banner
andrewji8

Being towards death

Heed not to the tree-rustling and leaf-lashing rain, Why not stroll along, whistle and sing under its rein. Lighter and better suited than horses are straw sandals and a bamboo staff, Who's afraid? A palm-leaf plaited cape provides enough to misty weather in life sustain. A thorny spring breeze sobers up the spirit, I feel a slight chill, The setting sun over the mountain offers greetings still. Looking back over the bleak passage survived, The return in time Shall not be affected by windswept rain or shine.
telegram
twitter
github
HomeArchives

Building your own AI search engine locally is so powerful!

#AI160
AI Translation
This post is translated from Chinese into English through AI.View Original
AI-generated summary
A hot open-source project called FreeAskInternet has gained over 5K stars in just a few days on Github. It is a free and private search aggregator and answer generator that runs locally without the need for GPUs. Users can ask questions and the project uses searxng for multi-engine search and ChatGPT3.5 LLM for generating answers. The project is easy to deploy using Docker and can be accessed from any device.

Today I was browsing Github and discovered a very popular open-source project in the past two days - FreeAskInternet, with the number of stars skyrocketing, already reaching 5K+ stars in just a few days.

Project Introduction
FreeAskInternet is a completely free, private, and locally run search aggregator and answer generator (i.e., a Q&A AI tool) that uses LLM technology without the need for GPU.

We can directly ask questions, and the project will use searxng for multi-engine search and combine the search results with ChatGPT3.5 LLM to generate answers based on the search results.

All processes run locally, without the need for GPU or OpenAI or Google API keys.

This project was only open-sourced in early April, and in just a few days, it has already received 5.6k stars and continues to increase.
Features
Completely free (no need for any API keys)
Completely local (no need for GPU, can run on any computer)
Completely private (all run locally, using custom LLM)
Does not use LLM hardware (no need for GPU)
Uses free ChatGPT3.5 / Qwen / Kimi / ZhipuAI(GLM) API (no need for API keys)
Supports custom LLM (ollama, llama.cpp)
Uses Docker Compose for quick deployment and ease of operation
Web and mobile-friendly interface, designed for AI-enhanced chat in web search, easily accessible from any device.
How It Works

  1. The project receives user input questions in the FreeAskInternet UI interface (locally run) and calls searxng (locally run) to search on multiple search engines.
  2. Crawls the content of search result links and passes it to ChatGPT3.5 / Kimi / Qwen / ZhipuAI / ollama (using custom LLM), asking LLM to answer user questions based on this content as a reference.
  3. Streams the answers to the Chat UI.
  4. The project supports custom LLM settings, theoretically supporting unlimited LLMs.
    Project Installation and Deployment
    The deployment method is also very simple, the official recommendation is to use docker
git clone https://github.com/nashsu/FreeAskInternet.git
cd ./FreeAskInternet
docker-compose up -d

Then open the following address in your browser: http://localhost:3000

image
FreeAskInternet is a practical tool that combines free, local, private, powerful search, and intelligent Q&A in one. It breaks the limitations of traditional search engines, allowing you to access information more efficiently.

For more details and features of the project, interested friends can check out the project address.

Project Address:
https://github.com/nashsu/FreeAskInternet

Loading...
Ownership of this post data is guaranteed by blockchain and smart contracts to the creator alone.