HackerTrans
TopNewTrendsCommentsPastAskShowJobs

pierre

no profile record

Submissions

Markdown Comes to Liteparse

llamaindex.ai
5 points·by pierre·23 dagen geleden·1 comments

Show HN: LiteParse v2, now in Rust 100x faster

github.com
15 points·by pierre·vorige maand·0 comments

Extract PDF text in the browser with LiteParse for the web

simonwillison.net
1 points·by pierre·3 maanden geleden·0 comments

Parsebench open leaderboard for PDF parsing

huggingface.co
1 points·by pierre·3 maanden geleden·0 comments

The Problem Isn't the Model, It's What It's Reading

ryanmcdonough.co.uk
1 points·by pierre·3 maanden geleden·0 comments

HuggingFace Papers

huggingface.co
2 points·by pierre·3 maanden geleden·0 comments

Show HN: ParseBench – Document parsing benchmark for AI agents

parsebench.ai
9 points·by pierre·3 maanden geleden·5 comments

Show HN: Git why – log your agent reasoning trace along your code

hexapode.github.io
11 points·by pierre·3 maanden geleden·1 comments

Liteparse

github.com
9 points·by pierre·3 maanden geleden·1 comments

LiteParse: Local document parsing for AI agents (Open source)

llamaindex.ai
2 points·by pierre·4 maanden geleden·2 comments

Show HN: Liteparse, an OSS universal fast document parser by LlamaParse team

github.com
2 points·by pierre·4 maanden geleden·1 comments

OlmOCR 2

github.com
5 points·by pierre·9 maanden geleden·1 comments

DeepSeek OCR

github.com
1,003 points·by pierre·9 maanden geleden·244 comments

comments

pierre
·23 dagen geleden·discuss
Liteparse now support markdown, beat markitdown in speed and accuracy, fully open source https://github.com/run-llama/liteparse
pierre
·3 maanden geleden·discuss
Yes, it evaluate using frontier model for parsing from all 3 major provider (google, anthropic and openai). It is also easy to extend to evaluaye new model (code/dataset is available)
pierre
·3 maanden geleden·discuss
Build a benchmark to evaluate how good document parser work on a dataset of 2000 PDFs manually annotated, trying to evaluate accross multiple dimensions: charts, tables, text styling, text correctness, and attribution.

The benchmark evaluate performance on full page (not selected part of the pages), and evaluaye different OSS / crobtier model / commercial approach.

For transparency it is available as a HF leaderbaord.

Paper: https://arxiv.org/abs/2604.08538
pierre
·3 maanden geleden·discuss
A fast and open source spatial text parser
pierre
·4 maanden geleden·discuss
A new document (including PDF) parser that outperform traditional tool such as PyPDF or MuTools.

Link to open source repo: https://github.com/run-llama/liteparse
pierre
·4 maanden geleden·discuss
Contributor here, happy to answer any questions!
pierre
·9 maanden geleden·discuss
Demo: https://olmocr.allenai.org/ Paper: https://arxiv.org/abs/2510.19817
pierre
·5 jaar geleden·discuss
I would love to see you success!

Do you have more technical details on your process? Did you publish anything? I try to dig more on your website but the content is rather thin (I learn more about what you are doing by reading your post here).

What are the by product? You mention cement and drinkable water, but there should be other byproduct to handle such as brime?