Connections
Grafana Cloud
Connections
Grafana Cloud
LLM Observability with Grafana Cloud and OpenLIT
To send OpenTelemetry data collected by OpenLIT from your LLM Application to Grafana Cloud, Add the snippet below to your Python application.
1
Get your Grafana Cloud Crednetials
- Sign in to Grafana Cloud Portal and select your Grafana Cloud Stack.
- Click Configure in the OpenTelemetry section.
- In the Password / API Token section, click on Generate now to create a new API token:
- Give the API token a name, for example
openlit - Click on Create token
- Click on Close without copying the token
- Copy and Save the value for
OTEL_EXPORTER_OTLP_ENDPOINTandOTEL_EXPORTER_OTLP_HEADERSReplace the space afterBasicwith%20: OTEL_EXPORTER_OTLP_HEADERS=“Authorization=Basic%20[base64 instanceID:token]”
- Give the API token a name, for example
2
Add the following two lines to your application code:
import openlit
openlit.init(
otlp_endpoint="YOUR_GRAFANA_OTEL_GATEWAY_URL",
otlp_headers="YOUR_GRAFANA_OTEL_GATEWAY_AUTH"
)
Replace:
YOUR_GRAFANA_OTEL_GATEWAY_URLwith theOTEL_EXPORTER_OTLP_ENDPOINTvalue you copied in Step 1.
- Example -
https://otlp-gateway-<zone>.grafana.net/otlp
YOUR_GRAFANA_OTEL_GATEWAY_AUTHwith theOTEL_EXPORTER_OTLP_HEADERSvalue you copied in Step 1.
- Example -
Authorization=Basic%20<base64 encoded Instance ID and API Token>
Refer to the OpenLIT Python SDK repository for more advanced configurations and use cases.
3
Import the pre-built Dashboard
- Log into your Grafana Cloud Instance.
- Click Dashboards in the primary menu.
- Click New and select Import in the drop-down menu.
- Copy the dashboard JSON provided in the accordion named
Dashboardbelow. - Paste the dashboard JSON text directly into the text area.
- Click Import.
- Save the dashboard.
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": 12,
"links": [
{
"asDropdown": false,
"icon": "bolt",
"includeVars": false,
"keepTime": false,
"tags": [],
"targetBlank": true,
"title": "OpenLIT Github",
"tooltip": "Github",
"type": "link",
"url": "https://github.com/openlit/openlit"
},
{
"asDropdown": false,
"icon": "doc",
"includeVars": false,
"keepTime": false,
"tags": [],
"targetBlank": true,
"title": "OpenLIT Docs",
"tooltip": "Documentation",
"type": "link",
"url": "https://docs.openlit.io/"
}
],
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"gridPos": {
"h": 5,
"w": 12,
"x": 0,
"y": 0
},
"id": 21,
"options": {
"code": {
"language": "plaintext",
"showLineNumbers": false,
"showMiniMap": false
},
"content": "---\n# GenAI Observability\n\nThis dashboard displays the usage of Large Language Models (LLM) and Vector Databases, tracking OpenTelemetry Traces and Metrics sent using [OpenLIT](https://github.com/openlit/openlit).\n\n---",
"mode": "markdown"
},
"pluginVersion": "11.1.0-69950",
"transparent": true,
"type": "text"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the LLM Request Rate ",
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "blue",
"mode": "palette-classic-by-name"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
},
{
"color": "#EAB839",
"value": 10
},
{
"color": "#6ED0E0",
"value": 100
}
]
},
"unit": "reqps"
},
"overrides": []
},
"gridPos": {
"h": 2,
"w": 12,
"x": 12,
"y": 0
},
"id": 22,
"options": {
"colorMode": "background",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": true,
"textMode": "value_and_name",
"wideLayout": true
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum(rate(gen_ai_requests_total{telemetry_sdk_name=\"openlit\"}[$__rate_interval]))",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "LLM Request Rate",
"range": true,
"refId": "A",
"useBackend": false
}
],
"transparent": true,
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the VectorDB Request Rate",
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "blue",
"mode": "palette-classic-by-name"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
},
{
"color": "#EAB839",
"value": 10
},
{
"color": "#6ED0E0",
"value": 100
}
]
},
"unit": "reqps"
},
"overrides": []
},
"gridPos": {
"h": 2,
"w": 12,
"x": 12,
"y": 2
},
"id": 23,
"options": {
"colorMode": "background",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": true,
"textMode": "value_and_name",
"wideLayout": true
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum(rate(db_requests_total{telemetry_sdk_name=\"openlit\"}[$__rate_interval]))",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "VectorDB Request Rate",
"range": true,
"refId": "A",
"useBackend": false
}
],
"transparent": true,
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the total cost incurred from using GenAI models. It reflects the financial impact of operational activities, offering insights into budgetary allocation and efficiency. Tracking this helps in effective cost management and financial planning for GenAI usage.",
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "blue",
"mode": "shades"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "currencyUSD"
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 12,
"x": 12,
"y": 4
},
"id": 2,
"options": {
