Skip to technology filters Skip to main content
Dynatrace Hub

Extend the platform,
empower your team.

Popular searches:
Home hero bg
Google Vertex AIGoogle Vertex AI
Google Vertex AI

Google Vertex AI

Get insights into Google Vertex AI service metrics.

Extension
Free trial
  • Product information
  • Release notes

Overview

This Dynatrace extension leverages data collected from the Google Operations API to constantly monitor health and performance of Google Vertex AI services.

This is intended for users who want to:

  • Enrich their monitoring data with metrics and logs from Google Operations API

This enables you to:

  • View and analyze metrics that are specific to Google Vertex AI, like Accelerator memory utilization, Memory utilization, CPU utilization, and more.

  • Analyze Google AI Platform logs.

Google AI Platform metric and log ingestion requires advanced GCP integration.

Compatibility requirements:

  • Dynatrace GCP integration version 1.0.0+. To enable metric and log ingestion, see Dynatrace Documentation.
  • Dynatrace version 1.230+
Dynatrace
By Dynatrace
Dynatrace support center
Subscribe to new releases
Copy to clipboard

Extension content

Content typeNumber of items included
generic type
11
metric metadata
95
generic relationship
10

Feature sets

Below is a complete list of the feature sets provided in this version. To ensure a good fit for your needs, individual feature sets can be activated and deactivated by your administrator during configuration.

