This project provides a semantic search engine for emojis, allowing users to find relevant emojis using natural language queries. It's designed for anyone who frequently uses emojis and wants a more efficient way to discover them beyond simple keyword matching. The primary benefit is improved emoji discovery through intelligent, context-aware search.

How It Works

The system leverages OpenAI's embeddings to represent both emoji descriptions and user queries in a shared vector space. A local vector index is built from a curated dataset of emojis and their associated descriptions. When a user submits a query, it's embedded and then used to find the nearest neighbors in the emoji embedding index, returning the most semantically relevant emojis.

Quick Start & Requirements

• Install/Run: Requires Python 3.x and Node.js.
  • Build index: OPENAI_API_KEY={api_key} python server/data/build.py
  • Start backend: OPENAI_API_KEY={api_key} python server/app.py
  • Start frontend: cd client && npm install && REACT_APP_SERVER_ADDRESS="http://localhost:5000" npm start
• Prerequisites: OpenAI API key.
• Links: emojisearch.app

Highlighted Details

• Utilizes OpenAI embeddings for semantic understanding.
• Provides a local build process for the embedding index.
• Includes a React-based frontend for user interaction.

Maintenance & Community

No specific community channels or maintenance details are provided in the README.

Licensing & Compatibility

The license is not specified in the README.

Limitations & Caveats

The project relies on an external OpenAI API key, incurring potential costs. The README does not specify the license, which may impact commercial use or integration into closed-source projects.