RAG Text Chunking Tool with Overlap Preview

Splits source text into deterministic character, word, sentence, or Markdown-section chunks and previews boundaries, overlap, character counts, and approximate token counts before RAG embedding.

Runs locally in your browser
Chunking and token estimates run locally. No document content is uploaded, embedded or sent to a model.
Source document

Tune chunk boundaries before creating embeddings

Chunk size and overlap affect retrieval recall, context duplication and cost. This preview uses transparent heuristics; evaluate the resulting chunks against representative questions before production use.

Recent tools: