Overview
This guide shows you how to integrate Latitude Telemetry into an existing application that uses the official Gemini SDK (google-genai).
After completing these steps:
- Every Gemini call (e.g.
generate_content) can be captured as a log in Latitude.
- Logs are grouped under a prompt, identified by a
path, inside a Latitude project.
- You can inspect inputs/outputs, measure latency, and debug your Gemini-powered features from the Latitude dashboard.
You’ll keep calling Gemini exactly as you do today — Telemetry simply observes
and enriches those calls.
Requirements
Before you start, make sure you have:
- A Latitude account and API key
- A Latitude project ID
- A Node.js or Python-based project that uses the Gemini SDK
That’s it — prompts do not need to be created ahead of time.
Steps
Install requirements
Add the Latitude Telemetry package to your project:npm add @latitude-data/telemetry
pip install latitude-telemetry
Initialize Latitude Telemetry
Create a single Telemetry instance when your app starts.You must enable the GoogleGenerativeAI instrumentor so Telemetry can trace Gemini calls automatically.import { LatitudeTelemetry, Instrumentors } from '@latitude-data/telemetry'
export const telemetry = new LatitudeTelemetry(process.env.LATITUDE_API_KEY, {
instrumentors: [Instrumentors.GoogleGenerativeAI], // This enables automatic tracing for Gemini
})
import os
from latitude_telemetry import Telemetry, Instrumentors, TelemetryOptions
telemetry = Telemetry(
os.environ["LATITUDE_API_KEY"],
TelemetryOptions(
instrumentors=[Instrumentors.GoogleGenerativeAI], # This enables automatic tracing for Gemini
),
)
The Telemetry instance should only be created once. Initialize it
before importing from google-genai so Gemini calls are
automatically traced.
Wrap your Gemini-powered feature
Wrap the code that calls Gemini using telemetry.capture.import { GoogleGenerativeAI } from '@google/generative-ai'
import { telemetry } from './telemetry'
export async function generateSupportReply(input: string) {
return telemetry.capture(
{
projectId: 123, // The ID of your project in Latitude
path: 'generate-support-reply', // Add a path to identify this prompt in Latitude
},
async () => {
// Your regular LLM-powered feature code here
const genAI = new GoogleGenerativeAI(process.env.GEMINI_API_KEY)
const model = genAI.getGenerativeModel({ model: 'gemini-2.0-flash' })
const result = await model.generateContent(input)
// You can return anything you want — the value is passed through unchanged
return result.response.text()
}
)
}
You can use the capture method as a decorator (recommended) or as a context manager:Using decorator (recommended)
import os
from telemetry import telemetry
from google import genai
@telemetry.capture(
project_id=123, # The ID of your project in Latitude
path="generate-support-reply", # Add a path to identify this prompt in Latitude
)
def generate_support_reply(input: str) -> str:
client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])
response = client.models.generate_content(
model="gemini-2.0-flash",
contents=input,
)
# You can return anything you want — the value is passed through unchanged
return response.text
import os
from telemetry import telemetry
from google import genai
def generate_support_reply(input: str) -> str:
with telemetry.capture(
project_id=123, # The ID of your project in Latitude
path="generate-support-reply", # Add a path to identify this prompt in Latitude
):
client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])
response = client.models.generate_content(
model="gemini-2.0-flash",
contents=input,
)
# You can return anything you want — the value is passed through unchanged
return response.text
The path:
- Identifies the prompt in Latitude
- Can be new or existing
- Should not contain spaces or special characters (use letters, numbers,
- _ / .)
Seeing your logs in Latitude
Once your feature is wrapped, logs will appear automatically.
- Open the prompt in your Latitude dashboard (identified by
path)
- Go to the Traces section
- Each execution will show:
- Input and output messages
- Model and token usage
- Latency and errors
- One trace per feature invocation
Each Gemini call appears as a child span under the captured prompt execution, giving you a full, end-to-end view of what happened.
That’s it
No changes to your Gemini calls, no special return values, and no extra plumbing — just wrap the feature you want to observe.
