Hybrid search strategies in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to combine vector similarity and keyword matching in a hybrid search.

Prompt Engineering / GenAI

hybrid_score = vector_score * [1] + keyword_score

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

A1.0

B0.5

C2.0

Dvector_score

Attempts:

3 left

💡 Hint

Common Mistakes

Using 1.0 or 2.0 makes vector similarity dominate too much.

Using 'vector_score' again causes a wrong calculation.

The vector similarity score is weighted by 0.5 before adding the keyword score to balance both methods.

2fill in blank

medium

Complete the code to filter search results by a minimum hybrid score threshold.

Prompt Engineering / GenAI

filtered_results = [r for r in results if r['hybrid_score'] [1] 0.7]

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

A==

B<

C!=

D>=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' filters out good results.

Using '==' is too strict and excludes most results.

We keep results with hybrid scores greater than or equal to 0.7 to ensure relevance.

3fill in blank

hard

Fix the error in the code that calculates the final hybrid score by normalizing vector and keyword scores.

Prompt Engineering / GenAI

final_score = (vector_score / max_vector) * [1] + (keyword_score / max_keyword)

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

Avector_score

Bmax_keyword

Cweight_vector

Dweight_keyword

Attempts:

3 left

💡 Hint

Common Mistakes

Multiplying by max_keyword mixes up normalization.

Using vector_score again ignores normalization.

The vector score is multiplied by its weight before adding the normalized keyword score.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps document IDs to their hybrid scores only if the score is above 0.6.

Prompt Engineering / GenAI

hybrid_dict = {doc['id']: doc['score'] for doc in docs if doc['score'] [1] 0.6 and doc['id'] [2] None}

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

A>

B!=

C==

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' includes low scores.

Using '==' None excludes valid IDs.

We select docs with scores greater than 0.6 and IDs that are not None.

5fill in blank

hard

Fill all three blanks to create a list comprehension that extracts titles of documents with hybrid scores above 0.75 and keyword matches greater than 2.

Prompt Engineering / GenAI

selected_titles = [doc[1] for doc in documents if doc['hybrid_score'] [2] 0.75 and doc['keyword_matches'] [3] 2]

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

A['title']

B>

D['id']

Attempts:

3 left

💡 Hint

Common Mistakes

Selecting 'id' instead of 'title'.

Using '<' includes unwanted docs.

We extract the 'title' field for docs with hybrid_score > 0.75 and keyword_matches > 2.