Paul Graham GPT is a specialized AI-powered search and chat app built on a corpus of essays from Paul Graham, giving users the ability to query and discuss his writings in a conversational way. The repo stores the full text of his essays (chunked), uses embeddings (e.g. via OpenAI embeddings) to allow semantic search over that corpus, and hosts a chat interface that combines retrieval results with LLM-based answering — enabling RAG (retrieval-augmented generation) over a fixed dataset. The app uses a Postgres database (with pgvector) hosted on Supabase for its embedding store, making the backend relatively simple and accessible, and the frontend is again built with Next.js/TypeScript for a modern responsive UI. By pulling together search and chat, it creates a useful tool both for readers who want to revisit or explore Paul Graham’s ideas thematically, and for learners or researchers who want to query specific essays or concepts quickly.
Features
- Provides semantic search + chat over a curated text corpus (Paul Graham’s essays) — enabling retrieval-augmented generation (RAG)
- Uses embeddings stored in database (Postgres with pgvector via Supabase) — scalable and accessible storage backend
- Modern frontend with Next.js/TypeScript for responsive, user-friendly search and chat UI
- Easy setup: clone, set environment variables (OpenAI key, Supabase URL), run embedding + server, start chatting
- Open-source template — can be forked/repurposed for other book/essay corpora or private document sets
- Great for study, research, or browsing content via Q&A interface rather than reading static text — more interactive and exploratory than plain search
Project Samples
