Quiz: RAG

5 questionsNo time limitPass: 60%+10 XP on first pass

Build a question-answering bot over your own documents: chunking, retrieving the best passages, a grounded prompt with numbered sources, citations, saying "not in the documents", and measuring retrieval quality — through a college handbook case study.

Free account · see your score, answers and explanations, earn XP

Question 1
What problem does RAG mainly solve?
Slow internet connectionsThe model not knowing your private or recent documents, and inventing answersThe cost of training a modelChoosing a programming language
Question 2
Why do chunks usually overlap a little?
To use more tokensSo information split across a boundary still appears whole in some chunkThe vector database requires itTo make chunks random
Question 3
Nothing relevant is retrieved for a question. What should the bot do?
Let the model answer from memorySay it can't find this in the documents and point to a humanRetry with a higher temperatureReturn the first chunk anyway
Question 4
What does "hit rate @ 2" measure?
How fast the model answersThe share of test questions whose correct passage is in the top 2 retrieved resultsHow many tokens are usedThe number of chunks
Question 5
Staff-only documents must not reach students. Where is this enforced?
In the prompt: "don't tell students"In retrieval: only search documents the user is allowed to seeBy the model's trainingNowhere — RAG can't do this

Skills101

Skills101 — practical coding courses in Hindi and English: DSA, Python, Java Full Stack and more. Structured lessons, real projects, free tutorials and certificates.

Explore

All courses
Free tutorials
Practice quizzes
Mock tests
Contests
Hackathons
Leaderboard
Interview experiences
Student tools
Online compilers
Tech dictionary
Project showcase
Blog
Corporate training

Contact

info@skills101.in
+91 86199 23140
WhatsApp us
Follow the WhatsApp Channel
Join the WhatsApp group
83-B, Ram Vihar Colony, Sanganer, Jaipur, Rajasthan 302029

YouTube
LinkedIn
X
Facebook