📄️ Dashboard
The Dashboard provides a high-level overview of the performance of your LLM application, focusing on latency metrics within a selected time range. You can adjust the from timestamp and to timestamp fields at the top to filter the data displayed.
📄️ Traces
The Traces section provides a detailed log of individual requests or
📄️ Sessions
The Sessions section allows you to group and analyze sequences of interactions, typically corresponding to a single user's engagement with your application over a period.