Vector similarity metrics in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to calculate the cosine similarity between two vectors.

Prompt Engineering / GenAI

from numpy import dot
from numpy.linalg import norm

def cosine_similarity(vec1, vec2):
    return dot(vec1, vec2) / (norm(vec1) [1] norm(vec2))

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

A*

B+

C-

D/

Attempts:

3 left

💡 Hint

Common Mistakes

Using addition instead of multiplication between the norms.

Dividing one norm by the other instead of multiplying.

The cosine similarity formula divides the dot product by the product of the norms (lengths) of the two vectors, so the operator between the norms is multiplication.

2fill in blank

medium

Complete the code to compute the Euclidean distance between two vectors.

Prompt Engineering / GenAI

import numpy as np

def euclidean_distance(vec1, vec2):
    return np.sqrt(np.sum((vec1 - vec2) [1] 2))

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

A+

B**

C*

D//

Attempts:

3 left

💡 Hint

Common Mistakes

Using multiplication '*' instead of exponent '**'.

Using integer division '//' which causes errors.

Euclidean distance uses the square of the difference, so the exponent operator '**' with 2 is correct.

3fill in blank

hard

Fix the error in the code to calculate the Manhattan distance between two vectors.

Prompt Engineering / GenAI

import numpy as np

def manhattan_distance(vec1, vec2):
    return np.sum(np.abs(vec1 [1] vec2))

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

A/

B+

C*

D-

Attempts:

3 left

💡 Hint

Common Mistakes

Using addition instead of subtraction inside the absolute value.

Using multiplication or division which are incorrect here.

Manhattan distance sums the absolute differences between vector elements, so subtraction is needed inside abs().

4fill in blank

hard

Fill both blanks to create a dictionary of word vectors filtered by length greater than 3.

Prompt Engineering / GenAI

words = ['cat', 'house', 'tree', 'sun']
vectors = {'cat': [1,2], 'house': [3,4], 'tree': [5,6], 'sun': [7,8]}
filtered_vectors = {word: vectors[word] for word in words if [1] [2] 3}

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

Alen(word)

Bword

C>

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using the word itself instead of its length.

Using less than '<' instead of greater than '>'.

The condition filters words whose length is greater than 3, so 'len(word) > 3' is correct.

5fill in blank

hard

Fill all three blanks to create a dictionary of words and their vector lengths filtered by length greater than 3.

Prompt Engineering / GenAI

words = ['dog', 'elephant', 'bird', 'ant']
vectors = {'dog': [1,1,1], 'elephant': [2,2,2], 'bird': [3,3,3], 'ant': [4,4,4]}
result = [1]: [2] for word in words if len(word) [3] 3

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

Aword

Blen(vectors[word])

C>

Dword.upper()

Attempts:

3 left

💡 Hint

Common Mistakes

Using the word as key without uppercase.

Using the word length instead of vector length as value.

Using '<' instead of '>' in the condition.

The dictionary keys are uppercase words, values are vector lengths, filtered by word length greater than 3.