Deploy Langfuse on Northflank

Langfuse is an open-source observability and analytics platform designed specifically for applications built with large language models (LLMs). It provides developers with detailed tracing, evaluation, and monitoring tools to gain visibility into the performance and behavior of LLM-powered features. By capturing structured metadata—such as prompt inputs, model outputs, latency, token usage, and user feedback—Langfuse helps teams analyze how their AI systems are being used and how they can be improved. It integrates seamlessly with various LLM providers and frameworks, making it easier to debug, optimize, and iterate on AI features in production.

• Langfuse web service
• Langfuse worker service
• ClickHouse service with persistent volume
• PostgreSQL, MinIO, and Redis managed addons for data storage and message brokering

1. Create an account on Northflank
2. Click deploy Langfuse now
3. Click deploy stack to save and run the Langfuse template
4. Select the web service when the template run has finished
5. Open the code.run domain in the service header to access Langfuse and create your account
6. Create a new project in Langfuse, and generate a new API key to integrate your AI project

Learn more about setting up Langfuse with their quickstart guide.