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
.envfile 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.