Chatbot development basics in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to initialize a chatbot model using a pre-trained transformer.

Prompt Engineering / GenAI

model = [1]('gpt-3.5-turbo')

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

Ainitialize

BChatbotModel

Ctransformer

Dload_model

Attempts:

3 left

💡 Hint

Common Mistakes

Using a class name instead of a function to load the model.

Using an undefined function like 'initialize'.

The function to load a pre-trained model is usually called load_model or similar. Here, load_model is the correct choice to initialize the chatbot.

2fill in blank

medium

Complete the code to generate a response from the chatbot given a user input.

Prompt Engineering / GenAI

response = model.[1](user_input)

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

Afit

Btrain

Cgenerate

Dpredict

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'train' or 'fit' which are for model training, not response generation.

Using 'predict' which is common in ML but less typical for text generation.

To get a chatbot's reply, we use the generate method which produces text based on input.

3fill in blank

hard

Fix the error in the code to correctly preprocess user input by converting it to lowercase.

Prompt Engineering / GenAI

processed_input = user_input.[1]()

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

Alower

BtoLowerCase

Clowercase

Ddowncase

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'lowercase' which is not a method.

Using JavaScript style 'toLowerCase'.

In Python, the correct method to convert a string to lowercase is 'lower()'.

4fill in blank

hard

Fill both blanks to create a dictionary that maps user intents to responses.

Prompt Engineering / GenAI

responses = { [1]: 'Hello!', [2]: 'Goodbye!'}

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

A'greeting'

B'farewell'

C'hello'

D'bye'

Attempts:

3 left

💡 Hint

Common Mistakes

Using response words as keys instead of intent names.

Using informal keys like 'hello' or 'bye' which are less clear.

The keys should be user intents like 'greeting' and 'farewell' to map to appropriate responses.

5fill in blank

hard

Fill all three blanks to filter user messages that contain the word 'help' and convert them to lowercase.

Prompt Engineering / GenAI

filtered = [msg.[1]() for msg in messages if '[2]' in msg.[3]()]

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

Alower

Bhelp

Clowercase

DHelp

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'lowercase' which is not a valid method.

Checking for 'Help' with uppercase H which misses lowercase matches.

We convert messages to lowercase with 'lower()' and check if 'help' is in the lowercase message.