Top all-time · #10946
Reducto: The Agentic Document Platform for AI Teams
Company blog · reducto.ai/blogaidata
Reducto: The Agentic Document Platform for AI Teams is the company blog at reducto.ai, writing about ai and data. Since 2024, 7 different Hacker News readers have linked it 13 times, most often “Evaluating Mistral OCR Against Gemini 2.0 Flash”. No feed was found, so read it on the site itself.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
HN readers link Reducto's site as an agentic document parsing and extraction platform for AI teams, often as a PDF/OCR tool. One comment cites its RD-TableBench benchmark post.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Reducto is the agentic document platform for leading AI teams—a comprehensive toolkit for every document task, built for enterprise performance at scale.
Most-linked posts?
- Evaluating Mistral OCR Against Gemini 2.0 Flash2 people · 3 mentions · first linked 2025-03-07
- /2 people · 2 mentions · first linked 2024-07-30
- Rd-TableBench – Accurately evaluating table extraction2 people · 2 mentions · first linked 2024-11-05
What Hacker News says?
We ran some benchmarks comparing against Gemini Flash 2.0. You can find the full writeup here: https://reducto.ai/blog/lvm-ocr-accuracy-mistral-gemini A high level summary is that while this is an impressive model, it underperforms even current SOTA VLMs on document parsing and has a tendency to hallucinate with OCR, table structure, and drop content.
Comment linking /blog/lvm-ocr-accuracy-mistral-gemini
on “Mistral OCR”Submitted Rd-TableBench – Accurately evaluating table extraction as a story · 29 points
HN discussionYes! We used our friends at Reducto ( https://reducto.ai/ ) for all document extraction and parsing (one of the best companies I've ever referred to YC ;) ) We did an initial parsing pass of all four DOJ document batches on Friday. This takes a raw PDF and returns chunks containing typed blocks—each with a type (Title, Text, Figure, etc.), bounding boxes, content, and confidence scores. For PDFs that were just scans…
Comment linking /
on “Show HN: Jmail – Google Suite for Epstein files”Submitted Evaluating Mistral OCR Against Gemini 2.0 Flash as a story · 15 points
HN discussionOne that I’ve seen recently is https://reducto.ai It appears to be an OCR wrapper.
Comment linking /
on “DeepSeek OCR”Submitted Reducto releases Deep Extract as a story · 5 points
HN discussionOpen Source Full Featured: https://github.com/Filimoa/open-parse/ [mine] https://docs.llamaindex.ai/en/stable/api_reference/node_pars... [text splitters lose page metadata] https://github.com/VikParuchuri/marker [strictly to markdown] Layout Parsers: These are collections of ML models to parse the core "elements" from a page (heading, paragraph, etc). You'll still need to work on combining these elements into querya…
Comment linking /
on “Ask HN: What are you using to parse PDFs for RAG?”Submitted Mistral OCR vs. Gemini Flash 2.0: Comparing VLM OCR Accuracy as a story · 5 points
HN discussionSaw reducto released benchmark related to your product: https://reducto.ai/blog/rd-tablebench Curious your take on the benchmark and how well midship performs
Comment linking /blog/rd-tablebench
on “Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data”Submitted We did a DB migration without logical replication – with zero downtime as a story · 4 points
HN discussionSubmitted Show HN: Reducto – A vision based document ingestion API for LLMs as a story · 3 points
HN discussionSubmitted Reducto Raises $108M to Shape the Future of AI Document Intelligence as a story · 2 points
HN discussionSubmitted Show HN: A SOTA chart-extraction system combining traditional CV and LVMs as a story · 1 points
HN discussion