mckaywrigley / clarity-ai

A simple Perplexity AI clone.

Clarity AI

Clarity is simple perplexity.ai clone. Use the code for whatever you like! :)

If you have any questions, feel free to reach out to me on Twitter.

How It Works

Given a query, Clarity fetches relevant, up-to-date information from the web and uses OpenAI's API to generate an answer.

The app works as follows:

1. Get query from user
2. Scrape Google for relevant webpages
3. Parse webpages for text
4. Build prompt using query + webpage text
5. Call OpenAI API to generate answer
6. Stream answer back to user

Requirements

Get OpenAI API key here.

Running Locally

1. Clone repo

git clone https://github.com/mckaywrigley/clarity-ai.git

2. Install dependencies

npm i

3. Run app

npm run dev

Improvement Ideas

Here are some ideas for how to improve Clarity:

• Speed up answers by replacing link scraping with the Google Search API (scraping was used to circumvent cost + rate limits)
• Add "follow up" searches
• Improve the prompt
• Get sources working in non text-davinci-003 models
• Train your own model to use for answer synthesis

Credits

Shoutout to Perplexity AI for the inspiration. I highly recommend checking their product out.

This repo is meant to show people that you can build powerful apps like Perplexity even if you don't have a large, experienced team.

LLMs are amazing, and I hope Clarity inspires you to build something cool!

clarity-ai's Issues

Can you provide support for third-party APIs, including the ability to input a third-party interface URL?

Can you provide support for third-party APIs, including the ability to input a third-party interface URL?

Support for local LLM?

Hey! I was wondering whether there is any support for running this on a local LLM rather than relying on the OpenAI API.

Thank you!

Error when I tried to get an answer

Hello Clarity AI Team,

First of all, thank you for your work. It seems great. Unfortunately, I can't make it work as I have an error when I ask something.

When I put in my OpenAI API key and try to ask something I have on my VScode console the following error

[Error: OpenAI API returned an error]

On the application, I have a 'just Answer error'

And in my browser console, I have a 500 Internal Server Error on the POST request.

Could you help me about it? :)

Google API and does this use gpt turbo?

Speed up answers by replacing link scraping with the Google Search API (scraping was used to circumvent cost + rate limits)

how do i implement this?

Not working

we tried to implement this code... it is not working

My front end