semantic-chunk

Overview

Splits long text into chunks for RAG pipelines, with three modes: 'fixed' (hard char-count windows with overlap), 'sentence' (greedy pack of sentences up to chunk_size), 'paragraph' (split on blank lines, never pack across paragraphs). Returns each chunk's text, start/end character offsets, and char count. Use it as a semantic chunker, text splitter, RAG chunker, or sentence + paragraph aware chunking-with-overlap tool.

Health