Document loaders in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a text document using a document loader.

Prompt Engineering / GenAI

loader = TextLoader('[1]')
documents = loader.load()

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

Aexample.txt

Bload_text

Cread_file

Ddocument

Attempts:

3 left

💡 Hint

Common Mistakes

Using a function name instead of a file path.

Forgetting to put the file name in quotes.

The TextLoader requires the file path as a string to load the document correctly.

2fill in blank

medium

Complete the code to load a PDF document using the PDFLoader.

Prompt Engineering / GenAI

loader = PDFLoader('[1]')
docs = loader.load()

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

Aimage.png

Bdocument.docx

Cnotes.txt

Dfile.pdf

Attempts:

3 left

💡 Hint

Common Mistakes

Using a non-PDF file with PDFLoader.

Providing a file with the wrong extension.

PDFLoader expects a PDF file path to load the document properly.

3fill in blank

hard

Fix the error in the code to load a CSV file using CSVLoader.

Prompt Engineering / GenAI

loader = CSVLoader(file_path='[1]')
data = loader.load()

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

Adata.txt

Bdata.pdf

Cdata.csv

Ddata.docx

Attempts:

3 left

💡 Hint

Common Mistakes

Using a non-CSV file with CSVLoader.

Incorrect file extension causing loading failure.

CSVLoader requires a CSV file path to load data correctly.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that loads documents only if their length is greater than 100.

Prompt Engineering / GenAI

filtered_docs = {doc.id: doc for doc in documents if len(doc.[1]) [2] 100}

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

Apage_content

Bmetadata

C>

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'metadata' instead of 'page_content' for length.

Using '<' instead of '>' causing wrong filtering.

We check the length of the document's page_content and filter those greater than 100.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps document titles to their content if the content length is less than 500.

Prompt Engineering / GenAI

doc_map = {doc.[1]: doc.[2] for doc in docs if len(doc.[3]) < 500}

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

Ametadata['title']

Bpage_content

Dmetadata['author']

Attempts:

3 left

💡 Hint

Common Mistakes

Using author instead of title for keys.

Mixing up content and metadata in length check.

We use the document's title from metadata as key, page_content as value, and filter by content length less than 500.