Similarity search and retrieval in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to compute cosine similarity between two vectors.

Prompt Engineering / GenAI

from sklearn.metrics.pairwise import [1]

vector_a = [[1, 2, 3]]
vector_b = [[4, 5, 6]]
similarity = [1](vector_a, vector_b)
print(similarity)

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

Apairwise_distances

Beuclidean_distances

Cmanhattan_distances

Dcosine_similarity

Attempts:

3 left

💡 Hint

Common Mistakes

Using distance functions instead of similarity functions.

Confusing cosine similarity with Euclidean distance.

The cosine_similarity function calculates the cosine similarity between vectors, which is commonly used in similarity search.

2fill in blank

medium

Complete the code to find the index of the most similar vector in a list using cosine similarity.

Prompt Engineering / GenAI

import numpy as np
from sklearn.metrics.pairwise import cosine_similarity

vectors = np.array([[1, 0], [0, 1], [1, 1]])
query = np.array([[0.9, 0.1]])
similarities = cosine_similarity(query, vectors)
most_similar_index = np.argmax([1])
print(most_similar_index)

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

Asimilarities

Bvectors

Cquery

Dnp.array

Attempts:

3 left

💡 Hint

Common Mistakes

Using the original vectors array instead of similarity scores.

Trying to find max on the query vector.

The similarities array contains similarity scores between the query and each vector. Using np.argmax on it finds the index of the highest similarity.

3fill in blank

hard

Fix the error in the code to correctly compute Euclidean distances between vectors.

Prompt Engineering / GenAI

from sklearn.metrics.pairwise import [1]

vectors = [[1, 2], [3, 4], [5, 6]]
distances = [1](vectors)
print(distances)

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

Acosine_similarity

Beuclidean_distances

Cmanhattan_distances

Dpairwise_kernels

Attempts:

3 left

💡 Hint

Common Mistakes

Using similarity functions instead of distance functions.

Passing a single list instead of a 2D array.

The euclidean_distances function computes the Euclidean distance matrix between vectors. The original code likely used a wrong function causing errors or wrong output.

4fill in blank

hard

Fill both blanks to create a dictionary of word lengths for words longer than 3 characters.

Prompt Engineering / GenAI

words = ['apple', 'bat', 'carrot', 'dog', 'elephant']
lengths = {word: [1] for word in words if len(word) [2] 3}
print(lengths)

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

Alen(word)

B<=

C>

Dword

Attempts:

3 left

💡 Hint

Common Mistakes

Using the word itself instead of its length.

Using the wrong comparison operator.

The dictionary comprehension uses len(word) to get word lengths and filters words with length greater than 3 using >.

5fill in blank

hard

Fill all three blanks to create a filtered dictionary with uppercase keys and values greater than 2.

Prompt Engineering / GenAI

data = {'a': 1, 'b': 3, 'c': 5, 'd': 2}
filtered = [1]: [2] for k, v in data.items() if v [3] 2}
print(filtered)

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

Ak.upper()

Bv

C>

Dk.lower()

Attempts:

3 left

💡 Hint

Common Mistakes

Not converting keys to uppercase.

Using wrong comparison operator or filtering condition.

The dictionary comprehension converts keys to uppercase with k.upper(), keeps values as v, and filters for values greater than 2 using >.