Context window and token limits in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to calculate the number of tokens in a text using a simple split.

Prompt Engineering / GenAI

text = "Hello world! This is a test."
tokens = text.[1]()
print(len(tokens))

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

Areplace

Bjoin

Cstrip

Dsplit

Attempts:

3 left

💡 Hint

Common Mistakes

Using join instead of split.

Trying to replace tokens instead of splitting.

The split() method splits the text into tokens (words) separated by spaces.

2fill in blank

medium

Complete the code to limit the number of tokens to a maximum context window size.

Prompt Engineering / GenAI

text = "Hello world! This is a test."
max_tokens = 5
tokens = text.split()
limited_tokens = tokens[:[1]]
print(limited_tokens)

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

A5 + 1

Blen(tokens)

Cmax_tokens

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using len(tokens) which does not limit tokens.

Using 0 which results in an empty list.

We use max_tokens to slice the tokens list and keep only the allowed number of tokens.

3fill in blank

hard

Fix the error in the code that counts tokens but mistakenly uses a wrong method.

Prompt Engineering / GenAI

text = "Sample text for token count."
token_count = len(text.[1]())
print(token_count)

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

Asplit

Bcount

Cjoin

Dreplace

Attempts:

3 left

💡 Hint

Common Mistakes

Using count() which counts occurrences of a substring.

Using join() which combines strings.

The split() method splits the text into tokens, so counting its length gives the token count.

4fill in blank

hard

Complete the code to create a dictionary of tokens and their counts, filtering tokens longer than 3 characters.

Prompt Engineering / GenAI

text = "Hello world! This is a test."
tokens = text.split()
token_counts = {token: tokens.count(token) for token in tokens if len(token) [1] 3}
print(token_counts)

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

A:

B>

C<

D=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '=' instead of ':' in dictionary comprehension.

Using '<' which filters shorter tokens.

The colon : separates keys and values in a dictionary. The greater than > filters tokens longer than 3 characters.

5fill in blank

hard

Fill both blanks to create a dictionary of tokens in uppercase, their counts, and filter tokens with length less than 6.

Prompt Engineering / GenAI

text = "Hello world! This is a test."
tokens = text.split()
result = { [1] : tokens.count(token) for token in tokens if len(token) [2] 6 }
print(result)

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

Atoken.upper()

B<

Ctoken

D:

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'token' instead of 'token.upper()' for keys.

Using '>' instead of '<' for filtering.

Forgetting ':' between key and value.

We use token.upper() to convert tokens to uppercase keys, '<' to filter tokens shorter than 6, and ':' to separate keys and values in the dictionary.