Configure your Splunk Observability Cloud account to collect GCP VertexAI metrics
Learn how to configure your Splunk Observability Cloud account to collect GCP VertexAI metrics.
You can monitor the performance of Google Cloud Platform (GCP) VertexAI applications by configuring your GCP VertexAI applications to send metrics to Splunk Observability Cloud. This solution creates a cloud connection in your Splunk Observability Cloud account that collects metrics from Google Cloud Monitoring.
Complete the following steps to collect metrics from GCP VertexAI.
- Connect GCP to Splunk Observability Cloud. For more information on the connection methods and instructions for each method, see Connect to Google Cloud Platform.
- To monitor GCP VertexAI metrics with Splunk Observability Cloud, run your applications that use GCP VertexAI models.
メトリクス
GCP VertexAI で使用可能なメトリクスについて確認します。
| メトリクス名 | ユニット(Units) | 説明 |
|---|---|---|
prediction/online /prediction_count | count | オンライン予想の数。 |
prediction/online /prediction_latencies | ミリ秒 | 展開モデルのオンライン予測遅延。 |
prediction/online /response_count | count | オンライン予測で返された異なるレスポンスコードの数。 |
prediction/online /prediction_latencies.count | count | オンライン予想の数。 |
prediction/online /prediction_latencies.sumOfSquareDeviation | ミリ秒 | 予測遅延の偏差平方和。 |
publisher/online_serving /model_invocation_count | count | モデル呼び出し(予測要求)の数。 |
publisher/online_serving /model_invocation_latencies.sumOfSquareDeviation | ミリ秒 | モデル呼び出し遅延の偏差平方和。 |
publisher/online_serving /model_invocation_latencies.count | count | モデル呼び出し(予測要求)の数。 |
publisher/online_serving /model_invocation_latencies | ミリ秒 | モデル呼び出しの遅延(予測遅延)。 |
publisher/online_serving /token_count | count | 累積入出力トークン数。 |
publisher/online_serving /consumed_token_throughput | count | トークンに基づく全体使用スループット(損失率を考慮)。 |
publisher/online_serving /consumed_throughput | count | 文字数に基づく全体使用スループット(損失率を考慮)。 |
publisher/online_serving /character_count | count | 累積入出力文字数。 |
publisher/online_serving /first_token_latencies | ミリ秒 | 要求を受信してから、クライアントに最初のトークンが返されるまでの時間。 |
publisher/online_serving /first_token_latencies.count | count | 最初のトークンの遅延数。 |
publisher/online_serving /first_token_latencies.sumOfSquareDeviation | ミリ秒 | 最初のトークン遅延の偏差平方和。 |
属性
GCP VertexAI で使用可能なリソース属性について確認します。
gcp_project_statusgcp_project_namegcp_project_label_last_revalidated_bymodel_user_idgcp_project_numberrequest_typegcp_idgcp_project_label_cloud_registration_idgcp_project_creation_timegcp_project_label_last_revalidated_atinput_token_sizeoutput_token_sizeproject_idmetricTypeDomaingcp_project_label_environmentpublishermonitored_resourcegcp_project_label_account_typegcp_project_label_owner_groupserviceLocation
type のリソース属性は publisher/online_serving /token_count および publisher/online_serving /character_count メトリクスでも使用可能です。
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.
| Monitoring tool | Use this tool to | Link to documentation |
|---|---|---|
| Built-in navigators | Orient and explore different layers of your AI tech stack. | |
| Built-in dashboards | Assess service, endpoint, and system health at a glance. | |
| Splunk Application Performance Monitoring (APM) service map and trace view | View all of your LLM service dependency graphs and user interactions in the service map or trace view. |