mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-14 19:01:08 +02:00
feat(telegram-bot): add local STT support and Prometheus metrics
- Fix telegram_user_id column type (integer -> bigint) for large user IDs - Add local STT support via mana-stt service (Whisper MLX + Voxtral) - Add STT provider config (local/openai) with fallback support - Add Grafana dashboard for mana-stt service metrics - Add ollama-metrics-proxy for LLM metrics collection - Add Grafana dashboard for Ollama LLM metrics Services added/updated: - telegram-project-doc-bot: local STT integration - mana-stt: Grafana dashboard - ollama-metrics-proxy: new service for Ollama metrics Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Till-JS
parent
876fd43a1c
commit
6402f287e8
6 changed files with 1433 additions and 12 deletions
740
services/mana-stt/grafana-dashboard.json
Normal file
740
services/mana-stt/grafana-dashboard.json
Normal file
|
|
@ -0,0 +1,740 @@
|
|||
{
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"description": "ManaCore Speech-to-Text Service Monitoring",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 1,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
|
||||
"id": 100,
|
||||
"panels": [],
|
||||
"title": "Overview",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [
|
||||
{
|
||||
"options": {
|
||||
"0": { "color": "red", "index": 1, "text": "DOWN" },
|
||||
"1": { "color": "green", "index": 0, "text": "UP" }
|
||||
},
|
||||
"type": "value"
|
||||
}
|
||||
],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "red", "value": null },
|
||||
{ "color": "green", "value": 1 }
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 0, "y": 1 },
|
||||
"id": 1,
|
||||
"options": {
|
||||
"colorMode": "background",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"pluginVersion": "10.4.1",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "up{job=\"mana-stt\"}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Service Status",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [
|
||||
{
|
||||
"options": {
|
||||
"0": { "color": "yellow", "index": 0, "text": "Not Loaded" },
|
||||
"1": { "color": "green", "index": 1, "text": "Loaded" }
|
||||
},
|
||||
"type": "value"
|
||||
}
|
||||
],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "yellow", "value": null },
|
||||
{ "color": "green", "value": 1 }
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 3, "y": 1 },
|
||||
"id": 2,
|
||||
"options": {
|
||||
"colorMode": "background",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "mana_stt_model_loaded{model=\"whisper\"}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Whisper Model",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [
|
||||
{
|
||||
"options": {
|
||||
"0": { "color": "yellow", "index": 0, "text": "Not Loaded" },
|
||||
"1": { "color": "green", "index": 1, "text": "Loaded" }
|
||||
},
|
||||
"type": "value"
|
||||
}
|
||||
],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "yellow", "value": null },
|
||||
{ "color": "green", "value": 1 }
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 6, "y": 1 },
|
||||
"id": 3,
|
||||
"options": {
|
||||
"colorMode": "background",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "mana_stt_model_loaded{model=\"voxtral\"}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Voxtral Model",
|
||||
"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": 3, "x": 9, "y": 1 },
|
||||
"id": 4,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(mana_stt_requests_total{status=\"success\"})",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Total Transcriptions",
|
||||
"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": 3, "x": 12, "y": 1 },
|
||||
"id": 5,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(mana_stt_characters_transcribed_total)",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Characters Transcribed",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "yellow", "value": 1 },
|
||||
{ "color": "red", "value": 3 }
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 15, "y": 1 },
|
||||
"id": 6,
|
||||
"options": {
|
||||
"colorMode": "background",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(mana_stt_active_requests)",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Active Requests",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "red", "value": 1 }
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 18, "y": 1 },
|
||||
"id": 7,
|
||||
"options": {
|
||||
"colorMode": "background",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(mana_stt_requests_total{status=\"error\"})",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Total Errors",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"mappings": [],
|
||||
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 21, "y": 1 },
|
||||
