Lesson Complete!

Set Up Your Environment

What you did in this lesson

  • Learned what RAG is and why it solves LLM hallucination
  • Created a Python virtual environment
  • Installed pypdf, google-genai, numpy, and python-dotenv
  • Created a .env file to store your API key safely
  • Wrote load_pdf() — the entry point of your pipeline

What comes next

A page count is a start, but you need the actual text. In Lesson 2, you will extract raw text from every page and split it into chunks that the embedding model can process.