"colorMode": "background",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": true,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum(gen_ai_usage_cost_USD_sum{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Total Usage Cost",
"range": true,
"refId": "A",
"useBackend": false
}
],
"transparent": true,
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the total number of successful requests made to the GenAI system. A successful request is one that is completed without errors, indicating seamless operation and effective utilization of the GenAI service. Tracking this helps in understanding the reliability and performance of the GenAI system.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic-by-name"
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 6,
"x": 0,
"y": 5
},
"id": 1,
"options": {
"colorMode": "background",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": true,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum by() (gen_ai_requests_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Total Successful GenAI Requests",
"range": true,
"refId": "A",
"useBackend": false
}
],
"transparent": true,
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the total count of successful VectorDB requests. It indicates requests that have been processed completely without any errors, showcasing VectorDB's effectiveness and reliability. Watching this helps gauge how well VectorDB is performing and its success in handling operations.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 6,
"x": 6,
"y": 5
},
"id": 7,
"options": {
"colorMode": "background",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": true,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum(db_requests_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Total Successful VectorDB Requests",
"range": true,
"refId": "A",
"useBackend": false
}
],
"transparent": true,
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the total number of tokens consumed by GenAI requests, providing a direct measure of usage. Monitoring this helps in assessing the demand on GenAI services and guiding resource allocation or optimization strategies.",
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "purple",
"mode": "shades"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 6,
"x": 12,
"y": 7
},
"id": 3,
"options": {
"colorMode": "background",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": true,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum(gen_ai_usage_tokens_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Total Usage Tokens",
"range": true,
"refId": "A",
"useBackend": false
}
],
"transparent": true,
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the average cost per use of the GenAI models and related services. It provides insights into the cost-effectiveness of interactions with GenAI, helping to identify trends in expense per operation. Monitoring this assists in optimizing budget allocation and improving cost efficiency in GenAI utilization.",
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "blue",
"mode": "shades"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "#EAB839",
"value": 0.5
},
{
"color": "red",
"value": 1
}
]
},
"unit": "currencyUSD"
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 6,
"x": 18,
"y": 7
},
"id": 5,
"options": {
"colorMode": "background",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": true,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "avg by() (gen_ai_usage_cost_USD_sum{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Avg Usage Cost",
"range": true,
"refId": "A",
"useBackend": false
}
],
"transparent": true,
"type": "stat"
},
{
"datasource": {
"type": "tempo",
"uid": "${traceDatasource}"
},
"description": "This panel displays the distribution of request durations for both GenAI and VectorDB services. It highlights how long requests take to complete, from the shortest to the longest durations, offering insights into system performance and efficiency. Understanding this distribution helps in identifying bottlenecks and optimizing response times for both services.",
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "blue",
"mode": "palette-classic"
},
"custom": {
"fillOpacity": 81,
"gradientMode": "opacity",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineWidth": 3,
"stacking": {
"group": "A",
"mode": "none"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 10
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 10
},
"id": 4,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
}
},
"pluginVersion": "11.1.0-69372",
"targets": [
{
"datasource": {
"type": "tempo",
"uid": "${traceDatasource}"
},
"filters": [
{
"id": "status",
"operator": "=",
"scope": "intrinsic",
"tag": "status",
"value": "ok",
"valueType": "keyword"
},
{
"id": "f755ab99",
"operator": "=",
"scope": "span",
"tag": "telemetry.sdk.name",
"value": [
"openlit"
],
"valueType": "string"
}
],
"limit": 20,
"query": "{status=ok && span.telemetry.sdk.name=\"openlit\" && span.gen_ai.application_name=~\"$application\" && span.gen_ai.environment=~\"$environment\"}",
"queryType": "traceql",
"refId": "A",
"tableType": "traces"
}
],
"title": "Request Duration Distribution",
