Why Caching strategies for LLMs in Prompt Engineering / GenAI? - Purpose & Use Cases

The Big Idea

What if your AI could remember every answer and never waste time thinking twice?

The Scenario

Imagine you ask a large language model (LLM) the same question multiple times during a chat or app use. Each time, the model has to think from scratch and generate the answer again.

This is like repeatedly asking a friend the same question and waiting for them to think each time, even though they already know the answer.

The Problem

Manually re-running the model for repeated requests wastes time and computing power.

This causes slow responses and higher costs, especially when many users ask similar questions.

It also makes the experience frustrating because you wait longer for answers that could be instantly reused.

The Solution

Caching strategies store previous answers so the model can quickly reuse them without rethinking.

This is like writing down your friend's answers once and showing them instantly next time.

Caching saves time, reduces cost, and makes the system faster and smoother.

Before vs After

✗ Before

response = llm.generate(prompt)
print(response)

✓ After

response = cache.get(prompt) or llm.generate(prompt)
cache.store(prompt, response)
print(response)

What It Enables

Caching unlocks instant replies and efficient use of powerful LLMs, making AI interactions seamless and scalable.

Real Life Example

In a customer support chatbot, caching common questions like "What are your hours?" lets the bot answer instantly without calling the model every time.

Key Takeaways

Caching avoids repeating expensive LLM computations.

It speeds up responses and lowers costs.

It improves user experience by delivering instant answers.

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