: The project gets created in the UI automatically based on the string you provide
• Environment Organization: Environments are used to organize traces (e.g., dev, prod, beta, staging)

Step 4: Add Your First Trace

Let's trace a simple LLM call using context managers. Add this code to your file:

def simple_llm_example():
    """A simple LLM call with automatic tracing using context managers"""
    
    # This will automatically trace the LLM call
    with trace_llm_call(model="gpt-4"):
        response = openai.chat.completions.create(
            model="gpt-4",
            messages=[{"role": "user", "content": "Hello! What is 2+2?"}],
            temperature=0.7
        )
        
        return response.choices[0].message.content
 
# Run the example
if __name__ == "__main__":
    result = simple_llm_example()
    print(f"AI Response: {result}")
    noveum_trace.flush()

Step 5: View Your Results

1. Run your script:

   python your_script.py

2. Visit your dashboard: Go to noveum.ai/app

3. Navigate to Explorer: Click on "Explorer" in the sidebar

4. Explore your traces - Environment Name -> Project name -> Traces

Traces

🎯 What You've Accomplished

In just 5 minutes, you've:

• ✅ Set up Noveum.ai account and API key
• ✅ Installed the Python SDK
• ✅ Initialized tracing in your application
• ✅ Traced your first LLM call
• ✅ Viewed results in the dashboard

🚀 Next Steps

Now that you have basic tracing working, here's what you can explore:

🔧 Troubleshooting

Common Issues

"API key not found" error:

# Make sure your environment variable is set
echo $NOVEUM_API_KEY
# If empty, set it:
export NOVEUM_API_KEY="your-key-here"

"No traces appearing in dashboard":

• Wait 30-60 seconds for traces to appear
• Check that your API key is correct
• Ensure you're looking at the right project

"OpenAI API error":

• Make sure you have a valid OpenAI API key
• Check your OpenAI account has credits
• Verify the model name is correct

Need Help?

• Documentation: Browse our comprehensive guides
• Community: Join our Discord for support
• Support: Contact us at support@noveum.ai

🎉 Success Checklist

Before moving on, make sure you can:

• See your trace in the Noveum dashboard
• View token usage and cost information
• Understand the trace timeline
• Add custom attributes to your traces
• Handle errors gracefully in your traces

Congratulations! You're now ready to transform your AI application observability with Noveum.ai. Start tracing, start optimizing, start building better AI applications.

What's next: Start Evaluating

Now that your traces are flowing in, set up the evaluation pipeline to score every LLM decision your agent makes and get AI-generated recommendations for improving it.

1. Create an ETL Job: Noveum reads your traces and uses AI to generate code that converts each LLM call into a dataset item
2. Create an Eval Job: attach NovaEval scorers to your dataset and score every item with 80+ built-in quality metrics
3. Get NovaPilot recommendations: AI-generated, prioritized fixes based on your evaluation results

Start the Evaluation Pipeline →