eb2702bcba
* misc: performance improvements * misc: performance improvements * misc: performance improvements
541 lines
13 KiB
JSON
541 lines
13 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null }
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 },
|
|
"id": 1,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"pluginVersion": "10.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(hindsight_llm_calls_total)",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Total LLM Calls",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null }
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 6, "x": 6, "y": 0 },
|
|
"id": 2,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"pluginVersion": "10.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(hindsight_llm_tokens_input_tokens_total) + sum(hindsight_llm_tokens_output_tokens_total)",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Total Tokens Used",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"fixedColor": "blue",
|
|
"mode": "fixed"
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null }
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 6, "x": 12, "y": 0 },
|
|
"id": 3,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"pluginVersion": "10.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(hindsight_llm_tokens_input_tokens_total)",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Input Tokens",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"fixedColor": "green",
|
|
"mode": "fixed"
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null }
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 6, "x": 18, "y": 0 },
|
|
"id": 4,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"pluginVersion": "10.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(hindsight_llm_tokens_output_tokens_total)",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Output Tokens",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 20,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null }
|
|
]
|
|
},
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 4 },
|
|
"id": 5,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["mean", "max"],
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "10.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (scope) (rate(hindsight_llm_calls_total[1m]))",
|
|
"legendFormat": "{{scope}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "LLM Calls per Second by Scope",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 20,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null }
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": { "id": "byName", "options": "Input" },
|
|
"properties": [{ "id": "color", "value": { "fixedColor": "blue", "mode": "fixed" } }]
|
|
},
|
|
{
|
|
"matcher": { "id": "byName", "options": "Output" },
|
|
"properties": [{ "id": "color", "value": { "fixedColor": "green", "mode": "fixed" } }]
|
|
}
|
|
]
|
|
},
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 12 },
|
|
"id": 6,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["mean", "max"],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "10.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(hindsight_llm_tokens_input_tokens_total[1m]))",
|
|
"legendFormat": "Input",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "sum(rate(hindsight_llm_tokens_output_tokens_total[1m]))",
|
|
"legendFormat": "Output",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"title": "Token Usage Rate (tokens/sec)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null }
|
|
]
|
|
},
|
|
"unit": "s"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 12 },
|
|
"id": 7,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["mean", "max"],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "10.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.95, sum by (scope, le) (rate(hindsight_llm_duration_seconds_bucket[5m])))",
|
|
"legendFormat": "{{scope}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "LLM Call Latency p95 by Scope",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 20,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "normal"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null }
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 20 },
|
|
"id": 8,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["mean", "max"],
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "10.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (scope) (rate(hindsight_llm_tokens_input_tokens_total[1m]))",
|
|
"legendFormat": "{{scope}} (input)",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "sum by (scope) (rate(hindsight_llm_tokens_output_tokens_total[1m]))",
|
|
"legendFormat": "{{scope}} (output)",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"title": "Token Usage by Scope (tokens/sec)",
|
|
"type": "timeseries"
|
|
}
|
|
],
|
|
"refresh": "5s",
|
|
"schemaVersion": 38,
|
|
"tags": ["hindsight", "llm"],
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"time": {
|
|
"from": "now-30m",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "browser",
|
|
"title": "Hindsight LLM Metrics",
|
|
"uid": "hindsight-llm",
|
|
"version": 1,
|
|
"weekStart": ""
|
|
}
|