Overview

Overview

Deploy Langfuse LLM observability alongside your application. Covers integrating the SDK for serverless (Vercel/Lambda), Docker, Cloud Run, and self-hosting the Langfuse server itself.

Prerequisites

• Langfuse API keys (cloud or self-hosted)
• Application using Langfuse SDK
• Target platform CLI installed

Instructions

Step 1: Vercel / Next.js Deployment

set -euo pipefail
# Add secrets to Vercel
vercel env add LANGFUSE_PUBLIC_KEY production
vercel env add LANGFUSE_SECRET_KEY production
vercel env add LANGFUSE_BASE_URL production

// app/api/chat/route.ts (Next.js App Router)
import { NextRequest, NextResponse } from "next/server";
import { LangfuseClient } from "@langfuse/client";
import { startActiveObservation, updateActiveObservation } from "@langfuse/tracing";
import OpenAI from "openai";

const langfuse = new LangfuseClient();
const openai = new OpenAI();

export async function POST(req: NextRequest) {
  const { messages } = await req.json();

  const response = await startActiveObservation(
    { name: "chat-api", asType: "generation" },
    async () => {
      updateActiveObservation({
        model: "gpt-4o",
        input: messages,
        metadata: { endpoint: "/api/chat" },
      });

      const result = await openai.chat.completions.create({
        model: "gpt-4o",
        messages,
      });

      updateActiveObservation({
        output: result.choices[0].message,
        usage: {
          promptTokens: result.usage?.prompt_tokens,
          completionTokens: result.usage?.completion_tokens,
        },
      });

      return result.choices[0].message;
    }
  );

  return NextResponse.json(response);
}