Chonky – a neural approach for text semantic chunking
TLDR: I’ve made a transformer model and a wrapper library that segments text into meaningful semantic chunks. The current text splitting approaches rely on heuristics (although one can use neural embedder to group semantically related sentences). I propose a fully neural approach to semantic chunking. I took the base distilbert model and trained it on a bookcorpus to split concatenated text paragraphs into original paragraphs. Basically it’s a token classification task. Model fine-tuning took day and a half on a 2x1080ti. The library could be used as a text splitter module in a RAG system or…
In plain words
Chonky is a neural text chunking tool that segments documents into meaningful semantic chunks using a transformer model trained on the BookCorpus dataset. Unlike traditional heuristic-based approaches, it uses a fully neural token classification method to identify natural paragraph boundaries in raw text. The library is designed for use in retrieval-augmented generation systems, transcript processing, and other applications requiring intelligent text segmentation. It leverages a fine-tuned DistilBERT model to improve upon conventional splitting methods.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
TLDR: I’ve made a transformer model and a wrapper library that segments text into meaningful semantic chunks. The current text splitting approaches rely on heuristics (although one can use neural embedder to group semantically related sentences). I propose a fully neural approach to semantic chunking. I took the base distilbert model and trained it on a bookcorpus to split concatenated text paragraphs into original paragraphs. Basically it’s a token classification task. Model fine-tuning took day and a half on a 2x1080ti. The library could be used as a text splitter module in a RAG system or for splitting transcripts for example. The usage pattern that I see is the following: strip all the markup tags to produce pure text and feed this text into the model. The problem is that although in theory this should improve overall RAG pipeline performance I didn’t manage to measure it properly. Other limitations: the model only supports English for now and the output text is downcased. Please give it a try. I'll appreciate a feedback. The Python library: https://github.com/mirth/chonky The transformer model: https://huggingface.co/mirth/chonky_distilbert_base_uncased_...
Does the same job
all alternatives →- CAChonky – a neural text semantic chunking goes multilingualOct 2025 · huggingface.co · ▲43
TLDR: I’m expanding the family of text-splitting Chonky models with new multilingual model. You can learn more about this neural approach in a previous post: https://news.ycombinator.com/item?id=43652968 Since the release of the first distilbert-based model I’ve released two more models based on a ModernBERT. All these models were pre-trained and fine-tuned primary on English texts. But recently mmBERT(https://huggingface.co/blog/mmbert) has been released. This model pre-trained on massive dataset that contains 1833 languages. So I had an idea of…
- CAChonkie – A Fast, Lightweight Text Chunking Library for RAG2024 · github.com · ▲199
I built Chonkie because I was tired of rewriting chunking code for RAG applications. Existing libraries were either too bloated (80MB+) or too basic, with no middle ground. Core features: - 21MB default install vs 80-171MB alternatives - 33x faster token chunking than popular alternatives - Supports multiple chunking strategies: token, word, sentence, and semantic - Works with all major tokenizers (transformers, tokenizers, tiktoken) - Zero external dependencies for basic functionality Technical optimizations: - Uses tiktoken with multi-threading for faster tokenization - Implements…
- IMI modeled the Voynich Manuscript with SBERT to test for structure2025 · github.com · ▲381
I built this project as a way to learn more about NLP by applying it to something weird and unsolved. The Voynich Manuscript is a 15th-century book written in an unknown script. No one’s been able to translate it, and many think it’s a hoax, a cipher, or a constructed language. I wasn’t trying to decode it — I just wanted to see: does it behave like a structured language? I stripped a handful of common suffix-like endings (aiin, dy, etc.) to isolate what looked like root forms. I know that’s a strong assumption — I call it out directly in the repo — but it helped clarify the clustering. From…
- ACAdvanced Chunking in JavaScript/TypeScript with Chonkie2025 · ▲10
Hi HN, We’re Shreyash and Bhavnick. We built Chonkie, an open-source library for advanced chunking and embedding of text and code. It was previously Python-only, but we just released a TypeScript version: https://github.com/chonkie-inc/chonkie-ts Many AI projects in JS/TS (like those using Vercel's AI SDK or Mastra) rely on basic text splitters. But better chunking = better retrieval = better performance. That’s what Chonkie is built for. Current native chunkers (in TS): - Code Chunker – handles Python, TypeScript, etc. - Recursive Chunker – rule-based, hierarchical…
- BTBeyond text splitting – improved file parsing for LLMs2024 · github.com · ▲206
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, April 2025
the whole month →- IB
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
- UC
Life & fun · 2025 · filiph.github.io
- IB
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
