Hybrid search (semantic + keyword) in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to combine semantic and keyword search scores by adding them.

Prompt Engineering / GenAI

final_score = semantic_score [1] keyword_score

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

A*

B-

C+

D/

Attempts:

3 left

💡 Hint

Common Mistakes

Using multiplication instead of addition

Using subtraction which lowers the score

We add semantic and keyword scores to get a combined relevance score.

2fill in blank

medium

Complete the code to normalize the semantic vector before searching.

Prompt Engineering / GenAI

normalized_vector = semantic_vector [1] np.linalg.norm(semantic_vector)

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

A/

B*

C+

D-

Attempts:

3 left

💡 Hint

Common Mistakes

Multiplying instead of dividing

Adding or subtracting which does not normalize

Dividing by the vector's norm scales it to length 1, which is normalization.

3fill in blank

hard

Fix the error in the code to filter documents containing the keyword 'AI'.

Prompt Engineering / GenAI

filtered_docs = [doc for doc in documents if 'AI' [1] doc['keywords']]

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

A==

Bin

Cnot in

D!=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '==' which compares equality incorrectly

Using 'not in' which excludes documents with 'AI'

The 'in' keyword checks if 'AI' is inside the keywords list of each document.

4fill in blank

hard

Fill both blanks to create a dictionary of document IDs and their combined scores, filtering for scores above 0.5.

Prompt Engineering / GenAI

result = {doc['id']: doc['semantic_score'] [1] doc['keyword_score'] for doc in docs if (doc['semantic_score'] [2] doc['keyword_score']) > 0.5}

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

A+

B-

C*

D/

Attempts:

3 left

💡 Hint

Common Mistakes

Using multiplication or division which changes score meaning

Using subtraction which can lower scores incorrectly

We add semantic and keyword scores to get combined scores and filter those above 0.5.

5fill in blank

hard

Fill all three blanks to create a list of document titles where the combined score is above 0.7.

Prompt Engineering / GenAI

top_titles = [doc[[1]] for doc in docs if (doc[[2]] + doc[[3]]) > 0.7]

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

A'title'

B'semantic_score'

C'keyword_score'

D'id'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'id' instead of 'title' for the first blank

Mixing up score fields or using wrong keys

We select the 'title' field for documents where the sum of 'semantic_score' and 'keyword_score' is greater than 0.7.