What is parent-child (small-to-big) chunking?

It is a hierarchical RAG pattern where you embed and search over small, precise child chunks but return the larger parent chunk they belong to as context. You get accurate retrieval from the small chunk and rich context from the parent.

How is the splitting done?

The document is first cut into parent chunks at sentence and paragraph boundaries near the target parent size, then each parent is cut again into child chunks near the target child size. Boundaries are respected so chunks rarely split mid-sentence.

Does this measure tokens or characters?

Sizes here are in characters, which are fast and deterministic to compute in the browser. As a rough guide, one token is about four characters of English, so a 1,200-character parent is roughly 300 tokens.

Is my document uploaded anywhere?

No. All chunking happens locally in your browser. The document text never leaves the page and is not stored or transmitted.

Parent-Child Chunker Preview

Preview parent-child chunking before you index

Hierarchical or small-to-big retrieval is one of the most effective RAG upgrades: you search over small child chunks for precise matches, but feed the larger parent chunk they came from into the model so it has enough surrounding context to answer well. This tool lets you preview that split — set a parent size and a child size, paste your document, and see exactly how the parents and nested children come out before you commit to an indexing pipeline.

How it works

The document is split in two passes. The first pass walks the text by sentence and paragraph boundaries, accumulating until it reaches roughly the parent size, producing the large context chunks. The second pass repeats the same boundary-aware accumulation inside each parent using the child size, producing the small chunks you would actually embed and search. Every child records which parent it belongs to, so the preview shows a clean nested tree with character counts at each level. Because the splitter respects sentence ends, chunks rarely break in the middle of a thought.

Tips and notes

A common starting point is parents of roughly 1,000–2,000 characters with children of 200–400 characters, but the right values depend on your model’s context budget and how dense your source material is. If children come out larger than your target, your document has long unbroken sentences — shorten them or accept the overshoot. Watch the parent-to-child ratio: too many tiny children per parent inflates your index, while too few defeats the precision benefit. Tune here, then mirror the same sizes in your real LangChain, LlamaIndex or custom retriever configuration.