"id": 8,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "histogram_quantile(0.50, sum(rate(mana_stt_transcription_duration_seconds_bucket[5m])) by (le))",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Median Duration",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
|
||||
"id": 101,
|
||||
"panels": [],
|
||||
"title": "Performance",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"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": "auto",
|
||||
"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": 0, "y": 6 },
|
||||
"id": 10,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["mean", "max"],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "histogram_quantile(0.50, sum(rate(mana_stt_transcription_duration_seconds_bucket{model=\"whisper\"}[5m])) by (le))",
|
||||
"legendFormat": "Whisper p50",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "histogram_quantile(0.95, sum(rate(mana_stt_transcription_duration_seconds_bucket{model=\"whisper\"}[5m])) by (le))",
|
||||
"legendFormat": "Whisper p95",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "histogram_quantile(0.50, sum(rate(mana_stt_transcription_duration_seconds_bucket{model=\"voxtral\"}[5m])) by (le))",
|
||||
"legendFormat": "Voxtral p50",
|
||||
"refId": "C"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "histogram_quantile(0.95, sum(rate(mana_stt_transcription_duration_seconds_bucket{model=\"voxtral\"}[5m])) by (le))",
|
||||
"legendFormat": "Voxtral p95",
|
||||
"refId": "D"
|
||||
}
|
||||
],
|
||||
"title": "Transcription Duration (p50 / p95)",
|
||||
"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": "auto",
|
||||
"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": 12, "x": 12, "y": 6 },
|
||||
"id": 11,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["mean", "sum"],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(rate(mana_stt_requests_total{model=\"whisper\", status=\"success\"}[5m]))",
|
||||
"legendFormat": "Whisper Success",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(rate(mana_stt_requests_total{model=\"voxtral\", status=\"success\"}[5m]))",
|
||||
"legendFormat": "Voxtral Success",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(rate(mana_stt_requests_total{status=\"error\"}[5m]))",
|
||||
"legendFormat": "Errors",
|
||||
"refId": "C"
|
||||
}
|
||||
],
|
||||
"title": "Request Rate",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 14 },
|
||||
"id": 102,
|
||||
"panels": [],
|
||||
"title": "Details",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } },
|
||||
"mappings": []
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 6, "x": 0, "y": 15 },
|
||||
"id": 12,
|
||||
"options": {
|
||||
"legend": { "displayMode": "list", "placement": "right", "showLegend": true },
|
||||
"pieType": "pie",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"tooltip": { "mode": "single", "sort": "none" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(mana_stt_requests_total{status=\"success\"}) by (model)",
|
||||
"legendFormat": "{{model}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Requests by Model",
|
||||
"type": "piechart"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } },
|
||||
"mappings": []
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 6, "x": 6, "y": 15 },
|
||||
"id": 13,
|
||||
"options": {
|
||||
"legend": { "displayMode": "list", "placement": "right", "showLegend": true },
|
||||
"pieType": "pie",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"tooltip": { "mode": "single", "sort": "none" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(mana_stt_requests_total{status=\"success\"}) by (language)",
|
||||
"legendFormat": "{{language}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Requests by Language",
|
||||
"type": "piechart"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "bars",
|
||||
"fillOpacity": 80,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": { "legend": false, "tooltip": false, "viz": false },
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"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": "decbytes"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 15 },
|
||||
"id": 14,
|
||||
"options": {
|
||||
"legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(rate(mana_stt_file_size_mb_sum{model=\"whisper\"}[5m])) * 1024 * 1024",
|
||||
"legendFormat": "Whisper",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(rate(mana_stt_file_size_mb_sum{model=\"voxtral\"}[5m])) * 1024 * 1024",
|
||||
"legendFormat": "Voxtral",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"title": "Data Processed",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 23 },
|
||||
"id": 103,
|
||||
"panels": [],
|
||||
"title": "Model Loading",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "yellow", "value": 30 },
|
||||
{ "color": "red", "value": 60 }
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 6, "w": 8, "x": 0, "y": 24 },
|
||||
