API Demo & Integration Guide

See how to integrate Latent Earth embeddings into your ML pipelines with real examples and step-by-step workflows

API Request Example

Request

Choose a model (e.g. og25) and send your coordinates; you’ll get an embedding vector for each coordinate.

curl -X POST https://staging-api.latentearth.com/api/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LATENTEARTH_API_KEY" \
  -d '{
    "uuid": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "model": "og25",
    "coordinates": [
      [37.774929, -122.419416],
      [40.712776, -74.005974]
    ]
  }'

import requests
	
	url = "https://staging-api.latentearth.com/api/v1/embeddings"
	api_key = "YOUR_API_KEY"
	headers = {
	  "Content-Type": "application/json",
	  "Authorization": f"Bearer {api_key}",
	}
	payload = {
	  "uuid": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
	  "model": "og25",
  "coordinates": [
    [37.774929, -122.419416],
    [40.712776, -74.005974],
  ],
}

	res = requests.post(url, json=payload, headers=headers, timeout=30)
	res.raise_for_status()
	print(res.json())

const res = await fetch("https://staging-api.latentearth.com/api/v1/embeddings", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    Authorization: `Bearer ${process.env.LATENTEARTH_API_KEY}`,
  },
  body: JSON.stringify({
    uuid: "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    model: "og25",
    coordinates: [
      [37.774929, -122.419416],
      [40.712776, -74.005974],
    ],
  }),
});

if (!res.ok) throw new Error(await res.text());
console.log(await res.json());

Output

{
			  "uuid": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
			  "model": "og25",
			  "embeddings": [
			    {
	      "coordinate": [37.7749, -122.4194],
	      "vector": [0.12341, -0.56789, 0.90129, ..., 0.43212]
	    },
	    {
	      "coordinate": [40.7128, -74.0060],
	      "vector": [0.23451, -0.67895, 0.01233, ..., 0.54320]
	    }
	  ],
	  "credits_used": 8
	}

ML Pipeline Integration

Observations with Location

Data points with coordinates attached

Feature Engineering

Hand-crafted features from your data

Latent Earth API

Location embeddings for coordinates

Enhanced Features

Hand-crafted + Location embeddings

Improved Model

Higher accuracy with location context

End-to-End Examples

Interactive Notebooks

Explore complete end-to-end demonstrations with real datasets. See how to integrate Latent Earth embeddings into your ML pipelines with step-by-step examples.

View on GitHub

Try It Out Yourself!

Create account

or schedule a 30-min consultation to discover how we can deliver impact for your business