Parsr VS surya

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

This looks great! You might be interested in surya - https://github.com/VikParuchuri/surya (I'm the author). It does OCR (much more accurate than tesseract), layout analysis, and text detection.

The OCR is slow on CPU (working on it), but faster than tesseract (CPU-only) on GPU.

Happy to discuss more, feel free to email me (in profile).

You may want to try https://github.com/VikParuchuri/surya (I'm the author). I've only benchmarked against tesseract, but it outperforms it by a lot (benchmarks in repo). Happy to discuss.

You could also try https://github.com/VikParuchuri/marker for general PDF parsing (I'm also the author) - it seems like you're more focused on tables.