Feature setsNumber of metrics included
Metric nameMetric keyDescriptionUnit
Accelerator duty cyclecloud.gcp.aiplatform_googleapis_com.prediction.online.deployment_resource_pool.accelerator.duty_cycle-Percent
Accelerator memory usagecloud.gcp.aiplatform_googleapis_com.prediction.online.deployment_resource_pool.accelerator.memory.bytes_used-Byte
CPU utilizationcloud.gcp.aiplatform_googleapis_com.prediction.online.deployment_resource_pool.cpu.utilization-Percent
Memory usagecloud.gcp.aiplatform_googleapis_com.prediction.online.deployment_resource_pool.memory.bytes_used-Byte
Network bytes receivedcloud.gcp.aiplatform_googleapis_com.prediction.online.deployment_resource_pool.network.received_bytes_count-Byte
Network bytes sentcloud.gcp.aiplatform_googleapis_com.prediction.online.deployment_resource_pool.network.sent_bytes_count-Byte
Replica countcloud.gcp.aiplatform_googleapis_com.prediction.online.deployment_resource_pool.replicas-Count
Replica targetcloud.gcp.aiplatform_googleapis_com.prediction.online.deployment_resource_pool.target_replicas-Count
Accelerator duty cyclecloud.gcp.aiplatform_googleapis_com.prediction.online.accelerator.duty_cycle-Percent
Accelerator memory usagecloud.gcp.aiplatform_googleapis_com.prediction.online.accelerator.memory.bytes_used-Byte
CPU utilizationcloud.gcp.aiplatform_googleapis_com.prediction.online.cpu.utilization-Percent
Number of online prediction errorscloud.gcp.aiplatform_googleapis_com.prediction.online.error_count-Count
Memory usagecloud.gcp.aiplatform_googleapis_com.prediction.online.memory.bytes_used-Byte
Network bytes receivedcloud.gcp.aiplatform_googleapis_com.prediction.online.network.received_bytes_count-Byte
Network bytes sentcloud.gcp.aiplatform_googleapis_com.prediction.online.network.sent_bytes_count-Byte
Number of online predictionscloud.gcp.aiplatform_googleapis_com.prediction.online.prediction_count-Count
Prediction latenciescloud.gcp.aiplatform_googleapis_com.prediction.online.prediction_latencies-MilliSecond
Private endpoint prediction latenciescloud.gcp.aiplatform_googleapis_com.prediction.online.private.prediction_latencies-MilliSecond
Private endpoint response countcloud.gcp.aiplatform_googleapis_com.prediction.online.private.response_count-Count
Replica countcloud.gcp.aiplatform_googleapis_com.prediction.online.replicas-Count
Response countcloud.gcp.aiplatform_googleapis_com.prediction.online.response_count-Count
Replica targetcloud.gcp.aiplatform_googleapis_com.prediction.online.target_replicas-Count
Executing PipelineJobscloud.gcp.aiplatform_googleapis_com.executing_vertexai_pipeline_jobs-Count
Executing PipelineTaskscloud.gcp.aiplatform_googleapis_com.executing_vertexai_pipeline_tasks-Count
Generate content requests per minute per project per base modelcloud.gcp.aiplatform_googleapis_com.generate_content_requests_per_minute_per_project_per_base_model-Count
Online prediction dedicated requests per base model versioncloud.gcp.aiplatform_googleapis_com.online_prediction_dedicated_requests_per_base_model_version-Count
Online prediction dedicated tokens per minute per base model versioncloud.gcp.aiplatform_googleapis_com.online_prediction_dedicated_tokens_per_base_model_version-Count
Online prediction requests per base modelcloud.gcp.aiplatform_googleapis_com.online_prediction_requests_per_base_model-Count
Online prediction tokens per minute per base modelcloud.gcp.aiplatform_googleapis_com.online_prediction_tokens_per_minute_per_base_model-Count
Generate content requests per minute per project per base model quota exceeded errorcloud.gcp.aiplatform_googleapis_com.quota.generate_content_requests_per_minute_per_project_per_base_model.exceeded-Count
Generate content requests per minute per project per base model quota limitcloud.gcp.aiplatform_googleapis_com.quota.generate_content_requests_per_minute_per_project_per_base_model.limit-Count
Generate content requests per minute per project per base model quota usagecloud.gcp.aiplatform_googleapis_com.quota.generate_content_requests_per_minute_per_project_per_base_model.usage-Count
Online prediction dedicated requests per base model version quota exceeded errorcloud.gcp.aiplatform_googleapis_com.quota.online_prediction_dedicated_requests_per_base_model_version.exceeded-Count
Online prediction dedicated requests per base model version quota limitcloud.gcp.aiplatform_googleapis_com.quota.online_prediction_dedicated_requests_per_base_model_version.limit-Count
Online prediction dedicated requests per base model version quota usagecloud.gcp.aiplatform_googleapis_com.quota.online_prediction_dedicated_requests_per_base_model_version.usage-Count
Online prediction dedicated tokens per minute per base model version quota exceeded errorcloud.gcp.aiplatform_googleapis_com.quota.online_prediction_dedicated_tokens_per_base_model_version.exceeded-Count
Online prediction dedicated tokens per minute per base model version quota limitcloud.gcp.aiplatform_googleapis_com.quota.online_prediction_dedicated_tokens_per_base_model_version.limit-Count
Online prediction dedicated tokens per minute per base model version quota usagecloud.gcp.aiplatform_googleapis_com.quota.online_prediction_dedicated_tokens_per_base_model_version.usage-Count
Online prediction requests per base model quota exceededcloud.gcp.aiplatform_googleapis_com.quota.online_prediction_requests_per_base_model.exceeded-Count
Online prediction requests per base model quota limitcloud.gcp.aiplatform_googleapis_com.quota.online_prediction_requests_per_base_model.limit-Count
Online prediction requests per base model quota usagecloud.gcp.aiplatform_googleapis_com.quota.online_prediction_requests_per_base_model.usage-Count
