Skip to content

Commit

Permalink
[DOCS] Improve average latency KPI description [1.7.x] (mlrun#6471)
Browse files Browse the repository at this point in the history
  • Loading branch information
Eyal-Danieli authored Oct 6, 2024
1 parent e9417c8 commit 6b53a61
Show file tree
Hide file tree
Showing 4 changed files with 4 additions and 4 deletions.
Binary file modified docs/_static/images/IG_model_endpoints_features_analysis.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified docs/_static/images/IG_model_endpoints_overview.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified docs/_static/images/model_endpoints_main.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
8 changes: 4 additions & 4 deletions docs/model-monitoring/monitoring-models.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -43,12 +43,12 @@
"* **Version** — user configured version taken from model deployment\n",
"* **Class** — the implementation class that is used by the endpoint\n",
"* **Labels** — user configurable tags that are searchable\n",
"* **Uptime** — first request for production data\n",
"* **First Request** — first request for production data\n",
"* **Last Prediction** — most recent request for production data\n",
"* **Average Latency** — Average latency time of serving a single event in the last hour\n",
"* **Error Count** — includes prediction process errors such as operational issues (For example, a function in a failed state), as well as data processing errors\n",
"* **Average Latency** — Average latency time of serving a single event in the last hour metric. The UI value is calculated by averaging the metric value from the last 10 minutes. If no events arrived in the last 10 minutes, `-` will be displayed\n",
"* **Error Count** — includes prediction process errors such as operational issues (for example, a function in a failed state), as well as data processing errors\n",
"(For example, invalid timestamps, request ids, type mismatches etc.)\n",
"* **Drift** — indication of drift status (no drift (green), possible drift (yellow), drift detected (red))\n",
"* **Drift Status** — indication of drift status (no drift (green), possible drift (yellow), drift detected (red))\n",
"\n",
"### Model endpoint overview\n",
"The Model Endpoints overview pane displays general information about the selected model.\n",
Expand Down

0 comments on commit 6b53a61

Please sign in to comment.