Perplexed

Open-source app inspired by the amazing web search product, Perplexity.

Live Demo

Implementation

Given a user query, the app conducts a web search, downloads the top N resulting web pages, then analyzes those pages with an LLM.

The LLM can be any smaller, consumer-grade with at least 5k context window (assuming each web page ~1k tokens).

Deployment Instructions

A. Python Server

1. cd backend
   copy config.json.sample config.json
   

2. In config.json, fill in GOOGLE_SEARCH_API_KEY and GOOGLE_SEARCH_ENGINE_ID credentials from Google Custom Search API.

3. Fill in GROQ_API_KEY credentials from Groq.

4. Setup virtual environment, packages, and deploy the server

   virtualenv venv
   . venv/bin/activate
   pip install -r requirements.txt
   python app.py
   

   This is fine for dev testing.

   In production, in addition, you probably want to use gunicorn (1, 2) and nginx (1) in conjunction with your python server (1) (utility scripts linked).

B. React Frontend

1. cd frontend
   

2. Update API_URL in constants.js to point to your server

3. npm install
   npm run build
   

4. In dev testing, to start the server:

   npm run start
   

   In production, to start the server:

   npm i -g npm@latest
   rm -rf node_modules
   rm -rf package-lock.json
   npm cache clean --force
   npm i --no-optional --omit=optional
   npm run build
   npm install -g serve
   server -s build