Text Chunker for RAG Pipelines
Paste long text and split it into retrieval-ready chunks. Choose a strategy, tune chunk size and overlap, and copy the result as a JSON array. Everything runs in your browser — nothing is uploaded.
About this tool
Splits text the way common RAG frameworks do: fixed-size windows, sentence or paragraph packing, or a recursive splitter that tries \n\n, then \n, then ". ", then spaces — the same order LangChain's RecursiveCharacterTextSplitter uses. Overlap is applied correctly: each chunk begins inside the tail of the previous one, so context isn't lost at boundaries. Token counts are rough estimates (~4 characters per token) — exact counts depend on the tokenizer your model uses.
Your text never leaves the page — there is no server, no upload, and no tracking of tool inputs. Chunking happens entirely in your browser, so it's safe to paste private documents.