This quickstart guide describes how to set up Genkit Monitoring foryour deployed Genkit features, so that you can collect and view real-timetelemetry data. With Genkit Monitoring, you get visibility into howyour Genkit features are performing in production.

Key capabilities of Genkit Monitoring include:

• Viewing quantitative metrics like Genkit feature latency, errors, andtoken usage.
• Inspecting traces to see your Genkit’s feature steps, inputs, and outputs,to help with debugging and quality improvement.
• Exporting production traces to run evals within Genkit.

Setting up Genkit Monitoring requires completing tasks in both your codebaseand on the Google Cloud Console.

1. If you haven’t already, create a Firebase project.

   In theFirebase console, clickAdd a project, then follow the on-screen instructions. You cancreate a new project or add Firebase services to an already-existing Google Cloud project.

2. Ensure your project is on theBlaze pricing plan.

   Genkit Monitoring relies on telemetry data written to Google CloudLogging, Metrics, and Trace, which are paid services. View theGoogle Cloud Observability pricing page for pricing details and to learn about free-of-charge tier limits.

3. Write a Genkit feature by following theGet Started Guide, and prepare your code for deployment by using one of the following guides:

a.Deploy flows using Cloud Functions for Firebaseb.Deploy flows using Cloud Runc.Deploy flows to any Node.js platform

a.Deploy flows using Cloud Run

Step 1. Add the Firebase plugin

Install the@genkit-ai/firebase plugin in your project:

npminstall@genkit-ai/firebase

Environment-based configuration

If you intend to use the default configuration for Firebase GenkitMonitoring, you can enable telemetry by setting theENABLE_FIREBASE_MONITORING environment variable in your deploymentenvironment.

export ENABLE_FIREBASE_MONITORING=true

Programmatic configuration

You can also enable Firebase Genkit Monitoring in code. This is usefulif you want to tweak any configuration settings like the metric exportinterval or to set up your local environment to export telemetry data.

ImportenableFirebaseTelemetry into your Genkit configuration file (thefile wheregenkit(...) is initalized), and call it:

import { enableFirebaseTelemetry }from'@genkit-ai/firebase';
enableFirebaseTelemetry();

You can also enable Firebase Genkit Monitoring in code. This is usefulif you want to tweak any configuration settings like the metric exportinterval or to set up your local environment to export telemetry data.

packagemain
import (
"context"
"github.com/firebase/genkit/go/genkit"
"github.com/firebase/genkit/go/plugins/firebase"
)
funcmain() {
ctx:= context.Background()
firebase.EnableFirebaseTelemetry(nil)
g:= genkit.Init(ctx,nil)
}

Step 2. Enable the required APIs

Step 3. Set up permissions

Step 4. (Optional) Test your configuration locally

1. In your Genkit code, setforceDevExport totrue to send telemetry fromyour local environment.

1. In your Genkit code, setForceDevExport totrue to send telemetry fromyour local environment.

Re-build, deploy, and invoke your Genkit feature to start collecting data.After Genkit Monitoring receives your metrics, you can view them byvisiting theGenkit Monitoring dashboard