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

Show HN: Open-source Rule-based PDF parser for RAG

github.com

Post reply on HN
Print view View original

11–20 of 33 posts

Re: Show HN: Open-source Rule-based PDF parser for RAG

#11

Post by mpeg »

dmezzetti wrote: post #7

Nice project! I've long used Tika for document parsing given it's maturity and wide number of formats supported. The XHTML output helps with chunking documents for RAG. Here's a couple examples: - https://neuml.hashnode.dev/build-rag-pipelines-with-txtai - https://neuml.hashnode.dev/extract-text-from-documents Disclaimer: I'm the primary author of txtai ( https://github.com/neuml/txtai ).

Off-topic, but do you know how Tika compares to other pdf parsing libraries? I was very unimpressed by pdfminer.six (what unstructured uses) as the layout detection seems pretty basic, it fails to parse multi column text, whereas MuPDF does it perfectly

Currently I'm using a mix of MuPDF + AWS Textract (for tables, mostly) but I'd love to understand what other people are doing

Re: Show HN: Open-source Rule-based PDF parser for RAG

#12

Post by infecto »

StrauXX wrote: post #3
guidedlight wrote: post #2

How does this differ from Azure Document Intelligence, or are they effectively the same thing?

Last I used it, Azure Document Intelligence wasn't all that smart about choosing split points. This seems to implement better heuristics.

What is a split point? I use Textract a lot and from my testing, always beats out any of the open source tooling to extract information. That could also be highly dependent on the document format.

Re: Show HN: Open-source Rule-based PDF parser for RAG

#13

Post by dmezzetti »

mpeg wrote: post #11
dmezzetti wrote: post #7

Nice project! I've long used Tika for document parsing given it's maturity and wide number of formats supported. The XHTML output helps with chunking documents for RAG. Here's a couple examples: - https://neuml.hashnode.dev/build-rag-pipelines-with-txtai - https://neuml.hashnode.dev/extract-text-from-documents Disclaimer: I'm the primary author of txtai ( https://github.com/neuml/txtai ).

Off-topic, but do you know how Tika compares to other pdf parsing libraries? I was very unimpressed by pdfminer.six (what unstructured uses) as the layout detection seems pretty basic, it fails to parse multi column text, whereas MuPDF does it perfectly Currently I'm using a mix of MuPDF + AWS Textract (for tables, mostly) but I'd love to understand what other people are doing

I don't have scientific metrics but I've found the quality much better than most. It does a pretty good job to pulling data from text and tables.

Re: Show HN: Open-source Rule-based PDF parser for RAG

#14

Post by batch12 »

infecto wrote: post #12
StrauXX wrote: post #3

Earlier quoted context omitted.

Last I used it, Azure Document Intelligence wasn't all that smart about choosing split points. This seems to implement better heuristics.

What is a split point? I use Textract a lot and from my testing, always beats out any of the open source tooling to extract information. That could also be highly dependent on the document format.

I think it is a reference to the place a larger document is split into chunks for calculating embeddings and storage.

Re: Show HN: Open-source Rule-based PDF parser for RAG

#17

Post by rmsaksida »

lmeyerov wrote: post #8

Tesseract OCR fallback sounds great! There are now a lot of file loaders for RAG (langchain, LLMindex, unstructured, ...), any reasons, like a leading benchmark score, to prefer this one?

Last time I tried Langchain (admittedly, that was ~6 months ago) the implementations for content extraction from PDFs and HTML files were very basic. Enough to get a prototype RAG solution going, but not enough to build anything reliable. This looks like a much more battle-tested implementation.

Re: Show HN: Open-source Rule-based PDF parser for RAG

#18

Post by asukla »

mpeg wrote: post #10
lmeyerov wrote: post #8

Tesseract OCR fallback sounds great! There are now a lot of file loaders for RAG (langchain, LLMindex, unstructured, ...), any reasons, like a leading benchmark score, to prefer this one?

I couldn't try this tool as it doesn't build on apple silicon (and there's no ARM docker image) However, I have a PDF parsing use-case that I tried those RAG tools for, but the output they give me is pretty low quality – it kinda works for RAG as the LLM can work around the issues but if you want to get higher quality responses with proper references and such I think the best way is to write your own rule-based parse…

To run the docker image on apple silicon, you can use the following command to pull - it will be slower but works: docker pull --platform linux/x86_64 ghcr.io/nlmatics/nlm-ingestor:latest

Re: Show HN: Open-source Rule-based PDF parser for RAG

#19

Post by ramoz »

mpeg wrote: post #10
lmeyerov wrote: post #8

Tesseract OCR fallback sounds great! There are now a lot of file loaders for RAG (langchain, LLMindex, unstructured, ...), any reasons, like a leading benchmark score, to prefer this one?

I couldn't try this tool as it doesn't build on apple silicon (and there's no ARM docker image) However, I have a PDF parsing use-case that I tried those RAG tools for, but the output they give me is pretty low quality – it kinda works for RAG as the LLM can work around the issues but if you want to get higher quality responses with proper references and such I think the best way is to write your own rule-based parse…

For me, PyMuPDF/fitz has been the best way to retain natural reading order and set dynamic enough rules to extract text in complex layouts.

None of the mentioned tools did this out of the box, none seemed easy to configured, all definitely hyped and marketed way beyond fitz though.

Re: Show HN: Open-source Rule-based PDF parser for RAG

#20

Post by asukla »

firtoz wrote: post #6

Thank you for sharing. Are there some example input output pairs somewhere?

You can use the library in conjunction with llmsherpa LayoutPDFReader.

Some examples are here with notebook: https://github.com/nlmatics/llmsherpa Here's another notebook from the repo with examples: https://github.com/nlmatics/nlm-ingestor/blob/main/notebooks...

Post reply on HN