Show HN: Rust-powered document chunker for RAG – 40x faster, O(1) memory

Source: Hacker News

Problem

LangChain’s chunker is pure Python and becomes a bottleneck at scale — it is slow and memory‑hungry on large document sets.

What Krira Chunker Does Differently

• Rust‑native processing — ~40× faster than LangChain’s implementation
• O(1) space complexity — memory usage stays flat regardless of document size
• Drop‑in Python API — works with any existing RAG pipeline
• Production‑ready — 17 versions shipped, 315+ installs

Installation

pip install krira-augment

Call for Feedback

I’d love brutal feedback from anyone building RAG systems — what chunking problems are you running into that this doesn’t solve yet?

Comments on Hacker News (Points: 14, Comments: 3)