CtrlK
BlogDocsLog inGet started
Tessl Logo

langfuse-deploy-integration

Deploy Langfuse with your application across different platforms. Use when deploying Langfuse to Vercel, AWS, GCP, or Docker, or integrating Langfuse into your deployment pipeline. Trigger with phrases like "deploy langfuse", "langfuse Vercel", "langfuse AWS", "langfuse Docker", "langfuse production deploy".

80

Quality

77%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/saas-packs/langfuse-pack/skills/langfuse-deploy-integration/SKILL.md
SKILL.md
Quality
Evals
Security

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

PlatformKey ConcernSolution
Vercel/EdgeFunction timeoutFlush before response; use v4+
AWS LambdaCold startsInitialize SDK outside handler
Cloud RunConcurrencySingleton client, shared OTel SDK
DockerSelf-hosted networkingEnsure app can reach Langfuse host
KubernetesPod lifecycleShutdown hook on SIGTERM

Error Handling

IssueCauseSolution
Traces missing in serverlessNot flushed before freezesdk.shutdown() before response
Auth error after deployWrong env for environmentVerify secrets match deployment
Self-hosted 502DB not readyAdd healthcheck + depends_on
High latency in prodSmall batch sizeIncrease flushAt / maxExportBatchSize

Resources

  • Self-Hosting Docker Compose
  • Self-Hosting Configuration
  • TypeScript SDK Setup
Repository
jeremylongshore/claude-code-plugins-plus-skills
Last updated
Created

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.