Semantic Embed SDK

A fast and lightweight TypeScript/JavaScript sdk for generating text embeddings based on FastAPI and other python tools.

📦 Overview

The Semantic Embed SDK is a TypeScript library designed to interface with the Semantic Embed API for generating text embeddings. With this SDK, developers can easily create and manage embeddings for their applications and work with semantic models powered by FastAPI. Whether you're building a recommendation system, semantic search, or performing content similarity analysis, Semantic Embed is your go-to tool for text embeddings.

---

🚀 Features

• TypeScript Ready: Fully written in TypeScript for type safety and developer-friendly experience.
• FastAPI Integration: Seamless integration with the Semantic Embed API built on FastAPI for optimal performance.
• Easy-to-use API: Simple and clean API design to get started with embedding generation effortlessly.
• Environment Config: Supports .env configuration for API keys and other environment variables.
• Support for Custom Models: Flexibility to work with different embedding models and configurations such as all-MiniLM-L6-v2 (384 dimensions), all-MiniLM-L12-v2 (384 dimensions), all-mpnet-base-v2 (768 dimensions) and finally e5-large-v2 (1024 dimensions).

---

⚡ Quick Start

Follow these steps to integrate the Semantic Embed SDK into your project:

1. Install the SDK

You can install the SDK via PNPM:

pnpm install semantic-embed

using Npm:

npm add semantic-embed

Or using Yarn:

yarn add semantic-embed

2. Setup API Key

Make sure you have an API key to access the Semantic Embed API, get one at semantic-embed.uanelacomo.com. You can set it up in a .env file at the root of your project:

SEMANTIC_EMBED_API_KEY=your-api-key-here

3. Using the SDK

After installation, you can easily use the SDK to generate embeddings for your content.

Example Usage:

import SemanticEmbed from "semantic-embed";

const semanticEmbed = new SemanticEmbed("your-api-key-if-not-in-env");

// Example text to generate embeddings
const text = "Semantic embedding is the future of search!";

async function generateEmbedding() {
  try {
    const embedding = await semanticEmbed.generateEmbedding(text);
    console.log("Generated Embedding: ", embedding);
  } catch (error) {
    console.error("Error generating embedding: ", error);
  }
}

generateEmbedding();

---

🔧 API

generateEmbedding(text: string): Promise<number[]>

Generates a semantic embedding for the provided text.

Arguments:

• text (string): The text content for which you want to generate an embedding.

Returns:

• Promise: A promise that resolves to the generated embedding data.

🛠️ Development

To contribute or build the SDK from source:

1. Clone the Repository

git clone https://github.com/uanela/semantic-embed-sdk.git
cd semantic-embed

2. Install Dependencies

pnpm install

3. Build the Project

pnpm run build

4. Run in Development Mode

pnpm run dev

---

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

---

📫 Contact

For any issues or questions, please open an issue or contact Uanela Como.