Back
intermediate
Vector Databases & Embeddings

Chunking Strategies

Learn practical chunking strategies for RAG: fixed, recursive, semantic, parent-child, and table-aware chunking

15 min read· Chunking· Text Processing· Vector Databases· RAG

Chunking Strategies

Chunking is how you split documents into retrievable pieces.

If chunks are bad, retrieval is bad. If retrieval is bad, the final answer is bad.

The tradeoff

Chunk too smallChunk too large
missing contextnoisy retrieval
broken meaningexpensive prompts
weak citationsirrelevant text

Common strategies

StrategyUse when
fixed-sizequick baseline
recursivemarkdown, docs, headings
semantictopic boundaries matter
sliding windowlocal context matters
parent-childprecise search plus larger answer context
table-awarestructured documents

Good chunk metadata

Store:

  • document ID
  • title
  • section heading
  • page or line number
  • source URL
  • timestamp
  • permissions

Practical default

Start with:

  • split by headings
  • keep 300-800 token chunks
  • add 10-20 percent overlap only when needed
  • evaluate with real user queries

Knowledge check

Q1: Why does chunking affect citations?

The chunk is often the evidence unit the answer cites.

Q2: What should you measure?

Whether expected evidence appears in retrieved top results.