Question answering in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained question answering model using Hugging Face Transformers.

Prompt Engineering / GenAI

from transformers import pipeline
qa_pipeline = pipeline('[1]')

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

Atext-generation

Bsentiment-analysis

Cquestion-answering

Dtranslation

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'text-generation' instead of 'question-answering'.

Forgetting to import the pipeline function.

The pipeline function with the argument question-answering loads a model specialized for answering questions.

2fill in blank

medium

Complete the code to get the answer from the question answering pipeline.

Prompt Engineering / GenAI

context = "The Eiffel Tower is in Paris."
question = "Where is the Eiffel Tower located?"
result = qa_pipeline({'question': question, 'context': [1])

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

Aanswer

Bquestion

Cresult

Dcontext

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the question as context.

Passing the result variable instead of context.

The context key should be assigned the text where the answer can be found.

3fill in blank

hard

Fix the error in extracting the answer text from the result dictionary.

Prompt Engineering / GenAI

answer_text = result[[1]]

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

A'answer'

B'text'

C'output'

D'result'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'text' or 'output' instead of 'answer'.

Using a variable name instead of a string key.

The result dictionary from the pipeline contains the key 'answer' for the predicted answer text.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that filters answers longer than 5 characters.

Prompt Engineering / GenAI

filtered_answers = {q: a for q, a in answers.items() if len(a) [1] [2]

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

A>

B5

C<

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>'.

Using '==' which filters only answers of length exactly 5.

The comprehension keeps answers where the length is greater than 5 characters.

5fill in blank

hard

Fill all three blanks to create a function that returns the answer from the QA pipeline given question and context.

Prompt Engineering / GenAI

def get_answer([1], [2]):
    result = qa_pipeline({'question': [1], 'context': [2])
    return result[[3]]

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

Aquestion

Bcontext

C'answer'

Dresult

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up parameter names.

Returning the whole result instead of the answer string.

The function takes question and context as inputs, calls the pipeline, and returns the 'answer' from the result.