Caching strategies for LLMs in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to store a generated response in the cache dictionary.

Prompt Engineering / GenAI

cache[[1]] = generated_response

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

Aprompt

Bresponse

Ccache_key

Dinput_text

Attempts:

3 left

💡 Hint

Common Mistakes

Using the response as the key instead of the prompt.

Using a variable not defined as the key.

The prompt is used as the key to store the generated response in the cache.

2fill in blank

medium

Complete the code to check if the prompt is already cached before generating a new response.

Prompt Engineering / GenAI

if [1] in cache:
    return cache[prompt]

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

Aresponse

Bprompt

Ccache_key

Dgenerated_response

Attempts:

3 left

💡 Hint

Common Mistakes

Checking for the response instead of the prompt.

Using an undefined variable in the condition.

We check if the prompt exists in the cache to avoid redundant generation.

3fill in blank

hard

Fix the error in the code to retrieve a cached response safely.

Prompt Engineering / GenAI

cached_response = cache.get([1], None)

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

Aprompt

Bresponse

Ccache_key

Dgenerated_response

Attempts:

3 left

💡 Hint

Common Mistakes

Using the response as the key in .get().

Using an undefined variable as the key.

The prompt is the key used to get the cached response safely with .get().

4fill in blank

hard

Fill both blanks to create a cache dictionary comprehension that stores prompt-response pairs only if the response length is greater than 10.

Prompt Engineering / GenAI

filtered_cache = {prompt: response for prompt, response in cache.items() if len(response) [1] [2]

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

A>

B10

C<

D5

Attempts:

3 left

💡 Hint

Common Mistakes

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

Using a smaller number like 5 instead of 10.

We filter cache items where the response length is greater than 10.

5fill in blank

hard

Fill all three blanks to implement a function that returns a cached response if available, otherwise generates, caches, and returns a new response.

Prompt Engineering / GenAI

def get_response(prompt):
    if prompt [1] cache:
        return cache[prompt]
    response = [2](prompt)
    cache[[3]] = response
    return response

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

Ain

Bgenerate_response

Cprompt

Dnot in

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'not in' instead of 'in' in the if condition.

Using wrong variable names for keys or functions.

We check if prompt is in cache, generate response if not, store it with prompt as key, then return it.