Metadata preservation during splitting in LangChain - Mini Project: Build & Apply

Metadata preservation during splitting

📖 Scenario: You are building a document processing tool using LangChain. You have a document with text and metadata. You want to split the document into smaller chunks but keep the metadata attached to each chunk.

🎯 Goal: Create a Python script that uses LangChain's CharacterTextSplitter to split a document while preserving its metadata in each chunk.

📋 What You'll Learn

Create a Document object with specific text and metadata

Create a CharacterTextSplitter with a chunk size of 10

Use the splitter to split the document into chunks

Ensure each chunk keeps the original metadata

💡 Why This Matters

🌍 Real World

When processing large documents for search or analysis, splitting text into smaller parts while keeping metadata helps maintain context and source information.

💼 Career

This skill is useful for developers working on document processing, search engines, chatbots, or any application that handles large text data with metadata.

1

Create the initial Document with text and metadata

Create a Document object named doc with the text 'Hello world! This is a test document.' and metadata {'source': 'test_source'}.

LangChain

# Create the Document object named doc with text and metadata
# Your code here

Hint

Use Document(page_content=..., metadata=...) to create the document.

2

Create a CharacterTextSplitter with chunk size 10

Create a CharacterTextSplitter object named splitter with chunk_size=10.

LangChain

from langchain.schema import Document

# Create the Document object named doc with text and metadata
doc = Document(
    page_content='Hello world! This is a test document.',
    metadata={'source': 'test_source'}
)

# Create the CharacterTextSplitter named splitter with chunk_size=10
# Your code here

Hint

Import CharacterTextSplitter from langchain.text_splitter and set chunk_size=10.

3

Split the document into chunks preserving metadata

Use splitter.split_documents with a list containing doc to create a variable chunks.

LangChain

from langchain.schema import Document
from langchain.text_splitter import CharacterTextSplitter

doc = Document(
    page_content='Hello world! This is a test document.',
    metadata={'source': 'test_source'}
)

splitter = CharacterTextSplitter(chunk_size=10)

# Split the document into chunks and store in chunks
# Your code here

Hint

Call split_documents on a list with doc inside.

4

Verify each chunk preserves the original metadata

Add a for loop iterating over chunks with variable chunk. Inside the loop, assign chunk.metadata to a variable meta.

LangChain

from langchain.schema import Document
from langchain.text_splitter import CharacterTextSplitter

doc = Document(
    page_content='Hello world! This is a test document.',
    metadata={'source': 'test_source'}
)

splitter = CharacterTextSplitter(chunk_size=10)

chunks = splitter.split_documents([doc])

# Loop over chunks and assign chunk.metadata to meta
# Your code here

Hint

Use for chunk in chunks: and inside assign meta = chunk.metadata.

Practice

1. What is the main benefit of preserving metadata when splitting documents in Langchain?

easy

A. It speeds up the splitting process.

B. It removes unnecessary text from documents.

C. It reduces the size of each chunk.

D. It keeps important context linked to each chunk.

Solution

1. Step 1: Understand what metadata means in this context

   Metadata is extra information about the document, like source or tags, that helps keep context.

2. Step 2: Recognize why preserving metadata is useful

   When splitting, keeping metadata ensures each chunk still knows where it came from and what it relates to.

3. Final Answer:

   It keeps important context linked to each chunk. -> Option D

4. Quick Check:

   Metadata preservation = keeps context [OK]

Hint: Metadata keeps context linked to chunks [OK]

Common Mistakes:

• Thinking metadata speeds splitting
• Confusing metadata with chunk size
• Believing metadata removes text

2. Which method in Langchain is used to split documents while preserving metadata?

easy

A. split_documents

B. preserve_metadata

C. chunk_text

D. split_text

Solution

1. Step 1: Recall the method name for splitting with metadata

   The method designed to split documents and keep metadata is called split_documents.

2. Step 2: Eliminate incorrect options

   Other options like preserve_metadata, chunk_text, and split_text are not valid Langchain methods for this purpose.

3. Final Answer:

   split_documents -> Option A

4. Quick Check:

   Method to split with metadata = split_documents [OK]

Hint: Remember method name: split_documents [OK]

Common Mistakes:

• Using split_text instead of split_documents
• Assuming preserve_metadata is a method
• Confusing chunk_text with splitting

3. Given this code snippet, what will be the metadata of the first chunk after splitting?

docs = [Document(page_content='Hello world', metadata={'source': 'file1'})]
splitter = RecursiveCharacterTextSplitter(chunk_size=5, chunk_overlap=0)
chunks = splitter.split_documents(docs)
print(chunks[0].metadata)

medium

A. null

B. {}

C. {'source': 'file1'}

D. {'chunk': 0}

Solution

1. Step 1: Understand the input document metadata

   The original document has metadata {'source': 'file1'}.

2. Step 2: Check if splitting preserves metadata

   The split_documents method keeps metadata for each chunk, so the first chunk keeps {'source': 'file1'}.

3. Final Answer:

   {'source': 'file1'} -> Option C

4. Quick Check:

   Metadata preserved = {'source': 'file1'} [OK]

Hint: Chunks keep original metadata unchanged [OK]

Common Mistakes:

• Expecting empty metadata after split
• Assuming metadata is lost or null
• Thinking chunk index is added to metadata

4. What is wrong with this code if the metadata is missing after splitting?

docs = [Document(page_content='Test text', metadata={'id': 123})]
splitter = RecursiveCharacterTextSplitter(chunk_size=4, chunk_overlap=1)
chunks = splitter.split_texts(docs)
print(chunks[0].metadata)

medium

A. Using split_texts instead of split_documents loses metadata.

B. Chunk size is too small to keep metadata.

C. Metadata key 'id' is invalid and removed.

D. Overlap must be zero to preserve metadata.

Solution

1. Step 1: Identify the method used for splitting

   The code uses split_texts which only splits text strings, not Document objects with metadata.

2. Step 2: Understand consequence on metadata

   Since split_texts works on strings, metadata is lost. The correct method to preserve metadata is split_documents.

3. Final Answer:

   Using split_texts instead of split_documents loses metadata. -> Option A

4. Quick Check:

   split_texts loses metadata [OK]

Hint: Use split_documents to keep metadata [OK]

Common Mistakes:

• Thinking chunk size affects metadata
• Believing metadata keys cause loss
• Assuming overlap affects metadata

5. You want to split a document into chunks of 100 characters with 20 characters overlapping, preserving metadata. Which code correctly achieves this?

hard

A. splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=20)
chunks = splitter.split_texts(docs)

B. splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=20)
chunks = splitter.split_documents(docs)

C. splitter = RecursiveCharacterTextSplitter(chunk_size=80, chunk_overlap=20)
chunks = splitter.split_documents(docs)

D. splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=0)
chunks = splitter.split_documents(docs)

Solution

1. Step 1: Set chunk size and overlap correctly

   The question asks for 100 characters chunk size and 20 characters overlap, so chunk_size=100 and chunk_overlap=20.

2. Step 2: Use the correct splitting method to preserve metadata

   To keep metadata, use split_documents method, not split_texts.

3. Final Answer:

   splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=20) chunks = splitter.split_documents(docs) -> Option B

4. Quick Check:

   Correct chunk size, overlap, and method = splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=20) chunks = splitter.split_documents(docs) [OK]

Hint: Match chunk size, overlap, and use split_documents [OK]

Common Mistakes:

• Using split_texts instead of split_documents
• Setting wrong chunk size or overlap
• Using zero overlap when asked for 20