llm-chunk

Splits text into semantically coherent chunks by recursively applying a configurable hierarchy of delimiters (newlines, spaces, characters) until target chunk size is reached. The algorithm attempts to preserve semantic boundaries by preferring higher-level delimiters (paragraphs) before falling back to lower-level ones (individual characters), minimizing mid-sentence or mid-word splits that degrade LLM context quality.

Allows developers to specify target chunk size (in characters) and optional overlap between consecutive chunks, enabling fine-tuned control over context window utilization and retrieval redundancy. The implementation maintains chunk boundaries while respecting the configured overlap parameter, useful for ensuring query-relevant context appears in multiple chunks for improved RAG recall.

Implements text chunking with zero external npm dependencies, relying only on native JavaScript string and array operations. This minimizes bundle size, installation time, and supply-chain risk, making it suitable for embedding in larger applications or edge environments where dependency bloat is problematic.

Implements a multi-level delimiter strategy that prioritizes semantic boundaries: first attempts to split on paragraph breaks (double newlines), then single newlines, then spaces, and finally characters as a last resort. This hierarchical approach preserves sentence and paragraph integrity, reducing the likelihood of splitting mid-sentence which degrades LLM comprehension and RAG relevance.