Skip to main content

Guided project

A RAG app over 20 documents with a test set

Build a question-answering app over at least 20 public documents: split them into chunks, embed and search them, answer with citations, refuse when the documents are silent, and measure it with a 20-question test set.

Intermediateabout 12 hours6 steps

On Generative AI & LLM Engineer: RAG builder

You will need

  • Python 3 and an API key for a hosted model
  • At least 20 public documents on one subject, such as a government scheme's FAQs or a product's help pages

Lessons it uses

What you will show

  • A repository with the app and the 20-question test set
  • A report with recall at five, answer accuracy and refusal accuracy
  • Three examples of failures and what you changed

Sign up free to see every step

The 6 steps, the rubric to check yourself against, and ideas to go further. It is free, takes a few seconds and needs no card.

Accounts are for learners aged 18 and over. Under 18? The quick answer and the first part of every lesson stay open: browse lessons by topic.

Today's AI turns are used

Lessons, roadmaps, videos, practice cards and the code playground stay free with your account, with no limit.