Online prediction tokens per minute per base model quota exceededcloud.gcp.aiplatform_googleapis_com.quota.online_prediction_tokens_per_minute_per_base_model.exceeded-Count
Online prediction tokens per minute per base model quota limitcloud.gcp.aiplatform_googleapis_com.quota.online_prediction_tokens_per_minute_per_base_model.limit-Count
Online prediction tokens per minute per base model quota usagecloud.gcp.aiplatform_googleapis_com.quota.online_prediction_tokens_per_minute_per_base_model.usage-Count
Character countcloud.gcp.aiplatform_googleapis_com.publisher.online_serving.character_count-Count
Characterscloud.gcp.aiplatform_googleapis_com.publisher.online_serving.characters-Count
Character Throughputcloud.gcp.aiplatform_googleapis_com.publisher.online_serving.consumed_throughput.count-Count
First token latenciescloud.gcp.aiplatform_googleapis_com.publisher.online_serving.first_token_latencies-MilliSecond
Model invocation countcloud.gcp.aiplatform_googleapis_com.publisher.online_serving.model_invocation_count-Count
Model invocation latenciescloud.gcp.aiplatform_googleapis_com.publisher.online_serving.model_invocation_latencies-MilliSecond
Token countcloud.gcp.aiplatform_googleapis_com.publisher.online_serving.token_count-Count
Tokenscloud.gcp.aiplatform_googleapis_com.publisher.online_serving.tokens-Count
Metric nameMetric keyDescriptionUnit
PipelineJob durationcloud.gcp.aiplatform_googleapis_com.pipelinejob.duration-Second
Completed PipelineTaskscloud.gcp.aiplatform_googleapis_com.pipelinejob.task_completed_count-Count
Metric nameMetric keyDescriptionUnit
Request countcloud.gcp.visionai_googleapis_com.platform.connected_service.request_count-Count
Request latenciescloud.gcp.visionai_googleapis_com.platform.connected_service.request_latencies-MilliSecond
Prediction countcloud.gcp.visionai_googleapis_com.platform.custom_model.predict_count-Count
Prediction latenciescloud.gcp.visionai_googleapis_com.platform.custom_model.predict_latencies-MilliSecond
Uptimecloud.gcp.visionai_googleapis_com.platform.instance.uptime-MilliSecond
Received bytescloud.gcp.visionai_googleapis_com.stream.network.received_bytes_count-Byte
Received packetscloud.gcp.visionai_googleapis_com.stream.network.received_packets_count-Count
Sent bytescloud.gcp.visionai_googleapis_com.stream.network.sent_bytes_count-Byte
Sent packetscloud.gcp.visionai_googleapis_com.stream.network.sent_packets_count-Count
Metric nameMetric keyDescriptionUnit
Datapoint countcloud.gcp.aiplatform_googleapis_com.matching_engine.stream_update.datapoint_count-Count
Stream update latenciescloud.gcp.aiplatform_googleapis_com.matching_engine.stream_update.latencies-MilliSecond
Request countcloud.gcp.aiplatform_googleapis_com.matching_engine.stream_update.request_count-Count
CPU request utilizationcloud.gcp.aiplatform_googleapis_com.matching_engine.cpu.request_utilization-Percent
Current replicascloud.gcp.aiplatform_googleapis_com.matching_engine.current_replicas-Count
Current shardscloud.gcp.aiplatform_googleapis_com.matching_engine.current_shards-Count
Memory usagecloud.gcp.aiplatform_googleapis_com.matching_engine.memory.used_bytes-Byte
Request latencycloud.gcp.aiplatform_googleapis_com.matching_engine.query.latencies-MilliSecond
Request countcloud.gcp.aiplatform_googleapis_com.matching_engine.query.request_count-Count
Metric nameMetric keyDescriptionUnit
Request countcloud.gcp.aiplatform_googleapis_com.featureonlinestore.online_serving.request_count-Count
Response bytes countcloud.gcp.aiplatform_googleapis_com.featureonlinestore.online_serving.serving_bytes_count-Count
Request latencycloud.gcp.aiplatform_googleapis_com.featureonlinestore.online_serving.serving_latencies-MilliSecond
Running sycscloud.gcp.aiplatform_googleapis_com.featureonlinestore.running_sync-Count
Serving data agescloud.gcp.aiplatform_googleapis_com.featureonlinestore.serving_data_ages-Second
Serving data by synced timecloud.gcp.aiplatform_googleapis_com.featureonlinestore.serving_data_by_sync_time-Count
CPU loadcloud.gcp.aiplatform_googleapis_com.featureonlinestore.storage.bigtable_cpu_load-Percent
CPU load (hottest node)cloud.gcp.aiplatform_googleapis_com.featureonlinestore.storage.bigtable_cpu_load_hottest_node-Percent
Node countcloud.gcp.aiplatform_googleapis_com.featureonlinestore.storage.bigtable_nodes-Count
Optimized node countcloud.gcp.aiplatform_googleapis_com.featureonlinestore.storage.optimized_nodes-Count
Bytes storedcloud.gcp.aiplatform_googleapis_com.featureonlinestore.storage.stored_bytes-Byte
CPU loadcloud.gcp.aiplatform_googleapis_com.featurestore.cpu_load-Percent
CPU load (hottest node)cloud.gcp.aiplatform_googleapis_com.featurestore.cpu_load_hottest_node-Percent
Node countcloud.gcp.aiplatform_googleapis_com.featurestore.node_count-Count
Entities updated on the Featurestore online storagecloud.gcp.aiplatform_googleapis_com.featurestore.online_entities_updated-Byte
Latenciescloud.gcp.aiplatform_googleapis_com.featurestore.online_serving.latencies-MilliSecond
Request sizecloud.gcp.aiplatform_googleapis_com.featurestore.online_serving.request_bytes_count-Byte
Serving countcloud.gcp.aiplatform_googleapis_com.featurestore.online_serving.request_count-Count
Response sizecloud.gcp.aiplatform_googleapis_com.featurestore.online_serving.response_size-Byte
Billable bytescloud.gcp.aiplatform_googleapis_com.featurestore.storage.billable_processed_bytes-Byte
Bytes storedcloud.gcp.aiplatform_googleapis_com.featurestore.storage.stored_bytes-Byte
Offline storage write for streaming writecloud.gcp.aiplatform_googleapis_com.featurestore.streaming_write.offline_processed_count-Count
Streaming write to offline storage delay timecloud.gcp.aiplatform_googleapis_com.featurestore.streaming_write.offline_write_delays-Second

