README.md

metadata

title: Vector Endpoint
emoji: 📉
colorFrom: red
colorTo: indigo
sdk: docker
pinned: false

Vector Endpoint

A simple API that converts text into vector embeddings using the LaBSE sentence transformer model.

API Reference

Endpoint

POST /vectorize

Request Format

{
  "text": "Your text to be vectorized"
}

Response Format

{
  "embedding": [0.123, 0.456, ...]  // Vector representation of your text
}

Usage Examples

cURL

curl -X 'POST' \
  'https://placingholocaust-vector-endpoint.hf.space/vectorize' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
  "text": "This is a text"
}'

Python

import requests
import json

url = "https://placingholocaust-vector-endpoint.hf.space/vectorize"
headers = {
    "accept": "application/json",
    "Content-Type": "application/json"
}
data = {
    "text": "This is a text"
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

print(f"Embedding length: {len(result)}")
print(f"First few values: {result[:5]}")

JavaScript

// Using fetch
async function getEmbedding(text) {
  const response = await fetch(
    "https://placingholocaust-vector-endpoint.hf.space/vectorize", 
    {
      method: "POST",
      headers: {
        "accept": "application/json",
        "Content-Type": "application/json"
      },
      body: JSON.stringify({ text })
    }
  );
  
  const data = await response.json();
  return data
}

// Example usage
getEmbedding("This is a text")
  .then(embedding => {
    console.log(`Embedding length: ${embedding.length}`);
    console.log(`First few values: ${embedding.slice(0, 5)}`);
  })
  .catch(error => console.error("Error:", error));

Model Information

This endpoint uses the sentence-transformers/LaBSE model, which produces 768-dimensional embeddings that capture semantic meaning of text across multiple languages.