Skip to main content

RAG App with Evals on Your Own Docs

Build a RAG app on your own documentation, with an eval suite that catches regressions. The canonical AI eng portfolio piece.

Next.js or StreamlitAnthropic SDKpgvectorLlamaIndex or LangChain

About this project

RAG is the bread-and-butter of AI engineering. This project teaches the canonical pipeline (chunk, embed, store, retrieve, rerank, generate) and the often-missing piece — evals. Use your own docs (Notion, GitHub, blog) and Claude or GPT-4o. Build a small eval set of 30 Q&A pairs and track precision@k as you tune the pipeline.

Why build this in 2026?

RAG is the most-shipped AI feature in 2026. Engineers who can ship reliable RAG with evals are the hottest hire.

What you'll ship

  • Live demo
GitHub repo
Eval report with metrics over time

Sign up to see the full project brief

Full deliverables, success criteria, and AI Career Tutor support — free.

You'll unlock:Complete project brief, AI tutor that knows this project, and progress tracking when you start.

Skills you'll practice

pythonlarge language modelsretrieval augmented generationvector databases