Opik TypeScript SDK

The Opik TypeScript SDK provides a powerful and easy-to-use interface for tracing, monitoring, and debugging your JavaScript and TypeScript applications. It offers comprehensive observability for LLM applications, agent workflows, and AI-powered systems.

Integrations

Opik provides seamless integrations with popular JavaScript/TypeScript frameworks and libraries:

Frameworks:

• Agno - Trace and monitor your Agno AI agent applications
• BeeAI - Trace and monitor your BeeAI agent applications
• LangChain - Trace and monitor your LangChain applications, including chains, agents, tools, and retrievers
• Mastra - Trace and monitor your Mastra AI applications
• Vercel AI SDK - Integrate Opik with Vercel AI SDK for monitoring AI-powered applications

Model Providers:

• Cloudflare Workers AI - Trace and monitor your Cloudflare Workers AI applications
• Gemini - Trace and monitor your applications using the Google Generative AI Node.js SDK
• OpenAI - Trace and monitor your applications using the official OpenAI Node.js SDK

For a complete list of TypeScript/JavaScript integrations and other language integrations, see the Integrations Overview.

Installation

Option 1: Using the Opik TS (Recommended)

The fastest way to get started is using the Opik TS, an interactive CLI tool that sets up Opik automatically in your project:

$
npx opik-ts configure

The CLI will:

• Detect your project setup
• Install Opik SDK and integration packages
• Configure environment variables
• Set up Opik client for your LLM integrations

Option 2: Manual Installation

You can also install the opik package manually using your favorite package manager:

$
npm install opik

Opik Configuration

You can configure the Opik client using environment variables.

$
export OPIK_API_KEY="your-api-key"
$
$
# If running on Opik Cloud
$
export OPIK_URL_OVERRIDE="https://www.comet.com/opik/api"
$
$
# If running locally
$
export OPIK_URL_OVERRIDE="http://localhost:5173/api"
$
$
export OPIK_PROJECT_NAME="your-project-name"
$
export OPIK_WORKSPACE="your-workspace-name"

Or you can pass the configuration to the Opik client constructor.

1
import { Opik } from "opik";
2
3
const client = new Opik({
4
  apiKey: "<your-api-key>",
5
  apiUrl: "https://www.comet.com/opik/api",
6
  projectName: "<your-project-name>",
7
  workspaceName: "<your-workspace-name>",
8
});

Usage

1
import { Opik } from "opik";
2
3
// Create a new Opik client with your configuration
4
const client = new Opik();
5
6
// Log 10 traces
7
for (let i = 0; i < 10; i++) {
8
  const someTrace = client.trace({
9
    name: `Trace ${i}`,
10
    input: {
11
      prompt: `Hello, world! ${i}`,
12
    },
13
    output: {
14
      response: `Hello, world! ${i}`,
15
    },
16
  });
17
18
  // For each trace, log 10 spans
19
  for (let j = 0; j < 10; j++) {
20
    const someSpan = someTrace.span({
21
      name: `Span ${i}-${j}`,
22
      type: "llm",
23
      input: {
24
        prompt: `Hello, world! ${i}:${j}`,
25
      },
26
      output: {
27
        response: `Hello, world! ${i}:${j}`,
28
      },
29
    });
30
31
    // Some LLM work
32
    await new Promise((resolve) => setTimeout(resolve, 100));
33
34
    // Mark the span as ended
35
    someSpan.end();
36
  }
37
38
  // Mark the trace as ended
39
  someTrace.end();
40
}
41
42
// Flush the client to send all traces and spans
43
await client.flush();