Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Chonky – a neural approach for text semantic chunking

github.com

Post reply on HN
Print view View original

21–30 of 38 posts

Re: Show HN: Chonky – a neural approach for text semantic chunking

#21

Post by andai »

Training a splitter based on existing paragraph conventions is really cool. Actually, that's a task I run into frequently (trying to turn YouTube auto-transcript blob of text into readable sentences). LLMs tend to rewrite the text a bit too much instead of just adding punctuation.

As for RAG, I haven't noticed LLMs struggling with poorly structured text (e.g. the YouTube wall of text blob can just be fed directly into LLMs), though I haven't measured this.

In fact my own "webgrep" (convert top 10 search results into text and run grep on them, optionally followed by LLM summary) works on the byte level (gave up chunking words, sentences and paragraphs entirely): I just shove the 1kb before and after the match into the context. This works fine because LLMs just ignore the "mutilated" word parts at the beginning and end.

The only downside of this approach is that if I was the LLM, I would probably be unhappy with my job!

As for semantic chunking (in the context of, maximize the relevance of stuff that goes into the LLM, or indeed as a semantic search for the user), I haven't solved it yet, but I can share one amusing experiment: to find the relevant part of the text (having already returned a mostly-relevant big chunk of text), chop off one sentence at a time and re-run the similarity check! So you "distil" the text down to that which is most relevant (according to the embedding model) to the user query.

This is very slow and stupid, especially in real-time (though kinda fun to watch), but kinda works for the "approximately one sentence answers my question" scenario. A much cheaper approximation here would just be to embed at the sentence level as well as the page/paragraph level.

Re: Show HN: Chonky – a neural approach for text semantic chunking

#22

Post by serjester »

michaelmarkell wrote: post #19

It seems to me like chunking (or some higher order version of it like chunking into knowledge graphs) is the highest leverage thing someone can work on right now if trying to improve intelligence of AI systems like code completion, PDF understanding etc. I’m surprised more people aren’t working on this.

Chunking is less important in the long context era with most people just pulling in top 20 K. You obviously don’t want to butcher it, but you’ve got a lot of room for error.

Re: Show HN: Chonky – a neural approach for text semantic chunking

#23

Post by cckolon »

dmos62 wrote: post #17

Pretty cool. What use case did you have for this? Text with paragraph breaks missing seems fairly exotic.

This would be useful when chunking PDFs scanned with OCR. I've done that before and paragraph breaks were detected pretty inconsistently.

Re: Show HN: Chonky – a neural approach for text semantic chunking

#24

Post by lmeyerov »

serjester wrote: post #22
michaelmarkell wrote: post #19

It seems to me like chunking (or some higher order version of it like chunking into knowledge graphs) is the highest leverage thing someone can work on right now if trying to improve intelligence of AI systems like code completion, PDF understanding etc. I’m surprised more people aren’t working on this.

Chunking is less important in the long context era with most people just pulling in top 20 K. You obviously don’t want to butcher it, but you’ve got a lot of room for error.

Yeah exactly

We still want chunking in practice to avoid LLM confusion, undifferentiated embeddings, and handling large datasets at lower cost + large volumes. Large context means we can now tolerate multi-paragraph/page, so more like chunk by coherent section.

In theory we can do entire chapter/book, but those other concerns come in, so I only see more niche tools or talk-to-your-PDF do that.

At the same time, embedding is often a significant cost in above scenarios, so I'm curious about the semantic chunking overheads..

Re: Show HN: Chonky – a neural approach for text semantic chunking

#26

Post by hessdalenlight »

mathis-l wrote: post #10

You might want to take a look at https://github.com/segment-any-text/wtpsplit It uses a similar approach but the focus is on sentence/paragraph segmentation generally and not specifically focused on RAG. It also has some benchmarks. Might be a good source of inspiration for where to take chonky next.

[dead]

Re: Show HN: Chonky – a neural approach for text semantic chunking

#28

Post by michaelmarkell »

serjester wrote: post #22
michaelmarkell wrote: post #19

It seems to me like chunking (or some higher order version of it like chunking into knowledge graphs) is the highest leverage thing someone can work on right now if trying to improve intelligence of AI systems like code completion, PDF understanding etc. I’m surprised more people aren’t working on this.

Chunking is less important in the long context era with most people just pulling in top 20 K. You obviously don’t want to butcher it, but you’ve got a lot of room for error.

In our use-case we have many gigabytes of PDFs that contain some qualitative data but also many pages of inline pdf tables. In an ideal world we’d be “compressing” those embedded tables into some text that says “there’s a table here with these columns, if you want to analyze it you can use this , but basically the table is talking about X, here are the relevant stats like mean, sum, cardinality.”

In the naive chunking approach, we would grab random sections of line items from these tables because they happen to reference some similar text to the search query, but there’s no guarantee the data pulled into context is complete.

Re: Show HN: Chonky – a neural approach for text semantic chunking

#29

Post by legel »

Very cool!

The training objective is clever.

The 50+ filters at Ecodash.ai for 90,000 plants came from a custom RAG model on top of 800,000 raw web pages. Because LLM’s are expensive, chunking and semantic search for figuring out what to feed into the LLM for inference is a key part of the pipeline nobody talks about. I think what I did was: run all text through the cheapest OpenAI embeddings API… then, I recall that nearest neighbor vector search wasn’t enough to catch all relevant information, for a given query to be answered by an LLM. So, I remember generating a large number of diverse queries, which mean the same thing (e.g. “plant prefers full sun”, “plant thrives in direct sunlight”, “… requires at least 6 hours of light per day”, …) and then doing nearest neighbor vector search on all queries, and using the statistics to choose what to semantically feed into RAG.

Post reply on HN