Your MLflow token usage and latency, summarized.
What it does
Summarizes MLflow trace activity through aggregated token usage, latency, counts, and evaluation scores.
When to use it
Use when asked to show metrics, analyze token usage or LLM costs, check usage trends, or query trace statistics.
How to use it
Give it a server URL, experiment IDs, a metric, and aggregation types; it returns the metrics as a table or JSON.
What you provide
- the MLflow server URL
- experiment IDs
- the metric
- aggregation types
Uses
Latest review
What you need · 2
Requires Python 3 to run the bundled metrics script.
Requires an MLflow tracking server to query.
Access · 1
This skill
MLflow
Write
Sends metric queries to MLflow