Loading PDFs with PyPDFLoader in LangChain - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import PyPDFLoader from langchain.document_loaders.

LangChain

from langchain.document_loaders import [1]

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

APyPDFLoader

BPDFLoader

CTextLoader

DCSVLoader

Attempts:

3 left

💡 Hint

Common Mistakes

Importing PDFLoader instead of PyPDFLoader

Using TextLoader for PDFs

Forgetting to import the loader

You need to import PyPDFLoader to load PDF files using Langchain.

2fill in blank

medium

Complete the code to create a PyPDFLoader instance for the file 'sample.pdf'.

LangChain

loader = PyPDFLoader([1])

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

A'sample.txt'

B'data.csv'

C'document.docx'

D'sample.pdf'

Attempts:

3 left

💡 Hint

Common Mistakes

Using a non-PDF file name

Forgetting quotes around the filename

Using a wrong file extension

The loader needs the PDF file path as a string, here 'sample.pdf'.

3fill in blank

hard

Fix the error in the code to load documents from the loader.

LangChain

documents = loader.[1]()

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

Aload_data

Bload

Cload_and_split

Dload_documents

Attempts:

3 left

💡 Hint

Common Mistakes

Using load_and_split() which does not exist on PyPDFLoader

Using load_data() which does not exist

Using load_documents() which is invalid

The correct method to load documents from the loader is load().

4fill in blank

hard

Fill both blanks to create a PyPDFLoader and load documents from 'report.pdf'.

LangChain

loader = [1]([2])
documents = loader.load()

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

APyPDFLoader

B'report.pdf'

C'data.txt'

DPDFLoader

Attempts:

3 left

💡 Hint

Common Mistakes

Using PDFLoader instead of PyPDFLoader

Passing a non-PDF filename

Forgetting quotes around filename

You create the loader with PyPDFLoader and pass the PDF filename 'report.pdf'.

5fill in blank

hard

Fill all three blanks to import PyPDFLoader, create a loader for 'file.pdf', and load documents.

LangChain

from langchain.document_loaders import [1]
loader = [2]([3])
docs = loader.load()

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

APyPDFLoader

B'file.pdf'

CPDFLoader

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up import and instance names

Using wrong loader class

Passing wrong filename

Import PyPDFLoader, create an instance with 'file.pdf', then load.