"id": 15,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "mana_stt_model_load_duration_seconds_sum{model=\"whisper\"} / mana_stt_model_load_duration_seconds_count{model=\"whisper\"}",
|
||||
"legendFormat": "Whisper",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Whisper Load Time",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "yellow", "value": 60 },
|
||||
{ "color": "red", "value": 120 }
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 6, "w": 8, "x": 8, "y": 24 },
|
||||
"id": 16,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "mana_stt_model_load_duration_seconds_sum{model=\"voxtral\"} / mana_stt_model_load_duration_seconds_count{model=\"voxtral\"}",
|
||||
"legendFormat": "Voxtral",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Voxtral Load Time",
|
||||
"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": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": { "legend": false, "tooltip": false, "viz": false },
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "smooth",
|
||||
"lineWidth": 2,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": { "type": "linear" },
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": { "group": "A", "mode": "none" },
|
||||
"thresholdsStyle": { "mode": "off" }
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 6, "w": 8, "x": 16, "y": 24 },
|
||||
"id": 17,
|
||||
"options": {
|
||||
"legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(rate(mana_stt_characters_transcribed_total{model=\"whisper\"}[5m]))",
|
||||
"legendFormat": "Whisper",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"expr": "sum(rate(mana_stt_characters_transcribed_total{model=\"voxtral\"}[5m]))",
|
||||
"legendFormat": "Voxtral",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"title": "Characters/sec Transcribed",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"refresh": "30s",
|
||||
"schemaVersion": 39,
|
||||
"tags": ["manacore", "stt", "ai"],
|
||||
"templating": { "list": [] },
|
||||
"time": { "from": "now-1h", "to": "now" },
|
||||
"timepicker": {},
|
||||
"timezone": "browser",
|
||||
"title": "ManaCore STT Service",
|
||||
"uid": "mana-stt-dashboard",
|
||||
"version": 1,
|
||||
"weekStart": "monday"
|
||||
}
|
||||
595
services/ollama-metrics-proxy/grafana-dashboard.json
Normal file
595
services/ollama-metrics-proxy/grafana-dashboard.json
Normal file
|
|
@ -0,0 +1,595 @@
|
|||
{
|
||||
"annotations": { "list": [] },
|
||||
"description": "Ollama LLM Monitoring - Generation metrics, token usage, model performance",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 1,
|
||||
"panels": [
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
|
||||
"id": 100,
|
||||
"panels": [],
|
||||
"title": "Overview",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [
|
||||
{
|
||||
"options": {
|
||||
"0": { "color": "red", "text": "DOWN" },
|
||||
"1": { "color": "green", "text": "UP" }
|
||||
},
|
||||
"type": "value"
|
||||
}
|
||||
],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "red", "value": null },
|
||||
{ "color": "green", "value": 1 }
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 0, "y": 1 },
|
||||
"id": 1,
|
||||
"options": {
|
||||
"colorMode": "background",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [{ "expr": "up{job=\"ollama\"}", "refId": "A" }],
|
||||
"title": "Proxy Status",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"mappings": [],
|
||||
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
||||
"unit": "short"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 3, "y": 1 },
|
||||
"id": 2,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [{ "expr": "sum(ollama_requests_total{status=\"success\"})", "refId": "A" }],
|
||||
"title": "Total Requests",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"mappings": [],
|
||||
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
||||
"unit": "short"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 6, "y": 1 },
|
||||
"id": 3,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [{ "expr": "sum(ollama_tokens_generated_total)", "refId": "A" }],
|
||||
"title": "Total Tokens Generated",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"mappings": [],
|
||||
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
||||
"unit": "short"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 9, "y": 1 },
|
||||
"id": 4,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [{ "expr": "sum(ollama_prompt_tokens_total)", "refId": "A" }],
|
||||
"title": "Total Prompt Tokens",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "yellow", "value": 1 },
|
||||
{ "color": "red", "value": 3 }
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 12, "y": 1 },
|
||||
"id": 5,
|
||||
"options": {
|
||||
"colorMode": "background",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [{ "expr": "sum(ollama_active_requests)", "refId": "A" }],
|
||||
"title": "Active Requests",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "red", "value": 1 }
