Loading web pages with WebBaseLoader in LangChain - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the WebBaseLoader class from langchain.document_loaders.

LangChain

from langchain.document_loaders import [1]

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

AWebBaseLoader

BWebLoader

CBaseLoader

DWebPageLoader

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'WebLoader' or 'WebPageLoader' which do not exist.

Importing from the wrong module.

The class to load web pages in LangChain is WebBaseLoader. Importing it correctly allows you to use it to fetch web content.

2fill in blank

medium

Complete the code to create a WebBaseLoader instance for the URL 'https://example.com'.

LangChain

loader = WebBaseLoader([1])

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

A'example.com'

B'http://example.com'

C'https://example.com'

Dhttps://example.com

Attempts:

3 left

💡 Hint

Common Mistakes

Omitting quotes around the URL.

Using 'http://' instead of 'https://'.

The URL must be a string including the scheme 'https://'. So the correct argument is 'https://example.com'.

3fill in blank

hard

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

LangChain

docs = loader.[1]()

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

Aget_docs

Bload

Cfetch

Dload_data

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'load_data' or 'fetch' which are not valid methods.

Trying to access a property instead of calling a method.

The correct method to load documents from a WebBaseLoader instance is load(). Other method names do not exist and cause errors.

4fill in blank

hard

Fill both blanks to create a WebBaseLoader for 'https://openai.com' and load documents.

LangChain

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

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

AWebBaseLoader

B'https://openai.com'

C'openai.com'

DWebLoader

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'WebLoader' which does not exist.

Passing URL without 'https://'.

You must use the class WebBaseLoader and pass the full URL string including 'https://'.

5fill in blank

hard

Fill all three blanks to import WebBaseLoader, create a loader for 'https://docs.python.org', 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'

AWebBaseLoader

B'https://docs.python.org'

D'docs.python.org'

Attempts:

3 left

💡 Hint

Common Mistakes

Using URL without 'https://'.

Importing or instantiating wrong class names.

First, import WebBaseLoader. Then create an instance with the full URL string including 'https://'. Finally, call load() to get documents.