grobid VS Parsr

Interesting concept. Grobid tries to do the same https://github.com/kermitt2/grobid

I would suggest using grobid - a pipeline for extracting scientific PDFs into a common XML format which can be easily parsed. Grobid has quite a nice mature REST API that I've used in some of my own projects. It parses references and matches them to their DOI using the CrossRef API with a reported 95% F1 score. This should make your job pretty simple as far as I can tell - all you'd need to do is run your papers through grobid and then build a citation graph by comparing document DOIs.

Just use science-parse or GROBID. They have been designed for that exact reason.

- I ended up using Grobid, which converts the PDF to a very detailed XML format. The format is not a word processing format though, but a format specifically for representing scientific documents. I don't know, if it would, for example, contain tags about bold or italicized text. The tool is working really well, but since you probably cannot use the output XML format directly, it will need some postprocessing, which would be relatively simple with XML parsing libraries.

A few years ago I evaluated a few open source tools. In the end focused on GROBID. As usual, it depends on the type of document whether it works well for your use-case. There is some focus on it being "fast" (if that is a concern).

I'm part of the team that build LlamaParse. It's net improvement compare to other PDF->Structured Text extractors (I build several in the past, includig https://github.com/axa-group/Parsr).

For character extraction, LlamaParse use a mixture of OCR / character extraction from the PDF (it's the only parser I'm aware of that address some of the buggy PDF font issues, check the 'text' mode to see raw document before reconstruction), use a mixture of heuristic and Machine learning models to reconstruct the document.

Once plug with a Recursive retrieval strategy, allow you to get Sota result on question answering over complexe text (see notebook: https://github.com/run-llama/llama_parse/blob/main/examples/...).

AMA

Link to the Github Repository and pre defined Docker Compose Build file for Parsr

I would check out https://github.com/Unstructured-IO/unstructured (what lang chain uses) or https://github.com/axa-group/Parsr (probably what unstructured copied to get their startup off the ground lol)

Things I still want to try: - Parsr

I personally haven't used it yet, but I heard some good things about Parsr: https://github.com/axa-group/Parsr

Parsing PDFs is very non-trivial process. Google and Amazon parses are largely based on OCRing. There are some advanced state-of-the-art NN-based OCR approaches but they are not very stable, but a stable industry standard is Tesseract, and nice all-in-one open source tools that brings a ton of tools together is https://github.com/axa-group/Parsr . hope this helps