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 15, "y": 1 },
|
||||
"id": 6,
|
||||
"options": {
|
||||
"colorMode": "background",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [{ "expr": "sum(ollama_requests_total{status=\"error\"})", "refId": "A" }],
|
||||
"title": "Total Errors",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"mappings": [],
|
||||
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
||||
"unit": "s"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 18, "y": 1 },
|
||||
"id": 7,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(ollama_generation_duration_seconds_bucket[5m])) by (le))",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Median Generation Time",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"mappings": [],
|
||||
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
||||
"unit": "s"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 3, "x": 21, "y": 1 },
|
||||
"id": 8,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(ollama_time_to_first_token_seconds_bucket[5m])) by (le))",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Median TTFT",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
|
||||
"id": 101,
|
||||
"panels": [],
|
||||
"title": "Performance",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 20,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": { "legend": false, "tooltip": false, "viz": false },
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "smooth",
|
||||
"lineWidth": 2,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": { "type": "linear" },
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": { "group": "A", "mode": "none" },
|
||||
"thresholdsStyle": { "mode": "off" }
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
||||
"unit": "s"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 6 },
|
||||
"id": 10,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["mean", "max"],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(ollama_generation_duration_seconds_bucket[5m])) by (le, model))",
|
||||
"legendFormat": "{{model}} p50",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.95, sum(rate(ollama_generation_duration_seconds_bucket[5m])) by (le, model))",
|
||||
"legendFormat": "{{model}} p95",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"title": "Generation Duration by Model (p50 / p95)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"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": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": { "group": "A", "mode": "none" },
|
||||
"thresholdsStyle": { "mode": "off" }
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
||||
"unit": "s"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 6 },
|
||||
"id": 11,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["mean", "max"],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(ollama_time_to_first_token_seconds_bucket[5m])) by (le, model))",
|
||||
"legendFormat": "{{model}} p50",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.95, sum(rate(ollama_time_to_first_token_seconds_bucket[5m])) by (le, model))",
|
||||
"legendFormat": "{{model}} p95",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"title": "Time to First Token by Model (p50 / p95)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 14 },
|
||||
"id": 102,
|
||||
"panels": [],
|
||||
"title": "Token Usage",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 30,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": { "legend": false, "tooltip": false, "viz": false },
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "smooth",
|
||||
"lineWidth": 2,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": { "type": "linear" },
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": { "group": "A", "mode": "normal" },
|
||||
"thresholdsStyle": { "mode": "off" }
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
||||
"unit": "short"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 15 },
|
||||
"id": 12,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["sum"],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(ollama_tokens_generated_total[5m])) by (model)",
|
||||
"legendFormat": "{{model}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Tokens Generated per Second by Model",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 30,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": { "legend": false, "tooltip": false, "viz": false },
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "smooth",
|
||||
"lineWidth": 2,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": { "type": "linear" },
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": { "group": "A", "mode": "normal" },
|
||||
"thresholdsStyle": { "mode": "off" }
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
||||
"unit": "reqps"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 15 },
