← Back to portfolio
AI Portfolio Assistant
A RAG-powered chatbot that answers questions about my work using vector search over my portfolio content.
How it works
- You ask a question through the chat interface
- The question is converted to a vector embedding using OpenAI's text-embedding-3-small
- Cosine similarity finds the 3 most relevant entries from 20+ knowledge base chunks
- GPT-4o-mini generates a response grounded in the retrieved context
- The response streams back in real-time via the Vercel AI SDK
Technical details
Stack
Next.js 16, React 19, TypeScript, Tailwind CSS, OpenAI GPT-4o-mini, text-embedding-3-small, Vercel AI SDK, custom cosine similarity implementation. Deployed on Vercel.
Cost
~$0.001–0.003 per conversation using GPT-4o-mini. Embeddings cost ~$0.0001 per query. Total for 100–200 monthly conversations: $1–2.
Try it
Click the chat button in the bottom-right corner, or try the inline chat on the homepage
AI-powered · Responses may not reflect exact words or opinions