Metadata preservation during splitting in LangChain - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the correct splitter class from LangChain.

LangChain

from langchain.text_splitter import [1]

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

ARecursiveCharacterTextSplitter

BCharacterTextSplitter

CTextSplitter

DMetadataSplitter

Attempts:

3 left

💡 Hint

Common Mistakes

Importing a non-existent class like MetadataSplitter.

Using a generic TextSplitter which is abstract.

The CharacterTextSplitter is the correct class to import for splitting text by characters while preserving metadata.

2fill in blank

medium

Complete the code to create a splitter that keeps metadata during splitting.

LangChain

splitter = CharacterTextSplitter(chunk_size=100, chunk_overlap=10, [1]=True)

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

Akeep_metadata

Badd_metadata

Cpreserve_metadata

Dreturn_metadata

Attempts:

3 left

💡 Hint

Common Mistakes

Using a wrong parameter name like preserve_metadata.

Not setting the parameter to True.

The keep_metadata parameter set to True ensures metadata is preserved during splitting.

3fill in blank

hard

Fix the error in the code to split documents while preserving metadata.

LangChain

docs = splitter.split_documents([1])

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

Adocuments

Btext

Cdoc

Ddocument_list

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a single string instead of a list of documents.

Using a singular variable name that is not a list.

The method split_documents expects a list of documents, so the variable should be documents.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps document texts to their metadata.

LangChain

{doc.page_content: doc[1] for doc in documents if doc[2] is not None}

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

A.metadata

B.content

C.text

D.data

Attempts:

3 left

💡 Hint

Common Mistakes

Using incorrect attributes like .content or .text.

Checking the wrong attribute in the condition.

Each document's page_content is the key, and doc.metadata is the value. The condition checks if doc.metadata is not None.

5fill in blank

hard

Fill all three blanks to create a list comprehension that extracts metadata keys from documents with metadata.

LangChain

[doc.metadata[1] for doc in documents if doc.metadata[2] and '[3]' in doc.metadata]

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

A.keys()

Bis not None

Csource

Dget('source')

Attempts:

3 left

💡 Hint

Common Mistakes

Using get('source') instead of checking key presence.

Not checking if metadata is None before accessing keys.

The code extracts keys from doc.metadata for documents where metadata exists and contains the key 'source'.