Langfuse Install & Auth

Overview

Install the Langfuse SDK and configure authentication for LLM observability. Covers both the legacy langfuse package (v3) and the modern modular SDK (v4+/v5) built on OpenTelemetry.

Prerequisites

• Node.js 18+ or Python 3.9+
• Package manager (npm, pnpm, or pip)
• Langfuse account (cloud at https://cloud.langfuse.com or self-hosted)
• Public Key (pk-lf-...) and Secret Key (sk-lf-...) from project settings

Instructions

Step 1: Install SDK

TypeScript/JavaScript (v4+ modular SDK -- recommended):

set -euo pipefail
# Core client for prompt management, datasets, scores
npm install @langfuse/client

# Tracing (observe, startActiveObservation)
npm install @langfuse/tracing @langfuse/otel @opentelemetry/sdk-node

# OpenAI integration (drop-in wrapper)
npm install @langfuse/openai

# LangChain integration
npm install @langfuse/langchain

TypeScript/JavaScript (v3 legacy -- single package):

npm install langfuse

Python:

pip install langfuse

Step 2: Get API Keys

1. Open Langfuse dashboard (https://cloud.langfuse.com or your self-hosted URL)
2. Go to Settings > API Keys
3. Click Create new API key pair
4. Copy both keys:

- Public Key: pk-lf-... (identifies your project) - Secret Key: sk-lf-... (grants write access -- keep secret)

1. Note the host URL (cloud default: https://cloud.langfuse.com)

Step 3: Configure Environment Variables

# Set environment variables
export LANGFUSE_PUBLIC_KEY="pk-lf-..."
export LANGFUSE_SECRET_KEY="sk-lf-..."
export LANGFUSE_BASE_URL="https://cloud.langfuse.com"

# Or create .env file
cat >> .env << 'EOF'
LANGFUSE_PUBLIC_KEY=pk-lf-your-public-key
LANGFUSE_SECRET_KEY=sk-lf-your-secret-key
LANGFUSE_BASE_URL=https://cloud.langfuse.com
EOF

Note: v4+ uses LANGFUSEBASEURL. Legacy v3 uses LANGFUSEHOST or LANGFUSEBASEURL.

Step 4: Initialize and Verify (v4+ Modular SDK)

// src/lib/langfuse.ts
import { LangfuseClient } from "@langfuse/client";
import { startActiveObservation } from "@langfuse/tracing";
import { LangfuseSpanProcessor } from "@langfuse/otel";
import { NodeSDK } from "@opentelemetry/sdk-node";

// 1. Register the OpenTelemetry span processor (once at app startup)
const sdk = new NodeSDK({
  spanProcessors: [new LangfuseSpanProcessor()],
});
sdk.start();

// 2. Create the Langfuse client for prompt/dataset/score operations
export const langfuse = new LangfuseClient({
  publicKey: process.env.LANGFUSE_PUBLIC_KEY,
  secretKey: process.env.LANGFUSE_SECRET_KEY,
  baseUrl: process.env.LANGFUSE_BASE_URL,
});

// 3. Verify connection
async function verify() {
  await startActiveObservation("connection-test", async (span) => {
    span.update({ input: { test: true } });
    span.update({ output: { status: "connected" } });
  });
  console.log("Langfuse connection verified. Check dashboard for trace.");
}

verify();

Step 5: Initialize and Verify (v3 Legacy SDK)

import { Langfuse } from "langfuse";

const langfuse = new Langfuse({
  publicKey: process.env.LANGFUSE_PUBLIC_KEY,
  secretKey: process.env.LANGFUSE_SECRET_KEY,
  baseUrl: process.env.LANGFUSE_HOST,
});

// Verify with a test trace
const trace = langfuse.trace({
  name: "connection-test",
  metadata: { test: true },
});

await langfuse.flushAsync();
console.log("Connected. Trace URL:", trace.getTraceUrl());

// Clean shutdown
process.on("beforeExit", async () => {
  await langfuse.shutdownAsync();
});

Step 6: Python Verification

from langfuse import Langfuse
import os

langfuse = Langfuse(
    public_key=os.environ["LANGFUSE_PUBLIC_KEY"],
    secret_key=os.environ["LANGFUSE_SECRET_KEY"],
    host=os.environ.get("LANGFUSE_HOST", "https://cloud.langfuse.com"),
)

# Test trace
trace = langfuse.trace(name="connection-test", metadata={"test": True})
langfuse.flush()
print(f"Connected. Trace: {trace.get_trace_url()}")

SDK Version Comparison

Error Handling

Output

Produce a connection-verification receipt with SDK version, configured host, project identifier, and a trace URL or identifier. Record only whether each credential is set; never print key values, headers, or compiled prompts.

Examples

Configure the v4 SDK with environment-provided keys, submit a single synthetic trace, and confirm it appears in the intended project. For a self-hosted host change, verify the health endpoint and test trace before removing the previous host configuration.

Resources

• TypeScript SDK Setup
• Python SDK Setup
• v3 to v4 Migration Guide
• Self-Hosting Configuration

Next Steps

After auth is working, proceed to langfuse-hello-world for your first traced LLM call.