LLM wrappers in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple LLM wrapper that calls the model's generate method.

Prompt Engineering / GenAI

response = llm.[1](prompt)

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

Afit

Bgenerate

Ctrain

Dcompile

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'train' or 'fit' instead of 'generate'.

Trying to compile the model instead of generating text.

The generate method is used to get the model's output for a given prompt.

2fill in blank

medium

Complete the code to initialize an LLM wrapper with a specific model name.

Prompt Engineering / GenAI

llm = LLMWrapper(model_name=[1])

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

ATrue

B12345

C'gpt-3.5-turbo'

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a number or boolean instead of a string.

Using None which means no model specified.

The model_name must be a string identifying the model, like 'gpt-3.5-turbo'.

3fill in blank

hard

Fix the error in the code to correctly call the LLM wrapper's generate method with a prompt.

Prompt Engineering / GenAI

output = llm.[1](input_text=prompt)

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

Atrain

Bpredict

Cfit

Dgenerate

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'predict' which is common in ML but not for LLM wrappers.

Using 'fit' or 'train' which are for model training.

The generate method accepts the prompt as input_text to produce output text.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps prompts to their generated outputs using the LLM wrapper.

Prompt Engineering / GenAI

results = {prompt: llm.[1](prompt) for prompt in prompts if len(prompt) [2] 0}

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

Agenerate

B>

C==

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using '==' instead of '>' to filter prompts.

Using a wrong method name instead of generate.

We use generate to get outputs and filter prompts with length greater than zero.

5fill in blank

hard

Fill all three blanks to create a list comprehension that generates outputs for prompts longer than 5 characters using the LLM wrapper.

Prompt Engineering / GenAI

outputs = [llm.[1](prompt) for prompt in prompts if len(prompt) [2] 5 and prompt.[3]('!')]

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

Agenerate

B>

Cendswith

Dstartswith

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'startswith' instead of 'endswith'.

Using '<' instead of '>' for length comparison.

We generate outputs for prompts longer than 5 characters that end with '!'.