Text embedding models in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a text embedding using a simple model.

Prompt Engineering / GenAI

embedding = model.[1](text)

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

Atransform

Bembed

Cfit

Dpredict

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'predict' instead of 'transform' causes errors because embeddings are not predictions.

Using 'fit' tries to train the model, not create embeddings.

The transform method is used to convert text into embeddings in many models.

2fill in blank

medium

Complete the code to normalize the embedding vector.

Prompt Engineering / GenAI

normalized_embedding = embedding / [1](embedding)

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

Anp.linalg.norm

Blen

Csum

Dmax

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'sum' adds all elements but does not give vector length.

Using 'len' returns number of elements, not vector magnitude.

Using np.linalg.norm calculates the length of the vector for normalization.

3fill in blank

hard

Fix the error in the code to compute cosine similarity between two embeddings.

Prompt Engineering / GenAI

similarity = np.dot(embedding1, embedding2) / ([1](embedding1) * np.linalg.norm(embedding2))

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

Amax

Bsum

Clen

Dnp.linalg.norm

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'sum' or 'len' causes incorrect similarity calculation.

Forgetting to normalize both vectors leads to wrong results.

Both vectors must be normalized by their norms to compute cosine similarity correctly.

4fill in blank

hard

Fill both blanks to create a dictionary of word embeddings for words longer than 3 letters.

Prompt Engineering / GenAI

word_embeddings = {word: [1] for word in words if len(word) [2] 3}

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

Amodel.transform(word)

Bmodel.fit(word)

C>

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'fit' instead of 'transform' tries to train the model on single words.

Using '<' filters words shorter than 3 letters, which is incorrect here.

We transform each word to get its embedding and filter words longer than 3 letters using >.

5fill in blank

hard

Fill all three blanks to create a filtered dictionary of embeddings where embedding norm is greater than 0.5.

Prompt Engineering / GenAI

filtered_embeddings = {word: emb for word, emb in embeddings.items() if [1](emb) [2] 0.5 and len(word) [3] 4}

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

Anp.linalg.norm

B>

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>' changes the filter logic incorrectly.

Not using norm function causes errors in filtering.

We use np.linalg.norm to get embedding length, filter embeddings with norm greater than 0.5, and words longer than 4 letters.