"type": "histogram"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the ranking of GenAI models based on their usage frequency. It identifies which models are most popular or in-demand, providing insights into user preferences and operational trends. Analyzing this helps in resource allocation, optimizing model availability, and understanding which GenAI features are driving usage.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "continuous-BlYlRd"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 10,
"w": 14,
"x": 0,
"y": 17
},
"id": 17,
"options": {
"displayMode": "gradient",
"maxVizHeight": 300,
"minVizHeight": 16,
"minVizWidth": 8,
"namePlacement": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showUnfilled": true,
"sizing": "auto",
"valueMode": "text"
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "topk(5, sum by(gen_ai_request_model) (gen_ai_requests_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"}))",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Top GenAI Models by Usage",
"transparent": true,
"type": "bargauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the distribution of GenAI requests across different platforms such as OpenAI, Cohere, Anthropic, etc. It shows where requests are being sent, giving insights into platform popularity and usage patterns. Monitoring this helps in understanding platform preferences, and it can guide strategic decisions for integration or diversification of GenAI services.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
}
},
"mappings": [],
"min": 0,
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 5,
"x": 14,
"y": 17
},
"id": 16,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"pieType": "pie",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "11.1.0-69372",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum by(gen_ai_system) (gen_ai_requests_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "GenAI Requests by Platform",
"type": "piechart"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the breakdown of GenAI requests by type, such as Chat, Embedding, Image, Audio, and Fine Tuning. It reveals the diversity in usage, highlighting which types of requests are most common. Understanding this distribution assists in optimizing resources for the most demanded services and planning for future needs based on usage trends.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
}
},
"mappings": [],
"min": 0,
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 5,
"x": 19,
"y": 17
},
"id": 13,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"pieType": "pie",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "11.1.0-69372",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum by(gen_ai_type) (gen_ai_requests_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "GenAI Requests by Type",
"type": "piechart"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the distribution of GenAI requests based on the environment, such as production, development, testing, etc. It shows where the requests are being utilized, providing a clear picture of operational focus and deployment strategies. Tracking this helps in aligning resources appropriately and optimizing the performance across different environments.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
}
},
"mappings": [],
"min": 0,
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 5,
"x": 14,
"y": 22
},
"id": 15,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"pieType": "pie",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "11.1.0-69372",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum by(gen_ai_environment) (gen_ai_requests_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "GenAI Requests by Environment",
"type": "piechart"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the distribution of GenAI requests based on the application, such as production, development, testing, etc. It shows where the requests are being utilized, providing a clear picture of operational focus and deployment strategies. Tracking this helps in aligning resources appropriately and optimizing the performance across different environments.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
}
},
"mappings": [],
"min": 0,
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 5,
"x": 19,
"y": 22
},
"id": 27,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"pieType": "pie",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "11.1.0-69372",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum by(gen_ai_application) (gen_ai_requests_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "GenAI Requests by Application",
"type": "piechart"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays a comparative graph showing the average number of tokens consumed for completions and prompts against the average usage cost. It provides a visual representation of the relationship between the volume of data processed (in tokens) and the financial implications of using GenAI services. Analyzing this comparison helps in assessing cost-effectiveness and guiding strategic decisions for efficient resource utilization.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 1,
