How to Build a Portfolio Chatbot With RAG on the Free Tier
A developer has created a portfolio chatbot using Google's Gemini 1.5 Flash model and Supabase's pgvector for its free tier capabilities. This setup allows the chatbot to answer questions about the developer's projects and experience without incurring any costs. The architecture leverages Gemini's free tier for LLM and embeddings, Supabase for vector storage, and Langfuse for observability, all hosted on Vercel's free tier. AI
IMPACT Demonstrates cost-effective AI application development, enabling personalized chatbots without significant infrastructure investment.