Top all-time · #6394
Datalab
Company blog · datalab.to/blogaidata
Datalab is the company blog at datalab.to, writing about ai and data. Since 2024, 12 different Hacker News readers have linked it 15 times, most often “Datalab – SOTA document intelligence models”. It is still writing: the last post was on 2026-10-29, and you can follow it by feed.
Too few sampled comments (12) to say how often HN recommends it.?
Why HN links it
HN readers link Datalab as a hosted and local option for OCR and PDF parsing, citing its Chandra model, the marker tool, and its serverless pricing. The comments are about the product rather than any writing.
Summarised by Claude from a sample of 12 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Transform unstructured content into precise, production-ready data. Datalab equips organizations to feed AI systems and automate workflows with dependable, audit-ready data.
Most-linked posts?
- Datalab – SOTA document intelligence models4 people · 5 mentions · first linked 2025-01-10
- /4 people · 5 mentions · first linked 2024-07-30
What Hacker News says?
Those are tricky! We've found https://www.datalab.to/ to be good for this @ thesynthesis.company
Comment linking /
on “Mistral OCR 3”Submitted Indra OCR: a 1M-parameter OCR model that reads 49 pages per second on CPU as a story · 39 points
HN discussionHello Vik, and thanks for your work on Surya, I really liked it once I found it, but my main issue now is the latency and hardware requirements, as accuracy could be fixed overtime for different page types. For example, I'm deploying tahweel to one of my webapps to allow limited number of users to run OCR on PDF files. I'm using a small CPU machine for this, deploying Surya will not be the same and I think you are f…
Comment linking /
on “Show HN: LLM-aided OCR – Correcting Tesseract OCR errors with LLMs”Submitted Our newest model: Chandra (OCR) as a story · 1 points
HN discussionDatalab | NYC | Full-time | Software Engineer and Head of Business Ops | $250k-$350k + 1.5-3% equity | https://www.datalab.to A significant % of useful data is locked away in tough-to-parse formats like PDFs. We build tools to extract it, like https://github.com/VikParuchuri/surya (15k Github stars), and https://github.com/VikParuchuri/marker (19k stars). We also run an inference API and product. We do meaningful re…
Comment linking /
on “Ask HN: Who is hiring? (January 2025)”Submitted Datalab – SOTA document intelligence models as a story · 1 points
HN discussionWow, Surya looks legit! https://www.datalab.to/
Comment linking /
on “Ask HN: What is the best method for turning a scanned book as a PDF into text?”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).
Comment linking /
on “Parsing PDFs (and more) in Elixir using Rust”Maker worked pretty well for me in my limited testing. They also have a hosted solution: https://www.datalab.to
Comment linking /
on “Ask HN: What are you using to parse PDFs for RAG?”I tested many open-source and hosted OCR models and Datalab Chandra was the most accurate. It can parse complex layouts, tables, handwriting, and formulas at a fraction of the cost of Claude/Gemini. Local: https://github.com/datalab-to/chandra Hosted: https://www.datalab.to Another decent option is GLM OCR. It's slightly less accurate but faster and cheaper. Local: https://github.com/zai-org/GLM-OCR Hosted: https://…
Comment linking /
on “OCR It – pull text out of un-copyable documents for your LLM”Congrats on the launch! How do you guys compare with Datalab with regards to accuracy? https://www.datalab.to/
Comment linking /
on “Launch HN: Reducto Studio (YC W24) – Build accurate document pipelines, fast”Rely | REMOTE (US/EST Preferred) | Full-time | Full-stack Engineer | https://tryrely.ai Rely is an AI-native platform reinventing due diligence and underwriting for multifamily real estate. We’re a small, remote-first team and the product is used by some of the largest operators in the industry. Last month, we processed over 2M pages of data. We’re hiring a full-stack engineer to help us scale fast and build on the…
Comment linking /blog/datalab-rely-case-study
on “Ask HN: Who is hiring? (February 2026)”Have you tried datalab-to/marker with the "Use LLM" option? They have a playground you can test it out on https://www.datalab.to/playground but I use their local CLI option: https://github.com/datalab-to/marker I just tried it on a fairly ugly TD Bank statement PDF I have and the markdown of the whole PDF (tables and all) is very accurate. Here is the config I use: marker_single --format_lines --use_llm --llm_servic…
Comment linking /playground
on “A Python tool to parse PDF statements from Poste Italiane”Hi, I'm a founder of Datalab. I'm not trying to take away from the launch (congrats), just wanted to respond to the specific feedback. I'm glad you found a solution that worked for you, but this is pretty surprising to hear - our new model, chandra, saturates handwriting-heavy benchmarks like this one - https://www.datalab.to/blog/saturating-the-olmocr-benchmark ,and our production models are more performant than OS…
Comment linking /blog/saturating-the-olmocr-benchmark
on “Launch HN: Pulse (YC S24) – Production-grade unstructured document extraction”How does this compare to DataLab ( https://www.datalab.to/ )
Comment linking /
on “Reducto releases Deep Extract”
