Re-ranking retrieved results in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to sort the retrieved results by their scores in descending order.

Prompt Engineering / GenAI

sorted_results = sorted(results, key=lambda x: x['score'], reverse=[1])

Drag options to blanks, or click blank then click option'

A0

BFalse

CTrue

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Using reverse=False which sorts ascending instead of descending.

Using None or 0 which are invalid for reverse parameter.

Setting reverse=True sorts the list from highest to lowest score, which is needed for re-ranking.

2fill in blank

medium

Complete the code to select the top 5 results after re-ranking.

Prompt Engineering / GenAI

top_results = sorted_results[:[1]]

Drag options to blanks, or click blank then click option'

A3

B5

C10

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using 3 or 10 which selects wrong number of results.

Using 0 which results in an empty list.

We want the top 5 results, so slicing up to index 5 selects the first five items.

3fill in blank

hard

Fix the error in the code to compute new scores by multiplying original scores by a re-ranker score.

Prompt Engineering / GenAI

for item in results:
    item['new_score'] = item['score'] * item[[1]]

Drag options to blanks, or click blank then click option'

A'rank_score'

B'score'

C'new_score'

D're_rank_score'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'score' which multiplies the score by itself.

Using 'new_score' which is not yet defined.

Using 'rank_score' which is not a valid key.

The re-ranker score is stored under the key 're_rank_score', so we multiply by that.

4fill in blank

hard

Fill both blanks to create a dictionary of item IDs mapped to their new scores, filtering only items with new_score above 0.5.

Prompt Engineering / GenAI

filtered_scores = {item['id']: item[[1]] for item in results if item[[2]] > 0.5}

Drag options to blanks, or click blank then click option'

A'new_score'

B'score'

D're_rank_score'

Attempts:

3 left

💡 Hint

Common Mistakes

Using different keys for mapping and filtering causing errors.

Using 'score' or 're_rank_score' which are not the updated scores.

We want to map IDs to new_score and filter by new_score greater than 0.5.

5fill in blank

hard

Fill all three blanks to sort the filtered scores dictionary by score descending and get a list of top 3 item IDs.

Prompt Engineering / GenAI

top_ids = [k for k, v in sorted(filtered_scores.items(), key=lambda item: item[[1]], reverse=[2])[:[3]]]

Drag options to blanks, or click blank then click option'

A1

BTrue

C3

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Sorting by index 0 which is the key, not the score.

Using reverse=False which sorts ascending.

Slicing with wrong number like 0 or 1.

We sort by the value at index 1 (the score), descending (reverse=True), and take the top 3 IDs.