Get started with ABV tracing in your JavaScript/TypeScript application in under 5 minutes
If you’re creating a new ABV account, the onboarding flow will guide you through these steps automatically. This guide is for manual setup or reference.
Get your API key
Create an ABV account and generate API credentials:
Best for: LLM applications that need automatic tracing with zero manual instrumentationThe ABV Gateway is the fastest way to get complete observability for LLM calls. It automatically captures all metrics without any manual tracing code.
New users get $1 in free credits to test the gateway.
Install the ABV client:
Copy
npm install @abvdev/client dotenv
Create a traced LLM application:
server.ts
Copy
import { ABVClient } from '@abvdev/client';import dotenv from 'dotenv';// Load environment variablesdotenv.config();// Initialize the ABV clientconst abv = new ABVClient(); // Uses ABV_API_KEY from environmentasync function main() { // Make a gateway request - automatically creates a complete trace const response = await abv.gateway.chat.completions.create({ provider: 'openai', model: 'gpt-4o-mini', messages: [ { role: 'user', content: 'What is the capital of France?' } ] }); // Access the response const output = response.choices[0].message.content; console.log(`Response: ${output}`);}main();
What gets captured automatically:
Full conversation context (user query and LLM response)
Model and provider information
Token usage (input/output counts)
Cost tracking (deducted from gateway credits)
Latency metrics (total duration and API timing)
Complete observability with zero manual instrumentation
Switch providers easily:
Copy
// Try Anthropic's Claudeconst response = await abv.gateway.chat.completions.create({ provider: 'anthropic', model: 'claude-sonnet-4-5', messages: [{ role: 'user', content: 'What is the capital of France?' }]});// Or try Google's Geminiconst response = await abv.gateway.chat.completions.create({ provider: 'gemini', model: 'gemini-2.0-flash-exp', messages: [{ role: 'user', content: 'What is the capital of France?' }]});
The gateway requires no OpenTelemetry setup. Just install @abvdev/client and start making requests.
Best for: Custom workflows where you need fine-grained control over tracingManual instrumentation gives you full control over what gets traced and when. This approach uses OpenTelemetry for flexible, detailed observability.Initialize OpenTelemetry:Create an instrumentation.ts file:
instrumentation.ts
Copy
import dotenv from "dotenv";dotenv.config();import { NodeSDK } from "@opentelemetry/sdk-node";import { ABVSpanProcessor } from "@abvdev/otel";const sdk = new NodeSDK({ spanProcessors: [ new ABVSpanProcessor({ apiKey: process.env.ABV_API_KEY, baseUrl: process.env.ABV_BASE_URL, exportMode: "immediate", // Send traces immediately for development flushAt: 1, flushInterval: 1, additionalHeaders: { "Content-Type": "application/json", "Accept": "application/json" } }) ],});sdk.start();
The exportMode: "immediate" setting ensures traces appear in the ABV dashboard instantly during development. For production, remove this parameter to use batched exports for better performance.
Create your first trace:
server.ts
Copy
import "./instrumentation"; // IMPORTANT: Must be the first importimport { startActiveObservation, startObservation } from "@abvdev/tracing";async function main() { await startActiveObservation("user-request", async (span) => { span.update({ input: { query: "What is the capital of France?" }, }); // Create a nested LLM generation observation const generation = startObservation( "llm-call", { model: "gpt-4o", input: [{ role: "user", content: "What is the capital of France?" }], }, { asType: "generation" }, ); // Simulate LLM response generation .update({ output: { content: "The capital of France is Paris." }, }) .end(); span.update({ output: "Successfully answered." }); });}main();
This creates a parent user-request observation with a nested llm-call generation. The nested structure helps you understand multi-step workflows in the ABV dashboard.
