Pinned Loading

1. chonkie chonkie Public

   🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

   Python 4.3k 296

2. pulpie pulpie Public

   Pareto-optimal models for cleaning the web — fast, encoder-based main-content extraction from HTML.

   HTML 5

3. chunk chunk Public

   🚀 The Fastest Chunker in the West 🇺🇸 Upto 1TB/s "semantic" chunking, quick and easy!

   Rust 351 21

4. chonkiejs chonkiejs Public

   🦛 CHONK your texts with Chonkie ✨ Type-friendly, light-weight, fast and super-simple chunking library

   TypeScript 352 11

5. catsu catsu Public

   🔌 Want one client library for all your embeddings? 💙 Choose Catsu! 🐱

   Rust 79 4

6. tokie tokie Public

   🍡 30x faster tokenization for every HuggingFace model

   Rust 45 4