Documentation Index
Fetch the complete documentation index at: https://docs.latitude.so/llms.txt
Use this file to discover all available pages before exploring further.
Overview
This guide shows you how to integrate Latitude Telemetry into an application that uses Google Cloud AI Platform.
You’ll keep calling AI Platform 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 Google Cloud AI Platform SDK
Steps
Install
npm install @latitude-data/telemetry
pip install latitude-telemetry
Initialize and use
import { Latitude, capture } from "@latitude-data/telemetry"
import { PredictionServiceClient } from "@google-cloud/aiplatform"
import * as AIPlatformSDK from "@google-cloud/aiplatform"
const latitude = new Latitude({
apiKey: process.env.LATITUDE_API_KEY!,
project: process.env.LATITUDE_PROJECT_SLUG!,
instrumentations: { aiplatform: AIPlatformSDK },
})
await latitude.ready
const client = new PredictionServiceClient()
await capture("generate-prediction", async () => {
const [response] = await client.predict({
endpoint: `projects/${process.env.GCP_PROJECT_ID}/locations/us-central1/publishers/google/models/text-bison`,
instances: [{ content: "Hello" }],
parameters: { temperature: 0.2, maxOutputTokens: 256 },
})
return response.predictions
})
await latitude.shutdown()
from google.cloud import aiplatform
from latitude_telemetry import Latitude, capture
latitude = Latitude(
api_key="your-api-key",
project="your-project-slug",
instrumentations={"aiplatform": aiplatform},
)
aiplatform.init(project="your-gcp-project", location="us-central1")
def generate_prediction():
model = aiplatform.TextGenerationModel.from_pretrained("text-bison")
response = model.predict("Hello", temperature=0.2, max_output_tokens=256)
return response.text
capture("generate-prediction", generate_prediction)
latitude.shutdown()
Seeing Your Traces
Once connected, traces appear automatically in Latitude:
- Open your project in the Latitude dashboard
- Each execution shows input/output messages, model, token usage, latency, and errors
That’s It
No changes to your AI Platform calls: just initialize Latitude and your LLM calls are traced.
