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.

Practice

1. What is the main purpose of caching in large language models (LLMs)?

easy

A. To save previous answers and avoid repeating work

B. To increase the size of the model

C. To change the model's training data

D. To make the model forget old information

Solution

1. Step 1: Understand caching concept

   Caching stores previous results so the system can reuse them instead of recalculating.

2. Step 2: Apply to LLMs context

   In LLMs, caching saves time and resources by reusing answers for repeated inputs.

3. Final Answer:

   To save previous answers and avoid repeating work -> Option A

4. Quick Check:

   Caching = Save and reuse answers [OK]

Hint: Caching means saving past answers to reuse them [OK]

Common Mistakes:

• Thinking caching changes model size
• Confusing caching with training data updates
• Believing caching deletes old info

2. Which Python tool is commonly used for simple caching in LLM applications?

easy

A. os.listdir

B. functools.lru_cache

C. math.sqrt

D. random.shuffle

Solution

1. Step 1: Identify caching tools in Python

   functools.lru_cache is a built-in decorator for caching function results.

2. Step 2: Check other options

   random.shuffle shuffles lists, math.sqrt calculates square roots, os.listdir lists files; none cache results.

3. Final Answer:

   functools.lru_cache -> Option B

4. Quick Check:

   Python caching tool = lru_cache [OK]

Hint: lru_cache is Python's simple caching decorator [OK]

Common Mistakes:

• Choosing random.shuffle as caching
• Confusing math functions with caching
• Picking file system functions

3. Given this Python code using a dictionary cache for LLM responses, what will be printed?

cache = {}
def get_response(input_text):
    if input_text in cache:
        return cache[input_text]
    response = f"Answer for {input_text}"
    cache[input_text] = response
    return response

print(get_response('hello'))
print(get_response('hello'))

medium

A. None\nAnswer for hello

B. Answer for hello\nNone

C. Error: KeyError

D. Answer for hello\nAnswer for hello

Solution

1. Step 1: Analyze first call get_response('hello')

   Cache is empty, so it creates 'Answer for hello', stores it, and returns it.

2. Step 2: Analyze second call get_response('hello')

   Input is in cache, so it returns cached 'Answer for hello' without recomputing.

3. Final Answer:

   Answer for hello Answer for hello -> Option D

4. Quick Check:

   Cache hit returns saved answer [OK]

Hint: Cache returns saved answer on repeated input [OK]

Common Mistakes:

• Assuming second call returns None
• Expecting error on repeated key
• Thinking cache clears automatically

4. This code tries to cache LLM outputs but has a bug. What is the error?

cache = {}
def get_response(input_text):
    if input_text in cache:
        return cache[input_text]
    response = f"Answer for {input_text}"
    cache = {input_text: response}
    return response

print(get_response('test'))
print(get_response('test'))

medium

A. Cache is reset each call, losing previous entries

B. generate_answer function is undefined

C. Syntax error in dictionary assignment

D. Infinite recursion in get_response

Solution

1. Step 1: Check cache update line

   cache = {input_text: response} replaces whole cache dict, losing old data.

2. Step 2: Understand effect on repeated calls

   Each call resets cache, so repeated inputs are not cached properly.

3. Final Answer:

   Cache is reset each call, losing previous entries -> Option A

4. Quick Check:

   Cache replaced, not updated [OK]

Hint: Use cache[key] = value to update, not assign new dict [OK]

Common Mistakes:

• Thinking generate_answer is missing
• Assuming syntax error in dict
• Believing recursion happens

5. You want to cache partial results of LLM calls to speed up responses when inputs share common prefixes. Which caching strategy best fits this need?

hard

A. Use random sampling to cache some inputs

B. Cache only full input strings as dictionary keys

C. Use a trie (prefix tree) to store cached outputs by input prefixes

D. Clear cache after every call to save memory

Solution

1. Step 1: Understand prefix sharing in inputs

   Inputs sharing prefixes can reuse partial results if cached by prefix.

2. Step 2: Identify suitable data structure

   A trie (prefix tree) efficiently stores and retrieves data by prefixes, ideal for this case.

3. Final Answer:

   Use a trie (prefix tree) to store cached outputs by input prefixes -> Option C

4. Quick Check:

   Prefix caching = trie structure [OK]

Hint: Trie caches shared prefixes efficiently [OK]

Common Mistakes:

• Caching only full inputs misses prefix reuse
• Random caching is inefficient
• Clearing cache wastes saved data