serebano / makr-ai

Chat GPT clone with enhanced features for makers on top of Next.js, Supabase, Typescript, Jotai and TailwindCSS.

Home Page:https://ai.makr.dev

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

makr.AI

makr.AI is a ChatGPT clone with enhanced features for makers & indie hackers built on top of using Next.js, TypeScript, Supabase, Jotai and Tailwind CSS.

makr.AI

Check this Youtube video to learn more.

Roadmap

I'll be building new features over time. If you have any suggestions, feel free to open a discussion or reach out to me on Twitter. I listed the features I'm working on next below.

What to expect:

  • Long-term Memory for Conversations (Supabase's Vector Database) - 14.04.23
  • Propmt Library
  • Organising Conversations with Folders etc.
  • Collections Library for saving responses
  • Plugins ecosystem with GPT agents

Deploy

Vercel

Host your own live version of makr.AI with Vercel.

Deploy with Vercel

Running Locally

1. Create a Supabase Project The application holds conversations in a Supabase database. You can create a free account here.

makr.AI needs a Supabase URL and Anon Key to connect to your database. You can find these in your Supabase project settings.

You must create 3 tables in your supabase project:

makr.AI

You can create all the tables you need with the sql function that I cretead in the sql folder of the repo. You can use the create-tables.sql file in the sql folder of the repo to create the tables. Remember that you must enable the pg_vector extension before creating the tables.

After you create the embedding column, you should create an index based on this column. You can use the create-index.sql file in the sql folder of the repo to create the index.

Finally, you must create a sql function called search-messages in your Supabase project. You can use the search-messages.sql file in the sql folder of the repo to create the function.

Project Setup tutorial. Longterm Memory for ChatGPT tutorial.

2. Clone The Repo

git clone https://github.com/batuhanbilginn/makr-ai.git

3. Install Dependencies

yarn install

4. Create Your Enviroment Variables

Create your .env.local file in the root of the repo with your Supabase URL and Supabase Anon Key:

NEXT_PUBLIC_SUPABASE_URL=YOUR_URL
NEXT_PUBLIC_SUPABASE_ANON_KEY=YOUR_KEY

4. Run Development Server

yarn dev

Configuration

When deploying the application, the following environment variables can be set:

Environment Variable Default value Description
NEXT_PUBLIC_SUPABASE_URL - The base url of your Supabase Project
NEXT_PUBLIC_SUPABASE_ANON_KEY - The Anon Key for your Supabase Project

If you don't have an OpenAI API key, you can get one here.

Contact

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

About

Chat GPT clone with enhanced features for makers on top of Next.js, Supabase, Typescript, Jotai and TailwindCSS.

https://ai.makr.dev


Languages

Language:TypeScript 97.3%Language:JavaScript 1.1%Language:CSS 1.0%Language:PLpgSQL 0.6%