Metadata preservation during splitting in LangChain - Step-by-Step Execution

Concept Flow - Metadata preservation during splitting

Input Document with Metadata

↓

Split Document into Chunks

↓

Copy Metadata to Each Chunk

↓

Output: List of Chunks with Metadata

The document is split into smaller parts, and metadata is copied to each part to keep context.

Execution Sample

LangChain

doc = Document(page_content='Hello world', metadata={'source': 'file1'})
splitter = CharacterTextSplitter(chunk_size=5)
chunks = splitter.split_documents([doc])

Splits a document into chunks while keeping the original metadata on each chunk.

Execution Table

Step	Action	Input Document	Chunks Created	Metadata on Chunks
1	Start with one document	{content: 'Hello world', metadata: {'source': 'file1'}}	0	N/A
2	Split content into chunks of size 5	Content split into ['Hello', ' world']	2	N/A
3	Assign metadata to each chunk	Each chunk gets metadata {'source': 'file1'}	2	All chunks have {'source': 'file1'}
4	Output chunks with metadata	Chunks ready for use	2	Metadata preserved on all chunks

💡 All chunks created and metadata copied, splitting complete

Variable Tracker

Variable	Start	After Split	Final
doc	{content: 'Hello world', metadata: {'source': 'file1'}}	Same	Same
chunks	[]	[{content: 'Hello'}, {content: ' world'}]	[{content: 'Hello', metadata: {'source': 'file1'}}, {content: ' world', metadata: {'source': 'file1'}}]

Key Moments - 2 Insights

Why does each chunk need its own copy of metadata?

Because after splitting, each chunk is treated as a separate document. The metadata must be copied to keep the original context, as shown in step 3 of the execution_table.

Does splitting change the original document's metadata?

No, the original document's metadata stays the same. The metadata is copied to new chunk objects, not removed or altered from the original, as seen in variable_tracker.

Visual Quiz - 3 Questions

Look at the execution_table at step 2. How many chunks are created after splitting?

A 1

B 2

C 3

D 0

💡 Hint

Check the 'Chunks Created' column at step 2 in the execution_table.

According to variable_tracker, what is the metadata of the final chunks?

A Empty dictionary {}

B No metadata

C {'source': 'file1'}

D Metadata removed

💡 Hint

Look at the 'chunks' row under the 'Final' column in variable_tracker.

If the chunk size was increased to 11, how would the number of chunks change?

A Fewer chunks than before

B More chunks than before

C Same number of chunks

D No chunks created

💡 Hint

Refer to how chunk_size affects splitting in the execution_sample code.

Concept Snapshot

Metadata preservation during splitting:
- Input document has content + metadata
- Split content into smaller chunks
- Copy metadata to each chunk
- Output chunks keep original metadata
- Keeps context for each piece after splitting

Full Transcript

This visual execution shows how a document with metadata is split into smaller chunks while keeping the metadata on each chunk. First, the document content is split into parts based on chunk size. Then, the metadata from the original document is copied to each chunk so that context is preserved. The execution table traces each step from starting with one document, splitting content, assigning metadata, to outputting chunks with metadata. The variable tracker shows how the chunks array changes from empty to holding chunks with metadata. Key moments clarify why metadata copying is necessary and that the original document's metadata remains unchanged. The quiz tests understanding of chunk count, metadata presence, and chunk size effects. This helps beginners see how metadata preservation works during document splitting in Langchain.