Vertex AI

Connect your Vertex AI-powered application to Latitude for observability.

Work in progress: Telemetry documentation is still being updated. Integration steps and APIs may be incomplete or out of date. Verify against your SDK versions and check back for revisions.

Overview

This guide shows you how to integrate Latitude Telemetry into an application that uses Google Cloud Vertex AI.

You’ll keep calling Vertex AI exactly as you do today. Telemetry simply observes and enriches those calls.

---

Requirements

• A Latitude account and API key
• A Latitude project slug
• A project that uses the Vertex AI SDK

---

Steps

1. Install

   TypeScript

   npm

   npm install @latitude-data/telemetry
   

   Python

   pip

   pip install latitude-telemetry
   
2. Initialize and use

   TypeScript

   import { initLatitude, capture } from "@latitude-data/telemetry"
   import { VertexAI } from "@google-cloud/vertexai"
   
   const latitude = initLatitude({
     apiKey: process.env.LATITUDE_API_KEY!,
     projectSlug: process.env.LATITUDE_PROJECT_SLUG!,
     instrumentations: ["vertexai"],
   })
   
   await latitude.ready
   
   const vertexAI = new VertexAI({
     project: process.env.GCP_PROJECT_ID!,
     location: "us-central1",
   })
   const model = vertexAI.getGenerativeModel({ model: "gemini-1.5-flash" })
   
   await capture("generate-reply", async () => {
     const result = await model.generateContent("Hello")
     return result.response.candidates?.[0].content.parts[0].text
   })
   
   await latitude.shutdown()
   

   Python

   from latitude_telemetry import init_latitude, capture
   import vertexai
   from vertexai.generative_models import GenerativeModel
   
   latitude = init_latitude(
       api_key="your-api-key",
       project_slug="your-project-slug",
       instrumentations=["vertexai"],
   )
   
   vertexai.init(project="your-gcp-project", location="us-central1")
   model = GenerativeModel("gemini-1.5-flash")
   
   def generate_reply():
       response = model.generate_content("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

---

That’s It

No changes to your Vertex AI calls: just initialize Latitude and your LLM calls are traced.