MiniSearch — Your private search, powered by AI right…

Pitch

Description

Comments

About this project

Self-hosted web-searching platform with an AI assistant that runs directly from your browser.

Uses Web-LLM, Wllama and SearXNG.

Demo: https://felladrin-minisearch.hf.space

A minimalist web-searching app with an AI assistant that runs directly from your browser.

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

Screenshot

MiniSearch Screenshot

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
Open-source: The code is available for inspection and contribution at GitHub

Prerequisites

Docker

Getting started

There are two ways to get started with MiniSearch. Pick one that suits you best.

Option 1 - Use MiniSearch's Docker Image by running:

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

Option 2 - Build from source by cloning this repository and running:

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

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

Frequently asked questions

How can I contribute to MiniSearch?

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! All contributions are welcome!

How do I search via the browser's address bar?

You can set MiniSearch as your browser's address-bar search engine using the pattern http://localhost:7860/?q=%s, in which your search term replaces %s.

Can I use custom models via OpenAI-Compatible API?

Yes! For this, open the Menu and change the "Inference Type" to OpenAI-Compatible API. Then configure the Base URL, and optionally set an API Key and a Model to use.

How do I restrict the access to my MiniSearch instance via password?

Create a .env file and set a value for ACCESS_KEYS. Then reset the MiniSearch docker container.

For example, if you to set the password to PepperoniPizza, then this is what you should add to your .env:
ACCESS_KEYS="PepperoniPizza"

You can find more examples in the .env.example file.

Why is MiniSearch built upon SearXNG's Docker Image and using a single image instead of composing it from multiple services?

There are a few reasons for this:

MiniSearch utilizes SearXNG as its meta-search engine.
Manual installation of SearXNG is not trivial, so we use the docker image they provide, which has everything set up.
SearXNG only provides a Docker Image based on Alpine Linux.
The user of the image needs to be customized in a specific way to run on HuggingFace Spaces, where MiniSearch's demo runs.
HuggingFace only accepts a single docker image. It doesn't run docker compose or multiple images, unfortunately.

I want to serve MiniSearch to other users, allowing them to use my own OpenAI-Compatible API key, but without revealing it to them. Is it possible?

Yes! In MiniSearch, we call this text-generation feature "Internal OpenAI-Compatible API". To use this it:

Set up your OpenAI-Compatible API endpoint by configuring the following environment variables in your .env file:
- INTERNAL_OPENAI_COMPATIBLE_API_BASE_URL: The base URL for your API
- INTERNAL_OPENAI_COMPATIBLE_API_KEY: Your API access key
- INTERNAL_OPENAI_COMPATIBLE_API_MODEL: The model to use
- INTERNAL_OPENAI_COMPATIBLE_API_NAME: The name to display in the UI
Restart MiniSearch server.
In the MiniSearch menu, select the new option (named as per your INTERNAL_OPENAI_COMPATIBLE_API_NAME setting) from the inference type dropdown.