ClickHouse Data Warehouse
Work in progress: This is the recommended path. A detailed setup guide will follow. Questions or requirements? Contact support or open a GitHub issue.
Export Langfuse data to ClickHouse to analyze AI activity alongside business and product data — for example, join usage and cost with customer accounts, or relate agent quality to product outcomes.
Recommended integration: Parquet export and an S3 ClickPipe
Write Parquet files to Amazon S3 with Langfuse's blob storage export, then load them into ClickHouse Cloud with an S3 ClickPipe.
- Export from Langfuse. In Settings → Integrations → Blob Storage, configure an S3 destination and choose Parquet. See Export to blob storage for setup and availability.
- Create an S3 ClickPipe. Point ClickHouse Cloud at the exported files and enable continuous ingestion. See the S3 ClickPipe setup guide.
- Analyze in ClickHouse. Use the export field reference when joining Langfuse data with your other datasets.
Was this page helpful?
Last updated on