Skip to main content

​
Overview

This guide shows you how to integrate Latitude Telemetry into an application that uses the Google Gemini Developer API (google-genai).
You’ll keep calling Gemini exactly as you do today. Telemetry simply observes and enriches those calls.
Auto-instrumentation for Gemini is available in the Python SDK. For other languages, send traces via the OpenTelemetry exporter.
Using Vertex AI or Google Cloud AI Platform instead of the Gemini Developer API? See Vertex AI or Google AI Platform.

​
Requirements

  • A Latitude account and API key
  • A Latitude project slug
  • A project that uses the Gemini SDK (google-genai)
  • A Gemini API key (set as GEMINI_API_KEY)

​
Steps

1

Install

pip install latitude-telemetry google-genai
2

Initialize and use

import os

from google import genai

from latitude_telemetry import Latitude, capture

latitude = Latitude(
    api_key="your-api-key",
    project="your-project-slug",
    instrumentations={"google_generativeai": genai},
)

client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])

def generate_reply():
    response = client.models.generate_content(
        model="gemini-2.0-flash",
        contents="Hello",
    )
    return response.text

capture("generate-reply", generate_reply)

latitude.shutdown()

​
Seeing Your Traces

Once connected, traces appear automatically in Latitude:
  1. Open your project in the Latitude dashboard
  2. Each execution shows input/output messages, model, token usage, latency, and errors