# Langfuse and ClickHouse: A new data stack for modern LLM applications

DevFeed: [Langfuse and ClickHouse: A new data stack for modern LLM applications](<https://devfeed.tech/articles/langfuse-and-clickhouse-a-new-data-stack-for-modern-llm-applications-5374.md>)

Original publisher: [Read original article](<https://clickhouse.com/blog/langfuse-and-clickhouse-a-new-data-stack-for-modern-llm-applications>)

Author: ClickHouse

Published: 2025-06-23T14:42:08Z

Content type: article

Language: en

Sources: [ClickHouse Blog](<https://devfeed.tech/sources/clickhouse-blog.md>)

Topics: [clickhouse](<https://devfeed.tech/topics/clickhouse.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Scalability](<https://devfeed.tech/topics/scalability.md>), [Self-hosted](<https://devfeed.tech/topics/self-hosted.md>), [data-architecture](<https://devfeed.tech/topics/data-architecture.md>), [Docker Compose](<https://devfeed.tech/topics/docker-compose.md>)

Tags: [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [data-architecture](<https://devfeed.tech/tags/data-architecture.md>), [docker](<https://devfeed.tech/tags/docker.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [llm](<https://devfeed.tech/tags/llm.md>), [observability](<https://devfeed.tech/tags/observability.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [self-hosted](<https://devfeed.tech/tags/self-hosted.md>)

## AI overview

Langfuse rebuilt its LLM observability platform around ClickHouse after its Postgres-based architecture struggled with billions of rows, complex queries, and rapidly growing ingestion volumes. The article describes the migration, its scalability benefits, and the rollout to more than 1,000 self-hosted users without downtime.

## Source excerpt

Langfuse rebuilt its observability platform for LLM applications with ClickHouse at the core, boosting performance, unlocking scalability, and rolling the change out to 1,000+ self-hosted users with zero downtime.