Directory loader for bulk documents in LangChain - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

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

LangChain

from langchain.document_loaders import [1]

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

ATextLoader

BFileLoader

CDirectoryLoader

DBulkLoader

Attempts:

3 left

💡 Hint

Common Mistakes

Using FileLoader instead of DirectoryLoader

Trying to import a non-existing class BulkLoader

The DirectoryLoader class is used to load multiple documents from a directory in Langchain.

2fill in blank

medium

Complete the code to create a DirectoryLoader instance for the folder 'docs'.

LangChain

loader = DirectoryLoader([1])

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

A'docs'

B'files'

C'documents'

D'data'

Attempts:

3 left

💡 Hint

Common Mistakes

Using a wrong folder name

Forgetting quotes around the folder name

The DirectoryLoader needs the path to the directory containing documents. Here, the folder is named 'docs'.

3fill in blank

hard

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

LangChain

documents = loader.[1]()

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

Afetch

Bload_data

Cload_documents

Dload

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'load_documents()' which does not exist

Using 'fetch()' which is incorrect

The correct method to load documents from DirectoryLoader is load().

4fill in blank

hard

Fill both blanks to filter only '.txt' files and load them from the directory.

LangChain

loader = DirectoryLoader('docs', glob='[1]')
documents = loader.[2]()

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

A*.txt

B*.pdf

Cload

Dload_files

Attempts:

3 left

💡 Hint

Common Mistakes

Using '*.pdf' to filter text files

Using 'load_files()' which is not a method

To load only text files, use the glob pattern '*.txt'. The method to load documents is 'load()'.

5fill in blank

hard

Fill all three blanks to create a DirectoryLoader for '.md' files in 'notes', load documents, and print the count.

LangChain

loader = DirectoryLoader('[1]', glob='[2]')
docs = loader.[3]()
print(len(docs))

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

Anotes

B*.md

Cload

Dload_all

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong folder name

Using '*.txt' instead of '*.md'

Using 'load_all()' which does not exist

The directory is 'notes', the glob pattern for markdown files is '*.md', and the method to load documents is 'load()'.