|
||||
"id": 13,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["mean", "sum"],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(ollama_requests_total{status=\"success\"}[5m])) by (model)",
|
||||
"legendFormat": "{{model}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Requests per Second by Model",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 23 },
|
||||
"id": 103,
|
||||
"panels": [],
|
||||
"title": "Model Distribution",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } },
|
||||
"mappings": []
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 8, "x": 0, "y": 24 },
|
||||
"id": 14,
|
||||
"options": {
|
||||
"legend": { "displayMode": "list", "placement": "right", "showLegend": true },
|
||||
"pieType": "pie",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"tooltip": { "mode": "single", "sort": "none" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(ollama_requests_total{status=\"success\"}) by (model)",
|
||||
"legendFormat": "{{model}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Requests by Model",
|
||||
"type": "piechart"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } },
|
||||
"mappings": []
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 8, "x": 8, "y": 24 },
|
||||
"id": 15,
|
||||
"options": {
|
||||
"legend": { "displayMode": "list", "placement": "right", "showLegend": true },
|
||||
"pieType": "pie",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"tooltip": { "mode": "single", "sort": "none" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(ollama_tokens_generated_total) by (model)",
|
||||
"legendFormat": "{{model}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Tokens by Model",
|
||||
"type": "piechart"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } },
|
||||
"mappings": []
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 8, "x": 16, "y": 24 },
|
||||
"id": 16,
|
||||
"options": {
|
||||
"legend": { "displayMode": "list", "placement": "right", "showLegend": true },
|
||||
"pieType": "pie",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"tooltip": { "mode": "single", "sort": "none" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(ollama_requests_total{status=\"success\"}) by (endpoint)",
|
||||
"legendFormat": "{{endpoint}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Requests by Endpoint",
|
||||
"type": "piechart"
|
||||
}
|
||||
],
|
||||
"refresh": "30s",
|
||||
"schemaVersion": 39,
|
||||
"tags": ["manacore", "ollama", "llm", "ai"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"current": { "selected": false, "text": "Prometheus", "value": "Prometheus" },
|
||||
"hide": 0,
|
||||
"includeAll": false,
|
||||
"multi": false,
|
||||
"name": "datasource",
|
||||
"options": [],
|
||||
"query": "prometheus",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"skipUrlSync": false,
|
||||
"type": "datasource"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": { "from": "now-1h", "to": "now" },
|
||||
"timepicker": {},
|
||||
"timezone": "browser",
|
||||
"title": "Ollama LLM Service",
|
||||
"uid": "ollama-dashboard",
|
||||
"version": 1,
|
||||
"weekStart": "monday"
|
||||
}
|
||||
|
|
@ -15,10 +15,15 @@ S3_ACCESS_KEY=minioadmin
|
|||
S3_SECRET_KEY=minioadmin
|
||||
S3_BUCKET=projectdoc-storage
|
||||
|
||||
# AI - Transcription (OpenAI Whisper)
|
||||
# AI - Transcription (STT)
|
||||
STT_PROVIDER=local # local | openai
|
||||
STT_LOCAL_URL=http://localhost:3020 # mana-stt service URL
|
||||
STT_MODEL=whisper # whisper | voxtral
|
||||
|
||||
# OpenAI (optional fallback for STT, required if STT_PROVIDER=openai)
|
||||
OPENAI_API_KEY=sk-your-openai-key
|
||||
|
||||
# AI - Generation
|
||||
LLM_PROVIDER=ollama # ollama | openai
|
||||
OLLAMA_URL=http://localhost:11434
|
||||
OLLAMA_URL=http://localhost:11435 # Use :11435 for metrics proxy, :11434 for direct
|
||||
OLLAMA_MODEL=gemma3:4b
|
||||
|
|
|
|||
|
|
@ -20,6 +20,11 @@ export default () => ({
|
|||
openai: {
|
||||
apiKey: process.env.OPENAI_API_KEY,
|
||||
},
|
||||
stt: {
|
||||
provider: process.env.STT_PROVIDER || 'local', // 'local' or 'openai'
|
||||
localUrl: process.env.STT_LOCAL_URL || 'http://localhost:3020',
|
||||
model: process.env.STT_MODEL || 'whisper', // 'whisper' or 'voxtral'
|
||||
},
|
||||
llm: {
|
||||
provider: process.env.LLM_PROVIDER || 'ollama',
|
||||
ollama: {
|
||||
|
|
|
|||
|
|
@ -1,10 +1,19 @@
|
|||
import { pgTable, uuid, text, timestamp, integer, jsonb, boolean } from 'drizzle-orm/pg-core';
|
||||
import {
|
||||
pgTable,
|
||||
uuid,
|
||||
text,
|
||||
timestamp,
|
||||
integer,
|
||||
bigint,
|
||||
jsonb,
|
||||
boolean,
|
||||
} from 'drizzle-orm/pg-core';
|
||||
import { relations } from 'drizzle-orm';
|
||||
|
||||
// Projects table
|
||||
export const projects = pgTable('projects', {
|
||||
id: uuid('id').primaryKey().defaultRandom(),
|
||||
telegramUserId: integer('telegram_user_id').notNull(),
|
