Google Cloud Firebase AI Logic monitoring integration

New Relic integrations with the Google Cloud Platform (GCP) include one that reports Firebase AI Logic (formerly Vertex AI in Firebase) data to New Relic. This document explains how to activate the GCP Firebase AI Logic integration and describes the data it reports.

Features

Firebase AI Logic lets mobile and web apps call Gemini and Imagen models directly from client SDKs, without a custom backend. New Relic Firebase AI Logic integration collects generative AI client telemetry for each model: operation duration, token usage, and per-modality usage counts.

Activate integration

Important

This integration is available only when you connect your GCP project with Workload Identity Federation. It isn't available for service account or user account connections.

To enable the integration, follow standard procedures to connect your GCP service to New Relic with Workload Identity Federation.

Polling frequency

New Relic integrations query your GCP services according to a polling interval that varies by integration. The polling frequency for Firebase AI Logic is 5 minutes. The resolution is 1 data point every minute.

Workload Identity Federation

Find and use data

All Firebase AI Logic model metrics available in GCP Cloud Monitoring are collected as dimensional metrics in the Metric event type.

This integration doesn't create entities in the New Relic entity explorer. Query its metrics directly on the Metric event type, for example:

FROM Metric SELECT count(*) WHERE metricName LIKE 'gcp.firebasevertexai.%' FACET metricName

Metric data

Metric name	Unit	Description
`gcp.firebasevertexai.model.gen_ai_client_operation_duration`	Distribution	The duration from request to response. Google declares this metric as a distribution with a dimensionless unit.
`gcp.firebasevertexai.model.gen_ai_client_token_usage`	Count	The number of tokens used in a request or response.
`gcp.firebasevertexai.model.gen_ai_firebase_modality_count`	Count	The number of times a particular modality is used.
`gcp.firebasevertexai.model.gen_ai_firebase_modality_usage`	Count	The number of tokens used for a particular modality.

gen_ai_client_operation_duration is also available as .p50, .p95, and .p99 percentile metrics.

Conseil

Firebase AI Logic also exposes Prompt Template metrics (render_count and render_latency) on a separate monitored resource. This integration doesn't collect those metrics because they're in preview.

For the complete list, see Google's Firebase AI Logic metrics documentation.