Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.uselumina.io/docs/llms.txt

Use this file to discover all available pages before exploring further.

Step-by-step guide to sending your first trace.

​
Prerequisites

  • Lumina running (Docker or Kubernetes)
  • Node.js 18+ or Bun

​
Step 1: Install SDK

npm install @uselumina/sdk @anthropic-ai/sdk

​
Step 2: Create Test File

Create first-trace.ts: 
import { initLumina } from '@uselumina/sdk';
import Anthropic from '@anthropic-ai/sdk';

const anthropic = new Anthropic({
  apiKey: process.env.ANTHROPIC_API_KEY,
});

const lumina = initLumina({
  endpoint: 'http://localhost:9411/v1/traces',
  service_name: 'quickstart',
});

async function main() {
  console.log('Sending first trace...');

  await lumina.traceLLM(
    () =>
      anthropic.messages.create({
        model: 'claude-sonnet-4-5',
        max_tokens: 100,
        messages: [{ role: 'user', content: 'Hello!' }],
      }),
    {
      name: 'hello-world',
      system: 'anthropic',
      prompt: 'Hello!',
    }
  );

  console.log('✓ Trace sent! View at http://localhost:3000/traces');
}

main();

​
Step 3: Run

npx tsx first-trace.ts

​
Step 4: View in Dashboard

  1. Open http://localhost:3000/traces
  2. Find your trace with service quickstart
  3. Click to view details
You should see:
  • Automatic cost calculation
  • Token counts
  • Latency measurement
  • Full prompt and response

​
Next Steps

SDK Documentation

Learn SDK usage patterns

Multi-Span Tracing

Track complex workflows