# Split a Document into Retrieval Chunks

> Chunk by tokens, sentences, paragraphs, a separator ladder or markdown headings — with overlap, token counts and embedding cost.

This chunker splits a document into retrieval-sized pieces using five strategies — a recursive separator ladder, sentence packing, paragraph packing, markdown heading sections, or fixed token windows — with configurable overlap. It reports the exact token count of every chunk, the size distribution, how much of the output is duplicated overlap, and what embedding the result would cost.

**URL:** https://convertto.tech/t/text-chunker-for-rag
**Category:** AI & LLM Tools (https://convertto.tech/c/ai-tools)
**Privacy:** Runs entirely in the browser; no upload
**Cost:** Free, no sign-up
**Last updated:** 2026-08-01

## Key facts

- **Common default:** 512 tokens with 64 tokens of overlap
- **Strategies:** Recursive, sentence, paragraph, markdown and fixed
- **Privacy:** Runs entirely in your browser — nothing is uploaded
- **Cost:** Free, unlimited, no sign-up

## How to use

1. Enter or paste your document.
2. Choose the strategy.
3. Set the chunk size.
4. Set the overlap.
5. Choose the count with.
6. Set the drop chunks under.
7. Choose the output as.
8. Press Run, then download the result when it is ready.

## FAQ

### What chunk size should I use?

400–800 tokens suits most documents. Go smaller when queries are narrow and factual, larger when an answer needs surrounding context. The real test is your own retrieval evaluation — chunk size is the single parameter most worth tuning in a RAG system.

### Why overlap at all?

Because a fact that straddles a boundary is unretrievable from either side. A definition at the end of one chunk and its use at the start of the next both score poorly against a query about the concept. Repeating 10–20% of the tokens fixes it cheaply.

### Is my document uploaded?

No. Chunking and token counting both run in your browser, which matters because the documents people chunk are usually internal.

## Sources

- [OpenAI — embeddings guide](https://platform.openai.com/docs/guides/embeddings) — OpenAI

## Related tools

- [Embedding Similarity Calculator](https://convertto.tech/t/embedding-similarity-calculator): Paste embedding vectors and get every pairwise cosine, dot product, Euclidean and Manhattan distance, ranked.
- [Semantic Search & Similarity](https://convertto.tech/t/semantic-search-tool): Embed a list of sentences with a real model and rank them by meaning — or find the near-duplicates in a list.
- [Chat with Any Document](https://convertto.tech/t/chat-with-document): Ask questions about a PDF, Word file, spreadsheet, CSV, Markdown or text file and get answers with the passage each came from.
- [Chat with PDF](https://convertto.tech/t/chat-with-pdf): Ask questions about any PDF and get answers with the page each one came from. The model runs in your browser — the file is never uploaded.
- [Context Window Calculator](https://convertto.tech/t/context-window-calculator): Paste a document and see which models it fits inside, how much of each window it fills, and what is left for the reply.
- [AI API Cost Calculator](https://convertto.tech/t/ai-api-cost-calculator): Work out what a prompt costs per call, per day and per month, and compare the same workload across every major model.
- [AI Writing Pattern Checker](https://convertto.tech/t/ai-writing-pattern-checker): Measure sentence-length variance, vocabulary richness, marker phrases and typographic tells, with per-sentence scoring.
- [Chat Export Formatter](https://convertto.tech/t/chat-export-formatter): Drop in an exported conversations file and get clean Markdown, HTML or plain text — one document per conversation.