||||
telegramUserId: bigint('telegram_user_id', { mode: 'number' }).notNull(),
|
||||
name: text('name').notNull(),
|
||||
description: text('description'),
|
||||
status: text('status').default('active').notNull(), // active, archived, completed
|
||||
|
|
|
|||
|
|
@ -2,48 +2,115 @@ import { Injectable, Logger } from '@nestjs/common';
|
|||
import { ConfigService } from '@nestjs/config';
|
||||
import OpenAI from 'openai';
|
||||
|
||||
interface LocalSTTResponse {
|
||||
text: string;
|
||||
language?: string;
|
||||
model: string;
|
||||
}
|
||||
|
||||
@Injectable()
|
||||
export class TranscriptionService {
|
||||
private readonly logger = new Logger(TranscriptionService.name);
|
||||
private readonly openai: OpenAI | null;
|
||||
private readonly provider: 'local' | 'openai';
|
||||
private readonly localUrl: string;
|
||||
private readonly sttModel: string;
|
||||
|
||||
constructor(private configService: ConfigService) {
|
||||
this.provider = this.configService.get<string>('stt.provider', 'local') as 'local' | 'openai';
|
||||
this.localUrl = this.configService.get<string>('stt.localUrl', 'http://localhost:3020');
|
||||
this.sttModel = this.configService.get<string>('stt.model', 'whisper');
|
||||
|
||||
const apiKey = this.configService.get<string>('openai.apiKey');
|
||||
|
||||
if (apiKey) {
|
||||
this.openai = new OpenAI({ apiKey });
|
||||
this.logger.log('OpenAI Whisper initialized');
|
||||
this.logger.log('OpenAI Whisper available as fallback');
|
||||
} else {
|
||||
this.openai = null;
|
||||
this.logger.warn('OpenAI API key not configured - transcription disabled');
|
||||
}
|
||||
|
||||
this.logger.log(
|
||||
`STT Provider: ${this.provider}, URL: ${this.localUrl}, Model: ${this.sttModel}`
|
||||
);
|
||||
}
|
||||
|
||||
async transcribe(audioBuffer: Buffer, filename = 'audio.ogg'): Promise<string> {
|
||||
// Try local STT first if configured
|
||||
if (this.provider === 'local') {
|
||||
try {
|
||||
return await this.transcribeLocal(audioBuffer, filename);
|
||||
} catch (error) {
|
||||
this.logger.warn(`Local STT failed, trying OpenAI fallback: ${error}`);
|
||||
if (this.openai) {
|
||||
return await this.transcribeOpenAI(audioBuffer, filename);
|
||||
}
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
|
||||
// Use OpenAI
|
||||
if (this.openai) {
|
||||
return await this.transcribeOpenAI(audioBuffer, filename);
|
||||
}
|
||||
|
||||
throw new Error('No STT provider available');
|
||||
}
|
||||
|
||||
private async transcribeLocal(audioBuffer: Buffer, filename: string): Promise<string> {
|
||||
const endpoint = this.sttModel === 'voxtral' ? '/transcribe/voxtral' : '/transcribe';
|
||||
const url = `${this.localUrl}${endpoint}`;
|
||||
|
||||
this.logger.debug(`Calling local STT: ${url}`);
|
||||
|
||||
const formData = new FormData();
|
||||
const uint8Array = new Uint8Array(audioBuffer);
|
||||
const blob = new Blob([uint8Array], { type: 'audio/ogg' });
|
||||
formData.append('file', blob, filename);
|
||||
formData.append('language', 'de');
|
||||
|
||||
const response = await fetch(url, {
|
||||
method: 'POST',
|
||||
body: formData,
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
const error = await response.text();
|
||||
throw new Error(`Local STT error: ${response.status} - ${error}`);
|
||||
}
|
||||
|
||||
const result: LocalSTTResponse = await response.json();
|
||||
this.logger.debug(`Local STT result: ${result.text.length} chars, model: ${result.model}`);
|
||||
|
||||
return result.text;
|
||||
}
|
||||
|
||||
private async transcribeOpenAI(audioBuffer: Buffer, filename: string): Promise<string> {
|
||||
if (!this.openai) {
|
||||
throw new Error('Transcription not available - OpenAI API key not configured');
|
||||
throw new Error('OpenAI not configured');
|
||||
}
|
||||
|
||||
try {
|
||||
// Create a File object from the buffer using Uint8Array
|
||||
const uint8Array = new Uint8Array(audioBuffer);
|
||||
const file = new File([uint8Array], filename, { type: 'audio/ogg' });
|
||||
|
||||
const response = await this.openai.audio.transcriptions.create({
|
||||
file,
|
||||
model: 'whisper-1',
|
||||
language: 'de', // Default to German, could be made configurable
|
||||
language: 'de',
|
||||
});
|
||||
|
||||
this.logger.debug(`Transcribed ${audioBuffer.length} bytes -> ${response.text.length} chars`);
|
||||
this.logger.debug(
|
||||
`OpenAI transcribed ${audioBuffer.length} bytes -> ${response.text.length} chars`
|
||||
);
|
||||
return response.text;
|
||||
} catch (error) {
|
||||
this.logger.error('Transcription failed:', error);
|
||||
this.logger.error('OpenAI transcription failed:', error);
|
||||
throw new Error('Transkription fehlgeschlagen');
|
||||
}
|
||||
}
|
||||
|
||||
isAvailable(): boolean {
|
||||
return this.openai !== null;
|
||||
return this.provider === 'local' || this.openai !== null;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue