Dashboard

Upon Siging UP on SimpliML, you gain immediate access to detailed, real-time analytics covering cost, latency, and accuracy across all your Language Model (LLM) requests. The analytics dashboard provides an interactive interface to comprehend your LLM application. Here, you can explore various graphs and metrics related to requests to different LLMs, costs, latencies, tokens, user activity, feedback, cache hits, errors, and more.

Charts

The dashboard offers insights into your users, errors, cache, feedback, and summarizes information by metadata.

Cache

Upon enabling cache while calling Inference gateway, you can track data on latency improvements and cost savings resulting from cache utilization.

Feedback

SimpliML enables you to gather feedback on LLM requests through the logs dashboard or via API. Analytics on this feedback are available on the dashboard.

Errors

SimpliML automatically captures errors for API and accuracy issues. The charts provide a quick overview of error rates, aiding in debugging when necessary.