Rate limiting and abuse prevention in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to set a maximum number of requests per minute.

Prompt Engineering / GenAI

rate_limit = [1]  # max requests per minute

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

A100

B1000

C10

D500

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing too high a number that defeats rate limiting purpose.

Setting rate_limit to 100 means the system allows 100 requests per minute.

2fill in blank

medium

Complete the code to check if the user has exceeded the allowed requests.

Prompt Engineering / GenAI

if user_requests > [1]:
    block_user()

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

Arate_limit + 10

Brate_limit

Crate_limit / 2

Drate_limit * 2

Attempts:

3 left

💡 Hint

Common Mistakes

Using a value higher than the limit, which delays blocking.

The user is blocked if their requests exceed the set rate_limit.

3fill in blank

hard

Fix the error in the code that resets the request count after one minute.

Prompt Engineering / GenAI

if time.time() - start_time >= [1]:
    user_requests = 0
    start_time = time.time()

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

A10

B30

C100

D60

Attempts:

3 left

💡 Hint

Common Mistakes

Using 30 or 10 seconds which resets too frequently.

The request count resets every 60 seconds (1 minute) to enforce rate limiting per minute.

4fill in blank

hard

Fill both blanks to implement a simple token bucket rate limiter.

Prompt Engineering / GenAI

bucket_capacity = [1]
tokens = [2]

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

A100

B0

C50

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Setting tokens to zero initially which blocks all requests at start.

The bucket capacity and initial tokens are both set to 100 to allow full capacity at start.

5fill in blank

hard

Fill all three blanks to update tokens and check if a request can proceed.

Prompt Engineering / GenAI

tokens = min([1] + refill_rate, [2])
if tokens >= [3]:
    tokens -= 1
    allow_request()

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

Atokens

Bbucket_capacity

C1

Drefill_rate

Attempts:

3 left

💡 Hint

Common Mistakes

Not capping tokens at bucket capacity or subtracting wrong token amount.

Tokens are refilled but capped at bucket capacity. A request uses 1 token if available.