Full version history

To have more information on how to install the downloaded package, please follow the instructions on this page.
ReleaseDate

Full version history

Version 1.0.0

Updated

  • Created new extension for Vertex AI platform.
Dynatrace Hub
Hub HomeGet data into DynatraceBuild your own app
Log Management and AnalyticsKubernetesAI and LLM ObservabilityInfrastructure ObservabilitySoftware DeliveryApplication ObservabilityApplication SecurityDigital ExperienceBusiness Observability
Filter
Type
Built and maintained by
Deployment model
SaaS
  • SaaS
  • Managed
Partner FinderBecome a partnerDynatrace Developer

All

194 Results filtered by:

Palo Alto firewalls logo

Palo Alto firewalls

Palo Alto extension for problems detection

Extension
Confluent Cloud (Kafka) logo

Confluent Cloud (Kafka)

Remotely monitor your Confluent Cloud Kafka Clusters and other resources!

Extension
Kong - Prometheus logo

Kong - Prometheus

Monitor Prometheus metrics exposed by Kong and proxied upstream services

Extension
Nutanix Clusters logo

Nutanix Clusters

Monitor Nutanix clusters' performance, usage and availability, with Nutanix API.

Extension
Luna Network HSM Device logo

Luna Network HSM Device

Monitor your Luna Network Hardware Security Module (HSM) Devices through SNMP.

Extension
Consul Service Mesh (StatsD) logo

Consul Service Mesh (StatsD)

Extend visibility into your Consul Service Mesh instances to monitor health and improve performance.

Extension
Microsoft IIS logo

Microsoft IIS

Flexible and secure web server for hosting with Windows Server.

Extension
Kubernetes Monitoring Statistics logo

Kubernetes Monitoring Statistics

Troubleshoot your Dynatrace Kubernetes monitoring and Prometheus integration.

Extension
Snyk logo

Snyk

Ingest Snyk vulnerability findings, scans, and audit logs.

Extension
Citrix DaaS & Virtual Apps and Desktops logo

Citrix DaaS & Virtual Apps and Desktops

Gain insight into your Citrix DaaS & Virtual Apps and Desktops environments

Extension
Google Memorystore logo

Google Memorystore

Get insights into Google Memorystore service metrics collected from the Google Operations API to ensure health of your cloud infrastructure.

Extension
Databricks Workspace logo

Databricks Workspace

Remotely monitor your Databricks Workspaces!

Extension
Uptime logo

Uptime

Monitor the uptime of your hosts

Extension
UPS Device logo

UPS Device

Monitor your Uninterruptible Power Supplies (UPS) over SNMP

Extension
Google App Engine (integration) logo

Google App Engine (integration)

Insights into Google App Engine service metrics collected from Operations API

Extensioncoming soon
Traceroute logo

Traceroute

Run traceroute commands and collect step performance metrics

Extension
[Deprecated] Kubernetes PVCs logo

[Deprecated] Kubernetes PVCs

Monitor your Kubernetes persistent volume claims and alert on capacity limits.

Extension
Google Cloud Storage Transfer logo

Google Cloud Storage Transfer

Get insights into Google Cloud Storage Transfer metrics collected from the Google Operations API to ensure health of cloud infrastructure.

