First interaction with GenAI APIs - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the GenAI client library.

Prompt Engineering / GenAI

from genai import [1]

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

APipeline

BModel

CClient

DTokenizer

Attempts:

3 left

💡 Hint

Common Mistakes

Importing Model instead of Client

Importing Pipeline which is not needed here

The Client class is used to interact with GenAI APIs, so we import it first.

2fill in blank

medium

Complete the code to create a GenAI client with your API key.

Prompt Engineering / GenAI

client = Client(api_key=[1])

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

A'your_api_key_here'

Byour_api_key_here

CAPI_KEY

D12345

Attempts:

3 left

💡 Hint

Common Mistakes

Forgetting quotes around the API key

Using a number instead of a string

The API key must be a string, so it needs quotes around it.

3fill in blank

hard

Fix the error in the code to generate text using the client.

Prompt Engineering / GenAI

response = client.generate(model='gpt-4', prompt=[1])

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

A['Hello, how are you?']

BHello, how are you?

CNone

D'Hello, how are you?'

Attempts:

3 left

💡 Hint

Common Mistakes

Passing prompt without quotes

Passing a list instead of a string

The prompt must be a string, so it needs quotes around it.

4fill in blank

hard

Fill both blanks to extract the generated text from the response.

Prompt Engineering / GenAI

generated_text = response.[1][0].[2]

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

Agenerations

Btext

Cchoices

Dcontent

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'choices' instead of 'generations'

Using 'content' instead of 'text'

The response object has a generations list, and each generation has a text attribute with the output.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps prompts to their generated texts.

Prompt Engineering / GenAI

results = { [1]: response.[2][0].[3] for prompt in prompts }

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

Aprompt

Bgenerations

Ctext

Dresponse

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'response' as key instead of 'prompt'

Using 'content' instead of 'text'

Using 'choices' instead of 'generations'

This comprehension creates a dictionary where each prompt maps to the first generated text in generations.