drittich/SemanticSlicer

🧠✂️ SemanticSlicer — A smart text chunker for LLM-ready documents.

45
/ 100
Emerging

When working with large text documents, like articles, reports, or web pages, you often need to break them into smaller, meaningful pieces to prepare them for AI models. This tool takes your raw text (from files or piped input) and outputs a series of carefully segmented text chunks, preserving important structural elements like sentences and headings. It's designed for anyone preparing content for natural language processing tasks, especially those involving AI embeddings.

Use this if you need to reliably segment long text documents (e.g., Markdown, HTML, plain text) into smaller, semantically coherent chunks for use with large language models or AI embedding services.

Not ideal if you only need basic text splitting by character count, or if your primary goal is simple string manipulation rather than preparing text for AI processing.

content-preparation document-processing text-analysis knowledge-management
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

36

Forks

5

Language

C#

License

MIT

Last pushed

Feb 26, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/drittich/SemanticSlicer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.