RAG Text Chunker (split for Embeddings)

Split long text into chunks for Embedding / RAG pipelines. 4 strategies (chars / tokens / paragraphs / Markdown headings), overlap control, per-chunk visualization, JSON / JSONL / Markdown export.

100% Free No signup Browser-only Instant download 5 languages Dark mode

Related: 💰 Embeddings Pricing · 🪙 LLM Token Counter

Input text

Strategy

Chunk size chars Overlap same unit Prefer sentence boundaries Add metadata (index / start / end)

Chunks

Avg size

Max

⬇

❓ FAQ

Recommended chunk size?

Embedding models: 256-512 tokens (OpenAI text-embedding-3-small) / 512-1024 (Voyage, Cohere). Big enough to preserve meaning

How much overlap?

10-20% of chunk size is standard — prevents context loss at boundaries

Why heading strategy?

Semantic chunks → often higher retrieval precision than fixed size (esp. for docs / code / FAQ)

🐛 Found a bug or issue with this tool?

Free to use, no signup. Even just the steps to reproduce are helpful. Reports go directly to the operator and help us fix issues.

RAG Text Chunker (split for Embeddings)

❓ FAQ

Thanks for your report!