Homework 4: Evaluation

Deadline: 13 July 2026 (Mon), 23:00

Shown in your timezone.

View public statistics

Correct answers are available below

This homework has already been scored. Log in to view your own submission, score, and feedback.

Correct answers

Review the expected answers for this scored homework.

1. When generating questions for the first 3 lesson pages, what is the average number of input tokens across these 3 calls? (1 point)

140

1400

14000

140000

2. After running text_search for the first ground truth question, what is the filename of the first result? (1 point)

01-agentic-rag/lessons/01-intro.md

01-agentic-rag/lessons/03-rag.md

01-agentic-rag/lessons/13-function-calling.md

01-agentic-rag/lessons/10-rag-next-steps.md

3. After running vector_search for the same question, what is the filename of the first result? (1 point)

01-agentic-rag/lessons/01-intro.md

01-agentic-rag/lessons/03-rag.md

04-evaluation/lessons/11-evaluation-intro.md

04-evaluation/lessons/12-rag-answers.md

4. After evaluating text_search on the ground truth, what is the Hit Rate? (1 point)

0.55

0.66

0.76

0.88

5. After evaluating vector_search on the ground truth, what is the MRR? (1 point)

0.35

0.45

0.55

0.65

6. When evaluating hybrid_search for k values 1, 50, 100, and 200, which k gives the best MRR? (1 point)

100

200