Load balancing for AI services in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple round-robin load balancer that selects the next AI service endpoint.

Prompt Engineering / GenAI

def get_next_endpoint(endpoints, current_index):
    return endpoints[[1]]  # Select next endpoint

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

Acurrent_index + 1 % len(endpoints)

Bcurrent_index - 1 % len(endpoints)

C(current_index + 1) % len(endpoints)

Dcurrent_index % len(endpoints)

Attempts:

3 left

💡 Hint

Common Mistakes

Forgetting parentheses causing wrong order of operations.

Not using modulo leading to index out of range.

The modulo operator (%) ensures the index wraps around to 0 after reaching the last endpoint, enabling round-robin selection.

2fill in blank

medium

Complete the code to check if an AI service endpoint is healthy before sending a request.

Prompt Engineering / GenAI

def is_healthy(endpoint):
    response = send_health_check_request(endpoint)
    return response.status_code == [1]

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

A200

B404

C500

D302

Attempts:

3 left

💡 Hint

Common Mistakes

Using error codes like 404 or 500 instead of 200.

Confusing redirect codes like 302 with success.

Status code 200 means the service is healthy and ready to accept requests.

3fill in blank

hard

Fix the error in the code that distributes requests evenly across AI service endpoints using modulo.

Prompt Engineering / GenAI

def distribute_request(request_id, endpoints):
    index = request_id [1] len(endpoints)
    return endpoints[index]

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

A%

B/

C*

D-

Attempts:

3 left

💡 Hint

Common Mistakes

Using division (/) instead of modulo (%).

Using multiplication (*) or subtraction (-) which do not wrap indices.

The modulo operator (%) is used to cycle through endpoints based on request_id.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps each AI service endpoint to its current load if the load is below 70%.

Prompt Engineering / GenAI

loads = {endpoint: [1] for endpoint, load in endpoint_loads.items() if load [2] 70}

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

Aload

B>

C<

Dendpoint

Attempts:

3 left

💡 Hint

Common Mistakes

Using '>' instead of '<' causing wrong filtering.

Mapping to 'endpoint' instead of 'load'.

The comprehension maps endpoints to their load only if load is less than 70%.

5fill in blank

hard

Fill all three blanks to create a function that selects the AI service endpoint with the lowest load from a dictionary.

Prompt Engineering / GenAI

def select_least_loaded(endpoint_loads):
    return min(endpoint_loads, key=lambda [1]: endpoint_loads[[2]]) if endpoint_loads else [3]

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

Aendpoint

CNone

Dload

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong variable names in lambda.

Not handling empty dictionary case.

The function uses min() with a key function to find the endpoint with the lowest load. Returns None if no endpoints.