Extension
NVIDIA GPU logo

NVIDIA GPU

Monitor base parameters of the GPU, including load, memory and temperature

Extension
Oracle Database logo

Oracle Database

Observe, analyze and optimize the usage, health and performance of your database

Extension
Cisco ACI/APIC logo

Cisco ACI/APIC

Get insights into your Cisco Application Centric Infrastructure (ACI)

Extension
Dell iDRAC logo

Dell iDRAC

Connect to the Redfish API to get insights into your Dell iDRAC environment

Extension
Azure Managed Apache Cassandra logo

Azure Managed Apache Cassandra

Gain insights into your Azure Managed Cassandra Instance health and performance

Extension
PayShield HSM Device logo

PayShield HSM Device

Monitor PayShield Payment Hardware Security Module (HSM) Devices through SNMP.

Extension
NetApp OnTap (Remote) logo

NetApp OnTap (Remote)

Remote extension that collects NetApp OnTap metrics from the OnTap 9.6+ API.

Extension
Google Firestore in Datastore mode logo

Google Firestore in Datastore mode

Get insights into Google Firestore in Datastore mode metrics collected from the Google Operations API to ensure health of infrastructure.

Extension
Redis (2.0) logo

Redis (2.0)

Collect important additional data for your Redis instances.

Extension
PHP-FPM logo

PHP-FPM

Monitor the PHP-FPM status of your applications with this extension.

Extension
Timedrift Monitoring logo

Timedrift Monitoring

Monitor your host's NTP/Chrony Time Offset!

Extension
Apache Kafka logo

Apache Kafka

Automatic and intelligent observability with trace and metric insights.

Extension
MongoDB (local or remote monitoring) logo

MongoDB (local or remote monitoring)

Monitor your MongoDB servers either locally or remotely!

Extension
Connection Pools: C3P0 logo

Connection Pools: C3P0

Application server method of pooling and sharing connections to a database.

Extension
AWS Entities for Metric Streaming logo

AWS Entities for Metric Streaming

Analyse metrics in the context of an entity based on AWS Metric Streaming.

Extension
MongoDB Atlas logo

MongoDB Atlas

Remotely monitor your SaaS installation of MongoDB (Atlas)

Extension
Microsoft SQL Server logo

Microsoft SQL Server

Improve the health and performance monitoring of your Microsoft SQL Servers.

Extension
IBM MQ Appliance logo

IBM MQ Appliance

Monitor your IBM MQ Appliances over SNMP

Extension
Google Apigee logo

Google Apigee

Get insights into Google Apigee service metrics collected from the Google Operations API to ensure health of your cloud infrastructure.

Extension
Oracle Autonomous Database on OCI logo

Oracle Autonomous Database on OCI

Monitor health and performance of the Oracle Autonomous Database.

Extension
Google Pub/Sub Lite logo

Google Pub/Sub Lite

Get insights into Google Pub/Sub Lite service metrics collected from the Google Operations API to ensure health of the cloud infrastructure.

Extension
Infoblox DDI logo

Infoblox DDI

Monitor Infoblox DDI using SNMP

Extension
SAP HANA Database (remote monitoring) logo

SAP HANA Database (remote monitoring)

Easily understand the health and performance of your SAP HANA databases.

Extension
Connection Pools: WebSphere Liberty logo

Connection Pools: WebSphere Liberty

Application server method of pooling and sharing connections to a database.

Extension
Google Cloud Composer logo

Google Cloud Composer

Get insights into Google Cloud Composer metrics collected from the Google Operations API to ensure health of your cloud infrastructure.

Extension
Google Cloud Spanner logo

Google Cloud Spanner

Get insights into Google Cloud Spanner metrics collected from the Google Operations API to ensure health of your cloud infrastructure.

Extension
IBM i logo

IBM i

Collect performance data from your IBM i Hosts via this Remote extension.

Extension
Google reCAPTCHA Enterprise logo

Google reCAPTCHA Enterprise

Get insights into Google reCAPTCHA Enterprise metrics collected from the Google Operations API to ensure health of your cloud infrastructure

Extension
.NET logo

.NET

Automatic end-to-end observability for .NET applications and processes.

Extension
Google Cloud's operations suite logo

Google Cloud's operations suite

Get insights into Google Cloud's operations suite metrics collected from the Google Operations API to ensure health of cloud infrastructure.

Extension
Google Vertex AI logo

Google Vertex AI

Get insights into Google Vertex AI service metrics.

Extension
Oracle Exadata logo

Oracle Exadata

Monitor Oracle Exadata systems for performance, usage and availability

Extension