{ "editable": true, "graphTooltip": 0, "id": 3607718328258560, "panels": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "decimals": 2, "unit": "reqps" }, "overrides": [] }, "gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 }, "id": 1, "options": { "colorMode": "value", "graphMode": "area", "reduceOptions": { "calcs": [ "lastNotNull" ] } }, "targets": [ { "expr": "sum(rate(te_request_count{job=\"tei\"}[5m]))", "refId": "A" } ], "title": "Request rate (req/s)", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "prometheus" }, "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "decimals": 2, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "yellow", "value": 1 }, { "color": "red", "value": 5 } ] }, "unit": "percent" }, "overrides": [] }, "gridPos": { "h": 4, "w": 6, "x": 6, "y": 0 }, "id": 2, "options": { "colorMode": "background", "graphMode": "area", "reduceOptions": { "calcs": [ "lastNotNull" ] } }, "targets": [ { "expr": "100 * (1 - (sum(rate(te_request_success{job=\"tei\"}[5m])) / clamp_min(sum(rate(te_request_count{job=\"tei\"}[5m])), 1e-9)))", "refId": "A" } ], "title": "Error rate (%)", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "prometheus" }, "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "decimals": 0, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "yellow", "value": 10 }, { "color": "red", "value": 50 } ] }, "unit": "short" }, "overrides": [] }, "gridPos": { "h": 4, "w": 6, "x": 12, "y": 0 }, "id": 3, "options": { "colorMode": "value", "graphMode": "area", "reduceOptions": { "calcs": [ "lastNotNull" ] } }, "targets": [ { "expr": "sum(te_queue_size{job=\"tei\"})", "refId": "A" } ], "title": "Queue size", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "prometheus" }, "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "decimals": 3, "unit": "s" }, "overrides": [] }, "gridPos": { "h": 4, "w": 6, "x": 18, "y": 0 }, "id": 4, "options": { "colorMode": "value", "graphMode": "area", "reduceOptions": { "calcs": [ "lastNotNull" ] } }, "targets": [ { "expr": "histogram_quantile(0.95, sum by (le) (rate(te_request_duration_bucket{job=\"tei\"}[5m])))", "refId": "A" } ], "title": "p95 request latency", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "prometheus" }, "fieldConfig": { "defaults": { "unit": "s" }, "overrides": [] }, "gridPos": { "h": 9, "w": 12, "x": 0, "y": 4 }, "id": 5, "options": { "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "expr": "histogram_quantile(0.50, sum by (le) (rate(te_request_duration_bucket{job=\"tei\"}[5m])))", "legendFormat": "p50", "refId": "A" }, { "expr": "histogram_quantile(0.95, sum by (le) (rate(te_request_duration_bucket{job=\"tei\"}[5m])))", "legendFormat": "p95", "refId": "B" }, { "expr": "histogram_quantile(0.99, sum by (le) (rate(te_request_duration_bucket{job=\"tei\"}[5m])))", "legendFormat": "p99", "refId": "C" } ], "title": "Request latency (p50 / p95 / p99)", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "prometheus" }, "fieldConfig": { "defaults": { "unit": "s" }, "overrides": [] }, "gridPos": { "h": 9, "w": 12, "x": 12, "y": 4 }, "id": 6, "options": { "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "expr": "histogram_quantile(0.95, sum by (le) (rate(te_request_inference_duration_bucket{job=\"tei\"}[5m])))", "legendFormat": "inference", "refId": "A" }, { "expr": "histogram_quantile(0.95, sum by (le) (rate(te_request_tokenization_duration_bucket{job=\"tei\"}[5m])))", "legendFormat": "tokenization", "refId": "B" }, { "expr": "histogram_quantile(0.95, sum by (le) (rate(te_request_queue_duration_bucket{job=\"tei\"}[5m])))", "legendFormat": "queue", "refId": "C" } ], "title": "Inference vs tokenization vs queue duration (p95)", "type": "timeseries" } ], "refresh": "30s", "schemaVersion": 39, "tags": [ "tei", "embeddings", "homelab" ], "time": { "from": "now-6h", "to": "now" }, "timezone": "browser", "title": "tei", "uid": "tei-homelab", "version": 1 }