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

Parsing PDFs (and more) in Elixir using Rust

chriis.dev

Post reply on HN
Print view View original

1–10 of 18 posts

Re: Parsing PDFs (and more) in Elixir using Rust

#4

Post by cpursley »

I've been thinking a lot about how to accomplish various RAG things in Elixir (for LLM applications). PDF is one of the missing pieces, so glad to see work here. The really tricky part is not just parsing out the text (you can just call the pdftotext unix command line utility for that), but accurately pulling out things like complex tables, etc in a way that could be chunked/post processed in a useful way. I'd love to see something like Unstructured or Marker but in Rust (i.e., fast) that Elixir could NIF out to it. And maybe some kind of hybrid system that uses open llm models with vision capabilities. Ref:

- https://github.com/Unstructured-IO/unstructured

- https://github.com/VikParuchuri/marker

Re: Parsing PDFs (and more) in Elixir using Rust

#5

Post by cpursley »

cpursley wrote: post #4

I've been thinking a lot about how to accomplish various RAG things in Elixir (for LLM applications). PDF is one of the missing pieces, so glad to see work here. The really tricky part is not just parsing out the text (you can just call the pdftotext unix command line utility for that), but accurately pulling out things like complex tables, etc in a way that could be chunked/post processed in a useful way. I'd love t…

Well derp, I should have read the linked extractous repo. This looks like the extract solution I've been after (see what I did there).

https://github.com/yobix-ai/extractous

Re: Parsing PDFs (and more) in Elixir using Rust

#6

Post by vikp »

cpursley wrote: post #4

I've been thinking a lot about how to accomplish various RAG things in Elixir (for LLM applications). PDF is one of the missing pieces, so glad to see work here. The really tricky part is not just parsing out the text (you can just call the pdftotext unix command line utility for that), but accurately pulling out things like complex tables, etc in a way that could be chunked/post processed in a useful way. I'd love t…

Hey, I'm the author of marker - thanks for sharing. Most of the processing time is model inference right now. I've been retraining some models lately onto new architectures to improve speed (layout, tables, LaTeX OCR).

We recently integrated gemini flash (via the --use_llm flag), which maybe moves us towards the "hybrid system" you mentioned. Hoping to add support for other APIs soon, but focusing on improving quality/speed now.

Happy to chat if anyone wants to talk about the difficulties of parsing PDFs, or has feedback - email in profile.

Re: Parsing PDFs (and more) in Elixir using Rust

#7

Post by bustylasercanon »

cpursley wrote: post #5
cpursley wrote: post #4

I've been thinking a lot about how to accomplish various RAG things in Elixir (for LLM applications). PDF is one of the missing pieces, so glad to see work here. The really tricky part is not just parsing out the text (you can just call the pdftotext unix command line utility for that), but accurately pulling out things like complex tables, etc in a way that could be chunked/post processed in a useful way. I'd love t…

Well derp, I should have read the linked extractous repo. This looks like the extract solution I've been after (see what I did there). https://github.com/yobix-ai/extractous

Yeah I could maybe highlight how good that library is in here

Re: Parsing PDFs (and more) in Elixir using Rust

#8

Post by cpursley »

vikp wrote: post #6
cpursley wrote: post #4

I've been thinking a lot about how to accomplish various RAG things in Elixir (for LLM applications). PDF is one of the missing pieces, so glad to see work here. The really tricky part is not just parsing out the text (you can just call the pdftotext unix command line utility for that), but accurately pulling out things like complex tables, etc in a way that could be chunked/post processed in a useful way. I'd love t…

Hey, I'm the author of marker - thanks for sharing. Most of the processing time is model inference right now. I've been retraining some models lately onto new architectures to improve speed (layout, tables, LaTeX OCR). We recently integrated gemini flash (via the --use_llm flag), which maybe moves us towards the "hybrid system" you mentioned. Hoping to add support for other APIs soon, but focusing on improving qualit…

Very cool, any plans for a dockerized API of marker similar to what Unstructured released? I know you have a very attractively priced serverless offering (https://www.datalab.to) but having something to develop against locally would be great (for those of us not in the Python world).

Re: Parsing PDFs (and more) in Elixir using Rust

#9

Post by vikp »

cpursley wrote: post #8
vikp wrote: post #6

Earlier quoted context omitted.

Hey, I'm the author of marker - thanks for sharing. Most of the processing time is model inference right now. I've been retraining some models lately onto new architectures to improve speed (layout, tables, LaTeX OCR). We recently integrated gemini flash (via the --use_llm flag), which maybe moves us towards the "hybrid system" you mentioned. Hoping to add support for other APIs soon, but focusing on improving qualit…

Very cool, any plans for a dockerized API of marker similar to what Unstructured released? I know you have a very attractively priced serverless offering ( https://www.datalab.to ) but having something to develop against locally would be great (for those of us not in the Python world).

It's on the list to build - been focusing on quality pretty heavily lately.

Re: Parsing PDFs (and more) in Elixir using Rust

#10

Post by constantinum »

cpursley wrote: post #4

I've been thinking a lot about how to accomplish various RAG things in Elixir (for LLM applications). PDF is one of the missing pieces, so glad to see work here. The really tricky part is not just parsing out the text (you can just call the pdftotext unix command line utility for that), but accurately pulling out things like complex tables, etc in a way that could be chunked/post processed in a useful way. I'd love t…

For instace Llamaparse(https://docs.llamaindex.ai/en/stable/llama_cloud/llama_parse...)uses LLMs for pdf text extraction, but the problem is hallucination. e.g > https://github.com/run-llama/llama_parse/issues/420

There is also LLMWhisperer that preserves the layout(tables, checkboxes, forms)and hence the context. https://pg.llmwhisperer.unstract.com/

Post reply on HN