shalingams/llamatutor

An AI personal tutor built with Llama 3.1

Llama Tutor

An open source AI personal tutor. Powered by Llama 3 70B & Together.ai

Tech stack

• Llama 3.1 70B from Meta for the LLM
• Together AI for LLM inference
• Next.js app router with Tailwind
• Serper for the search API
• Helicone for observability
• Plausible for website analytics

Cloning & running

1. Fork or clone the repo
2. Create an account at Together AI for the LLM
3. Create an account at SERP API or with Azure (Bing Search API)
4. Create an account at Helicone for observability
5. Create a .env (use the .example.env for reference) and replace the API keys
6. Run npm install and npm run dev to install dependencies and run locally

Future Tasks

• Add a share & copy buttons that folks can click on after convos are generated
• Add potential follow up questions + new chat at the end of chat page
• Split the page into two pages and add back the footer
• Move all my icons into their own typescript file (transform.tools)
• Add a more detailed landing page with a nice section with the GitHub link
• Add nice hamburger menu on mobile
• Try out the generative UI stuff from Vercel
• Add a nicer dropdown overall