nvidia dash

nvidia_nim/README.md

@@ -2,7 +2,7 @@
 
 ## Overview
 
-This check monitors [Nvidia NIM][1] through the Datadog Agent. 
+This check monitors [NVIDIA NIM][1] through the Datadog Agent. 
 
 ## Setup
 
@@ -12,15 +12,15 @@ Follow the instructions below to install and configure this check for an Agent r
 
 ### Installation
 
-The Nvidia NIM check is included in the [Datadog Agent][2] package. No additional installation is needed on your server.
+The NVIDIA NIM check is included in the [Datadog Agent][2] package. No additional installation is needed on your server.
 
 ### Configuration
 
-Nvidia NIM provides Prometheus metrics indicating request statistics. By default, these metrics are available at http://localhost:8000/metrics. The Datadog Agent can collect the exposed metrics using this integration. Follow the instructions below to configure data collection from any or all of the components.
+NVIDIA NIM provides Prometheus metrics indicating request statistics. By default, these metrics are available at http://localhost:8000/metrics. The Datadog Agent can collect the exposed metrics using this integration. Follow the instructions below to configure data collection from any or all of the components.
 
 **Note**: This check uses [OpenMetrics][10] for metric collection, which requires Python 3.
 
-1. Edit the `nvidia_nim.d/conf.yaml` file, in the `conf.d/` folder at the root of your Agent's configuration directory to start collecting your Nvidia NIM performance data. See the [sample nvidia_nim.d/conf.yaml][4] for all available configuration options.
+1. Edit the `nvidia_nim.d/conf.yaml` file, in the `conf.d/` folder at the root of your Agent's configuration directory to start collecting your NVIDIA NIM performance data. See the [sample nvidia_nim.d/conf.yaml][4] for all available configuration options.
 
 2. [Restart the Agent][5].
 
@@ -36,11 +36,11 @@ See [metadata.csv][7] for a list of metrics provided by this integration.
 
 ### Events
 
-The Nvidia NIM integration does not include any events.
+The NVIDIA NIM integration does not include any events.
 
 ### Service Checks
 
-The Nvidia NIM integration does not include any service checks.
+The NVIDIA NIM integration does not include any service checks.
 
 See [service_checks.json][8] for a list of service checks provided by this integration.
 

nvidia_nim/assets/configuration/spec.yaml

@@ -12,5 +12,5 @@ files:
         openmetrics_endpoint.required: true
         openmetrics_endpoint.value.example: http://localhost:8000/metrics
         openmetrics_endpoint.description: |
-          Endpoint exposing the Nvidia NIM's Prometheus metrics. For more information refer to:
+          Endpoint exposing the NVIDIA NIM's Prometheus metrics. For more information refer to:
           https://docs.nvidia.com/nim/large-language-models/latest/observability.html

nvidia_nim/assets/monitors/latency.json

@@ -3,15 +3,15 @@
     "created_at": "2024-07-02",
     "last_updated_at": "2024-07-02",
     "title": "Average Request Latency is High",
-    "description": "This monitor alerts you if Nvidia NIM request latency is too high. High latency means requests are waiting long to be processed. This results in clients having to wait longer for their requests to complete. It also indicates your Nvidia NIM server is receiving more requests than it can comfortably handle.",
+    "description": "This monitor alerts you if NVIDIA request latency is too high. High latency means requests are waiting long to be processed. This results in clients having to wait longer for their requests to complete. It also indicates your NVIDIA server is receiving more requests than it can comfortably handle.",
     "tags": [
       "integration:nvidia-nim"
     ],
     "definition": {
       "name": "Average request latency is high",
       "type": "query alert",
       "query": "sum(last_15m):sum:nvidia_nim.e2e_request_latency.seconds.sum{*}.as_count() / sum:nvidia_nim.e2e_request_latency.seconds.count{*}.as_count() > 0.3",
-      "message": "The average latency for requests coming into your Nvidia NIM instance is higher than the threshold. This means requests are waiting too long to be processed.",
+      "message": "The average latency for requests coming into your NVIDIA instance is higher than the threshold. This means requests are waiting too long to be processed.",
       "tags": [
         "integration:nvidia_nim"
       ],

nvidia_nim/assets/service_checks.json

@@ -1,7 +1,7 @@
 [    
     {
     "agent_version": "7.61.0",
-    "integration": "Nvidia NIM",
+    "integration": "nvidia_nim",
     "check": "nvidia_nim.openmetrics.health",
     "statuses": [
         "ok",
@@ -11,7 +11,7 @@
         "host",
         "endpoint"
     ],
-    "name": "Nvidia NIM OpenMetrics endpoint health",
-    "description": "Returns `CRITICAL` if the Agent is unable to connect to the Nvidia NIM OpenMetrics endpoint, otherwise returns `OK`."
+    "name": "NVIDIA NIM OpenMetrics endpoint health",
+    "description": "Returns `CRITICAL` if the Agent is unable to connect to the NVIDIA NIM OpenMetrics endpoint, otherwise returns `OK`."
     }
 ]

nvidia_nim/datadog_checks/nvidia_nim/check.py

@@ -42,7 +42,7 @@ def _submit_version_metadata(self):
             }
             self.set_metadata('version', version_raw, scheme='semver', part_map=version_parts)
         else:
-            self.log.debug("Invalid Nvidia NIM release format: %s", version)
+            self.log.debug("Invalid NVIDIA NIM release format: %s", version)
 
     def check(self, instance):
         super().check(instance)

nvidia_nim/datadog_checks/nvidia_nim/data/conf.yaml.example

@@ -46,7 +46,7 @@ init_config:
 instances:
 
     ## @param openmetrics_endpoint - string - required
-    ## Endpoint exposing the Nvidia NIM's Prometheus metrics. For more information refer to:
+    ## Endpoint exposing the NVIDIA NIM's Prometheus metrics. For more information refer to:
     ## https://docs.nvidia.com/nim/large-language-models/latest/observability.html
     #
   - openmetrics_endpoint: http://localhost:8000/metrics

nvidia_nim/datadog_checks/nvidia_nim/metrics.py

@@ -27,7 +27,6 @@
     'request_prompt_tokens': 'request.prompt_tokens',
     'request_success': 'request.success',
     'request_failure': 'request.failure',
-
 }
 
 RENAME_LABELS_MAP = {

nvidia_nim/manifest.json

@@ -43,6 +43,9 @@
         "vllm_nvext.entrypoints.openai.api_server"
       ]
     },
+    "dashboards": {
+      "NVIDIA NIM Overview": "assets/dashboards/nvidia_nim_overview.json"
+    },
     "monitors": {
       "Average Request Latency is High": "assets/monitors/latency.json"
     }