felladrin / MiniSearch

Minimalist web-searching app with an AI assistant that runs directly from your browser. Uses Web-LLM, Ratchet-ML, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space

MiniSearch

A minimalist search engine with integrated browser-based AI.

Live demo: https://felladrin-minisearch.hf.space

Features

• Privacy-focused: No tracking, no ads, no data collection
• Easy to use: Minimalist yet intuitive interface for all users
• Cross-platform: Models run inside the browser, both on desktop and mobile
• Integrated: Search from the browser address bar by setting it as the default search engine
• Time-saver: AI responses enhanced with search results
• Efficient: Models are loaded and cached only when needed
• Optimized: Aims for the balance between size and performance
• Open-source: The code is available for inspection and contribution at GitHub

Prerequisites

• Docker

Getting started

The easiest way to get started is by using MiniSearch's Docker Image by running the following command:

docker run -p 7860:7860 ghcr.io/felladrin/minisearch:main

Then, open http://localhost:7860 in your browser and start searching!

Building and running from source

You can build and run it from the source if you don't want to use MiniSearch's Docker Image. For that, clone this repository and run the following command:

docker-compose -f docker-compose.production.yml up --build

Contributing

MiniSearch is open-source and contributions are welcome!

Fork this repository and clone it. Then, start the development server by running the following command:

docker-compose up

Make your changes, push them to your fork, and open a pull request!