Langfuse analytics derives actionable insights from production data.
→ Not using Langfuse yet? Explore the dashboard in our interactive demo.
- Quality is measured through user feedback, model-based scoring, human-in-the-loop scored samples or custom scores via SDKs/API (see scores). Quality is assessed over time as well as across prompt versions, LLMs and users.
- Cost and Latency are accurately measured and broken down by user, session, geography, feature, model and prompt version.
- Volume based on the ingested traces and tokens used.
Analytics is incrementally adoptable based on the data you send to Langfuse. The following dimensions are available:
- Trace name: differentiate between different use cases, features, etc. by adding a
namefield to your traces.
- User: track usage and cost by user, see user-level analytics for more details.
- Release and version numbers: track how changes to the LLM application affected your metrics.