Overview
This guide shows you how to integrate Latitude Telemetry into an existing application that uses the official Google Vertex AI SDK.
After completing these steps:
- Every Google Vertex AI call (e.g.
generateContent) 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 Google Vertex AI-powered features from the Latitude dashboard.
You’ll keep calling Google Vertex AI 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 Google Vertex AI 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
Wrap your Google Vertex AI-powered feature
Initialize Latitude Telemetry and wrap the code that calls Google Vertex AI using telemetry.capture.import { LatitudeTelemetry } from '@latitude-data/telemetry'
import * as VertexAI from '@google-cloud/vertexai'
const telemetry = new LatitudeTelemetry(
process.env.LATITUDE_API_KEY,
{ instrumentations: { vertexai: VertexAI } }
)
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 () => {
const client = new VertexAI.VertexAI({
project: 'your-gcp-project',
location: 'us-central1',
})
const model = client.getGenerativeModel({ model: 'gemini-1.5-pro' })
const result = await model.generateContent(input)
return result.response
}
)
}
You can use the capture method as a decorator (recommended) or as a context manager:Using decorator (recommended)
import os
import vertexai
from vertexai.generative_models import GenerativeModel
from latitude_telemetry import Telemetry, Instrumentors, TelemetryOptions
telemetry = Telemetry(
os.environ["LATITUDE_API_KEY"],
TelemetryOptions(instrumentors=[Instrumentors.VertexAI]),
)
@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:
vertexai.init(project="your-gcp-project", location="us-central1")
model = GenerativeModel("gemini-1.5-pro")
response = model.generate_content(input)
return response.text
import os
import vertexai
from vertexai.generative_models import GenerativeModel
from latitude_telemetry import Telemetry, Instrumentors, TelemetryOptions
telemetry = Telemetry(
os.environ["LATITUDE_API_KEY"],
TelemetryOptions(instrumentors=[Instrumentors.VertexAI]),
)
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
):
vertexai.init(project="your-gcp-project", location="us-central1")
model = GenerativeModel("gemini-1.5-pro")
response = model.generate_content(input)
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 Google Vertex AI 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 Google Vertex AI calls, no special return values, and no extra plumbing — just wrap the feature you want to observe.
