🟣 EMBER

A terminal-based text embeddings demonstration tool that showcases how semantic similarity works using OpenAI's text embedding models.

This is a vibe-coded toy app I built for a presentation on how vector-based text similarity works.

Uses OpenAI's API to embed and compare similarity of text using the text-embedding-3-small model and cosine similarity.

Screenshots

Installation

Option 1: Download Prebuilt Binary

Download the latest release for your platform from the Releases page.

Available for:

• Linux (x64, ARM64)
• macOS (Intel, Apple Silicon)
• Windows (x64)

Option 2: Build from Source

Prerequisites:

• Go 1.21 or later

Build:

git clone <this-repo>
cd ember
go build -o ember .

Usage

Setup

You need an OpenAI API key to generate embeddings:

export OPENAI_API_KEY="your-api-key-here"

Get an API key from OpenAI's platform.

Running

ember

License

MIT License - see LICENSE file for details.