Imported from jeremylongshore/tons-of-skills-marketplace (plugins/saas-packs/langfuse-pack/skills/langfuse-deploy-integration/SKILL.md). Install upstream with npx skills add jeremylongshore/tons-of-skills-marketplace --skill langfuse-deploy-integration. Copyright stays with the author (MIT).

Langfuse Deploy Integration

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);
}

Serverless note: Langfuse SDK v4+ uses OTel which handles flushing asynchronously. For v3, always call await langfuse.flushAsync() before the response returns -- serverless functions may freeze after response.

Step 2: AWS Lambda / Serverless

// handler.ts
import { LangfuseSpanProcessor } from "@langfuse/otel";
import { NodeSDK } from "@opentelemetry/sdk-node";
import { startActiveObservation, updateActiveObservation } from "@langfuse/tracing";

// Initialize OUTSIDE handler for connection reuse
const sdk = new NodeSDK({
  spanProcessors: [
    new LangfuseSpanProcessor({
      exportIntervalMillis: 1000, // Flush fast in serverless
    }),
  ],
});
sdk.start();

export const handler = async (event: any) => {
  return await startActiveObservation("lambda-handler", async () => {
    updateActiveObservation({ input: event });

    const result = await processRequest(event);

    updateActiveObservation({ output: result });

    // Force flush before Lambda freezes
    await sdk.shutdown();

    return { statusCode: 200, body: JSON.stringify(result) };
  });
};

Step 3: Self-Hosted Langfuse Server (Docker)

# docker-compose.yml
services:
  langfuse:
    image: langfuse/langfuse:latest
    ports:
      - "3000:3000"
    environment:
      - DATABASE_URL=postgresql://langfuse:${DB_PASSWORD}@postgres:5432/langfuse
      - NEXTAUTH_SECRET=${NEXTAUTH_SECRET}
      - NEXTAUTH_URL=https://langfuse.your-domain.com
      - SALT=${SALT}
      - ENCRYPTION_KEY=${ENCRYPTION_KEY}
      - AUTH_DISABLE_SIGNUP=true
      - LANGFUSE_DEFAULT_PROJECT_ROLE=VIEWER
    depends_on:
      postgres:
        condition: service_healthy

  postgres:
    image: postgres:16-alpine
    environment:
      POSTGRES_USER: langfuse
      POSTGRES_PASSWORD: ${DB_PASSWORD}
      POSTGRES_DB: langfuse
    volumes:
      - pgdata:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U langfuse"]
      interval: 5s
      timeout: 5s
      retries: 5

volumes:
  pgdata:

set -euo pipefail
# Generate secrets
export DB_PASSWORD=$(openssl rand -hex 16)
export NEXTAUTH_SECRET=$(openssl rand -hex 32)
export SALT=$(openssl rand -hex 16)
export ENCRYPTION_KEY=$(openssl rand -hex 32)

# Start
docker compose up -d

# Wait and verify
sleep 10
curl -s http://localhost:3000/api/public/health

Step 4: Google Cloud Run

set -euo pipefail
# Build and push
gcloud builds submit --tag gcr.io/$PROJECT_ID/my-llm-app

# Deploy with Langfuse env vars from Secret Manager
gcloud run deploy my-llm-app \
  --image gcr.io/$PROJECT_ID/my-llm-app \
  --set-secrets="LANGFUSE_PUBLIC_KEY=langfuse-public-key:latest" \
  --set-secrets="LANGFUSE_SECRET_KEY=langfuse-secret-key:latest" \
  --set-env-vars="LANGFUSE_BASE_URL=https://cloud.langfuse.com"

Step 5: Health Check Endpoint

// app/api/health/route.ts
import { LangfuseClient } from "@langfuse/client";

const langfuse = new LangfuseClient();

export async function GET() {
  try {
    // Quick connectivity check
    await langfuse.prompt.get("__health__").catch(() => {});
    return Response.json({ status: "healthy", tracing: "enabled" });
  } catch {
    return Response.json(
      { status: "degraded", tracing: "disabled" },
      { status: 503 }
    );
  }
}

Platform-Specific Considerations

Error Handling

Output

Produce a deployment receipt with the target environment, deployed revision, secret reference names (never values), health endpoint result, and one verified Langfuse trace. If tracing is degraded, report the application status separately from the telemetry status so an observability outage is not misrepresented as an application outage.

Examples

Deploy a staging revision with secret-manager references, call the health endpoint, and submit one synthetic request; verify its trace appears in the staging Langfuse project. For self-hosting, wait for the database health check before accepting application traffic and retain the compose revision used for the deployment.

Resources

• Self-Hosting Docker Compose
• Self-Hosting Configuration
• TypeScript SDK Setup