Document loaders in Prompt Engineering / GenAI - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main purpose of a document loader in AI?

Imagine you want to teach a computer to understand many documents. What does a document loader do in this process?

A It reads and converts documents into a format the AI can process.

B It evaluates the AI model's accuracy on document tasks.

C It generates new documents based on existing ones.

D It trains the AI model directly on raw text data.

💡 Hint

Think about the first step before teaching the AI anything.

A document loader's job is to read documents and prepare them so the AI can understand and work with the content.

❓ Predict Output

intermediate

Output of loading documents with a simple loader

Given this code snippet that loads text files, what will be the output?

Prompt Engineering / GenAI

documents = ['doc1.txt', 'doc2.txt']
loaded = [open(doc).read() for doc in documents]
print(len(loaded))

A 0

B 2

C Error: File not found

D 1

💡 Hint

How many files are being read?

The code reads two files and stores their content in a list, so the length is 2.

❓ Model Choice

advanced

Choosing the best document loader for PDFs

You want to load text from PDF files for your AI project. Which document loader is best suited?

A A loader that extracts text from PDF structure and layout.

B A loader that reads plain text files line by line.

C A loader that loads audio files as text.

D A loader that only reads images without text extraction.

💡 Hint

PDFs have special formatting and structure.

PDF loaders extract text considering PDF layout, which is necessary for accurate text extraction.

❓ Hyperparameter

advanced

Effect of chunk size in document loading

When loading large documents, you can split them into chunks. What happens if you set chunk size too small?

A The AI ignores the chunks and reads the whole document at once.

B The AI merges chunks into one large text automatically.

C The AI processes many small pieces, which may slow down training.

D The AI crashes because chunk size must be large.

💡 Hint

Think about how many pieces the AI must handle.

Small chunks increase the number of pieces, which can slow processing and increase overhead.

🔧 Debug

expert

Why does this document loader code raise an error?

Look at this code snippet and find why it raises an error:

docs = ['file1.txt', 'file2.txt']
loaded_docs = []
for doc in docs:
    with open(doc, 'r') as f
        loaded_docs.append(f.read())
print(len(loaded_docs))

A The print statement is outside the loop causing indentation error.

B The list 'docs' is empty, so no files to read.

C The variable 'loaded_docs' is not defined before appending.

D Missing colon ':' after 'with open(doc, 'r') as f' causes SyntaxError.

💡 Hint

Check the syntax of the 'with' statement.

The 'with' statement must end with a colon ':' to be valid Python syntax.