"drawStyle": "line",
"fillOpacity": 30,
"gradientMode": "opacity",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "smooth",
"lineStyle": {
"fill": "solid"
},
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "always",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 27
},
"id": 6,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "avg(gen_ai_usage_prompt_tokens_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Prompt Tokens",
"range": true,
"refId": "A",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "avg(gen_ai_usage_completion_tokens_total{telemetry_sdk_name=\"openlit\"})",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Completion Tokens",
"range": true,
"refId": "B",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "avg(gen_ai_usage_cost_USD_bucket{telemetry_sdk_name=\"openlit\"})",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Usage Cost",
"range": true,
"refId": "C",
"useBackend": false
}
],
"title": "Average Token Consumption vs. Average Usage Cost Comparison",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 35
},
"id": 10,
"panels": [],
"title": "GenAI Requests",
"type": "row"
},
{
"datasource": {
"type": "tempo",
"uid": "${traceDatasource}"
},
"description": "This panel displays a detailed table of GenAI request traces, providing comprehensive insights into each request's timing, source, type, and outcome. It allows for the in-depth analysis of individual requests, facilitating troubleshooting, performance monitoring, and understanding user interactions with GenAI services. Tracking this helps in identifying patterns, potential issues, and opportunities for optimization.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "continuous-BlPu"
},
"custom": {
"align": "auto",
"cellOptions": {
"type": "color-background"
},
"inspect": false
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 16,
"w": 24,
"x": 0,
"y": 36
},
"id": 8,
"options": {
"cellHeight": "sm",
"footer": {
"countRows": false,
"fields": "",
"reducer": [
"sum"
],
"show": false
},
"showHeader": true
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "tempo",
"uid": "${traceDatasource}"
},
"filters": [
{
"id": "e7e29fde",
"operator": "!=",
"scope": "span",
"tag": "gen_ai.type",
"value": [
"vectordb"
],
"valueType": "string"
},
{
"id": "status",
"operator": "=",
"scope": "intrinsic",
"tag": "status",
"value": "ok",
"valueType": "keyword"
}
],
"limit": 20,
"query": "{span.gen_ai.type!=\"vectordb\" && status=ok && span.gen_ai.application_name=~\"$application\" && span.gen_ai.environment=~\"$environment\"} | select(span.gen_ai.content.prompt, span.gen_ai.content.completion, span.gen_ai.usage.cost)",
"queryType": "traceql",
"refId": "A",
"tableType": "traces"
}
],
"transparent": true,
"type": "table"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "",
"gridPos": {
"h": 2,
"w": 24,
"x": 0,
"y": 52
},
"id": 25,
"options": {
"code": {
"language": "plaintext",
"showLineNumbers": false,
"showMiniMap": false
},
"content": "### VectorDB\n\n---",
"mode": "markdown"
},
"pluginVersion": "11.1.0-69950",
"transparent": true,
"type": "text"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the breakdown of database requests based on the type of operation, such as add, updates, deletes, and queries. It provides insights into the operational dynamics of database interactions, highlighting the most common actions performed. Understanding this distribution helps in optimizing database performance and planning for capacity based on operational needs.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "continuous-BlYlRd"
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 9,
"w": 14,
"x": 0,
"y": 54
},
"id": 20,
"options": {
"displayMode": "gradient",
"maxVizHeight": 300,
"minVizHeight": 16,
"minVizWidth": 8,
"namePlacement": "top",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showUnfilled": true,
"sizing": "auto",
"valueMode": "text"
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum by(db_operation) (db_requests_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "DB Requests by Operation",
"transparent": true,
"type": "bargauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the distribution of requests across different VectorDB systems, such as Chroma, Pinecone, etc. It highlights which VectorDB services are most frequently used, providing insights into system preference and usage patterns. Monitoring this helps in evaluating the performance and scalability of each VectorDB system, guiding strategic decisions for technology adoption and integration.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
}
},
"mappings": []
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 10,
"x": 14,
"y": 54
},
"id": 18,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"pieType": "pie",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum by(db_system) (db_requests_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "DB Requests by System",
