How to Generate Text Embeddings Using JavaScript

In this article, you'll learn how to generate text embeddings using JavaScript and the Eden AI API.

Whether you're building smart search engines, recommendation systems, or natural language applications, embeddings are essential for understanding the meaning of text.

Eden AI simplifies this process by offering unified access to multiple NLP providers through a single API.

‍

What Are Text Embeddings

Text embeddings are vector representations of text that capture semantic meaning. Instead of processing words or sentences as plain strings, embeddings convert them into numerical formats that can be used in machine learning models and similarity comparisons.

Use Cases:

• Semantic Search: Find relevant documents even if keywords don’t match exactly.
• Text Classification: Identify the category or sentiment of a piece of text.
• Recommendation Systems: Suggest similar articles or products based on content.

‍

How to Generate Text Embeddings

Get Access to Eden AI

1. Sign Up for an Eden AI Account: To begin using the Text Embeddings API, create an account on Eden AI. After registration, you’ll receive an API key that unlocks access to Text Embeddings among many other AI services.

2. Access Text Technologies: After logging in, navigate to the Text section of the platform.

3. Select Text Embeddings: Choose the Text Embeddings feature.

‍

Test Models Live on Eden AI

Before integrating in code, you can test embedding models directly on the Eden AI platform to compare providers and understand outputs.

‍

Implementing Text Embeddings in JavaScript

‍

Prepare the Code

const fetch = require('node-fetch'); // For Node.js < 18

const url = 'https://api.edenai.run/v2/text/embeddings/';
const token = '<your_api_key>'; // Replace with your actual Eden AI API key

fetch(url, {
  method: 'POST',
  headers: {
    'accept': 'application/json',
    'content-type': 'application/json',
    'authorization': `Bearer ${token}`
  },
  body: JSON.stringify({
    providers: ['google'], // You can use "openai", "cohere", etc.
    texts: [
      "Machine learning is amazing",
      "Natural language processing is powerful"
    ]
  })
})
  .then(res => res.json())
  .then(data => console.log(data))
  .catch(error => console.error('Error:', error));

Code Explanation

• fetch(): Sends a POST request to Eden AI’s embedding endpoint.
• headers: Sets up the API key and content type for the request.
• body: Specifies the embedding provider and input texts.
• .then(): Processes the JSON response.
• .catch(): Handles any errors during the request.

‍

Interpreting the Output

Here’s an example output (simplified):

{
  "google": {
    "items": [
      {
        "embedding": [0.034, -0.213, ..., 0.145],
        "text": "Machine learning is amazing"
      },
      {
        "embedding": [0.012, -0.167, ..., 0.101],
        "text": "Natural language processing is powerful"
      }
    ],
    "cost": 0.0001,
    "provider": "google",
    "status": "success"
  }
}

Output Explanation

• embedding: A vector that numerically represents the meaning of the text.
• text: The original input string.
• cost: API usage cost (if applicable).
• provider: Which AI provider generated the embeddings.
• status: Indicates if the request was successful.

‍

‍

Why Eden AI is the Best Tool for Text Embeddings

‍

Eden AI offers several advantages for Text Embeddings.

Access to multiple providers‍

With Eden AI, you can choose from a variety of providers, giving you great flexibility.

Ease of use‍

Eden AI’s API is designed to be simple and intuitive, making it easy for developers to integrate many AI services into their applications with minimal effort.

Scalability‍

Whether you’re working on small projects or large-scale applications, Eden AI is built to scale with your needs, making it suitable for a wide range of use cases.

‍

Conclusion

Recap

• Text embeddings transform textual data into machine-readable vectors.
• Eden AI makes it easy to generate these embeddings via a simple, unified API.
• JavaScript (with Node.js) can easily integrate this functionality for a variety of applications.

Final Thoughts

For developers looking to add semantic understanding to their applications, Eden AI offers a flexible and efficient way to generate high-quality text embeddings. With minimal setup and support for multiple providers, it’s a valuable tool for any NLP workflow.