Configure your Splunk Observability Cloud account to collect Azure OpenAI metrics

Learn how to configure your Splunk Observability Cloud account to collect Azure OpenAI metrics.

You can monitor the performance of Azure OpenAI applications by configuring your Azure OpenAI applications to send metrics to Splunk Observability Cloud. This solution creates a cloud connection in your Splunk Observability Cloud account that collects metrics from Azure application insights.

Complete the following steps to collect metrics from your Azure OpenAI applications.

  1. Connect Azure to Splunk Observability Cloud. For more information on the connection methods and instructions for each method, see Available options to connect with Azure.
    Note: If you connect with Azure using the guided setup, the Select the data to import page includes the option to import data from All Azure services or Specified Azure services only. If you select Specified Azure services only, select Cognitive Services from the Specified services drop-down menu to ensure that Azure OpenAI metrics are ingested.
  2. To monitor Azure OpenAI metrics with Splunk Observability Cloud, run your applications that use Azure OpenAI models.

メトリクスと属性

Azure OpenAI で使用可能なメトリクスを確認します。

Azure OpenAI アプリケーションでは以下のメトリクス、リソース属性が利用できます。
メトリクス名タイプユニット（Units）説明ディメンション
ProcessedPromptTokenscountercountOpenAI モデルで処理された（入力）プロンプトトークンの数。

  • ApiName

  • ModelDeploymentName

  • FeatureName

  • UsageChannel

  • Region

  • ModelVersion

GeneratedTokens

counter

countOpenAI モデルで生成（出力）されたトークンの数。

  • ApiName

  • ModelDeploymentName

  • FeatureName

  • UsageChannel

  • Region

  • ModelVersion

AzureOpenAIRequestscountercountAzure OpenAI サービスへの呼び出し数。

  • ApiName

  • OperationName

  • Region

  • ModelDeploymentName

  • ModelName

  • ModelVersion

  • StatusCode

AzureOpenAITimeToResponseヒストグラムミリ秒ユーザーがプロンプトを送信してから最初の応答が表示されるまでにかかった時間。

  • ApiName

  • OperationName

  • Region

  • ModelDeploymentName

  • ModelName

  • ModelVersion

  • StatusCode

AzureOpenAIAvailabilityRategaugepercent次の計算式で求められる可用性の割合：（総呼び出し数 - サーバーエラー数）÷ 総呼び出し数サーバーエラーには 500 秒以上の HTTP 応答が含まれます。

  • ApiName

  • OperationName

  • Region

  • ModelDeploymentName

  • ModelName

  • ModelVersion

  • StatusCode

AzureOpenAITokenPerSecond

gaugecount特定の Azure OpenAI モデル応答の生成速度。

  • Region

  • ModelDeploymentName

  • ModelName

  • ModelVersion

AzureOpenAIContextTokensCacheMatchRategaugepercentキャッシュに到達したプロンプトトークンの割合。

  • Region

  • ModelDeploymentName

  • ModelName

  • ModelVersion

Next steps

How to monitor your AI components after you set up Observability for AI.

After you set up data collection from supported AI components to Splunk Observability Cloud, the data populates built-in experiences that you can use to monitor and troubleshoot your AI components.

The following table describes the tools you can use to monitor and troubleshoot your AI components.
Monitoring toolUse this tool toLink to documentation
Built-in navigatorsOrient and explore different layers of your AI tech stack.
Built-in dashboardsAssess service, endpoint, and system health at a glance.
Splunk Application Performance Monitoring (APM) service map and trace viewView all of your LLM service dependency graphs and user interactions in the service map or trace view.

Splunk APM を使用して LLM サービスをモニタリングする