"type": "piechart"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the breakdown of DB requests by application name, offering insights into which applications are leveraging VectorDB services the most. This identification helps in understanding application-specific demand, guiding resource allocation, and supporting targeted optimization efforts for enhanced efficiency in application performance.\"",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
}
},
"mappings": [],
"min": 0,
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 5,
"x": 14,
"y": 59
},
"id": 19,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"pieType": "pie",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "11.1.0-69372",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum by(gen_ai_application_name) (db_requests_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "DB Requests by Application",
"type": "piechart"
},
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"description": "This panel displays the breakdown of DB requests by application name, offering insights into which applications are leveraging VectorDB services the most. This identification helps in understanding application-specific demand, guiding resource allocation, and supporting targeted optimization efforts for enhanced efficiency in application performance.\"",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
}
},
"mappings": [],
"min": 0,
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 5,
"x": 19,
"y": 59
},
"id": 26,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"pieType": "pie",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "11.1.0-69372",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum by(gen_ai_application_name) (db_requests_total{telemetry_sdk_name=\"openlit\", gen_ai_application_name=~\"$application\", gen_ai_environment=~\"$environment\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "DB Requests by Application",
"type": "piechart"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 63
},
"id": 12,
"panels": [],
"title": "VectorDB Requests",
"type": "row"
},
{
"datasource": {
"type": "tempo",
"uid": "${traceDatasource}"
},
"description": "This panel displays a table with detailed traces of VectorDB requests, offering insights into specifics like request timing, source, operation type, and results. It's designed for thorough examination of VectorDB interactions, enabling precise troubleshooting, performance evaluation, and user behavior understanding. By monitoring these traces, users can spot trends, diagnose problems, and improve operational efficiency in handling VectorDB requests.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic-by-name"
},
"custom": {
"align": "auto",
"cellOptions": {
"type": "color-background"
},
"inspect": false
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 15,
"w": 24,
"x": 0,
"y": 64
},
"id": 9,
"options": {
"cellHeight": "sm",
"footer": {
"countRows": false,
"fields": "",
"reducer": [
"sum"
],
"show": false
},
"showHeader": true
},
"pluginVersion": "11.1.0-69950",
"targets": [
{
"datasource": {
"type": "tempo",
"uid": "${traceDatasource}"
},
"filters": [
{
"id": "e7e29fde",
"operator": "=",
"scope": "span",
"tag": "gen_ai.type",
"value": [
"vectordb"
],
"valueType": "string"
},
{
"id": "status",
"operator": "=",
"scope": "intrinsic",
"tag": "status",
"value": "ok",
"valueType": "keyword"
}
],
"limit": 20,
"query": "{span.gen_ai.type=\"vectordb\" && status=ok && span.gen_ai.application_name=~\"$application\" && span.gen_ai.environment=~\"$environment\"}",
"queryType": "traceql",
"refId": "A",
"tableType": "traces"
}
],
"transparent": true,
"type": "table"
}
],
"refresh": "",
"schemaVersion": 39,
"tags": [
"LLM",
"VectorDB",
"GenAI"
],
"templating": {
"list": [
{
"hide": 0,
"includeAll": false,
"label": "Trace Datasource",
"multi": false,
"name": "traceDatasource",
"options": [],
"query": "tempo",
"queryValue": "",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"hide": 0,
"includeAll": false,
"label": "Metrics Datasource",
"multi": false,
"name": "metricsDatasource",
"options": [],
"query": "prometheus",
"queryValue": "",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"current": {
"selected": true,
"text": [
"All"
],
"value": [
"$__all"
]
},
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"definition": "label_values(gen_ai_application_name)",
"hide": 0,
"includeAll": true,
"label": "Application",
"multi": true,
"name": "application",
"options": [],
"query": {
"qryType": 1,
"query": "label_values(gen_ai_application_name)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"type": "query"
},
{
"current": {
"selected": true,
"text": [
"All"
],
"value": [
"$__all"
]
},
"datasource": {
"type": "prometheus",
"uid": "${metricsDatasource}"
},
"definition": "label_values(gen_ai_environment)",
"hide": 0,
"includeAll": true,
"label": "Environment",
"multi": true,
"name": "environment",
"options": [],
"query": {
"qryType": 1,
"query": "label_values(gen_ai_environment)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"type": "query"
}
]
},
"time": {
"from": "now-24h",
"to": "now"
},
"timeRangeUpdatedDuringEditOrView": false,
"timepicker": {},
"timezone": "browser",
"title": "GenAI Observability",
"uid": "cdiz9piuoa3gge",
"version": 15,
"weekStart": ""
}
Was this page helpful?