Zerox – Document OCR with GPT-mini
This started out as a weekend hack with gpt-4-mini, using the very basic strategy of "just ask the ai to ocr the document". But this turned out to be better performing than our current implementation of Unstructured/Textract. At pretty much the same cost. I've tested almost every variant of document OCR over the past year, especially trying things like table / chart extraction. I've found the rules based extraction has always been lacking. Documents are meant to be a visual representation after all. With weird layouts, tables, charts, etc. Using a vision model just make sense! In…
Zerox – Document OCR with GPT-mini launched on July 23, 2024 with 246 votes, #216 of 5,184 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 2 years on.
In plain words
Zerox is a document OCR tool that uses GPT-4 mini's vision capabilities to extract text, tables, and charts from images and PDFs. It's designed for users who need accurate document processing and have found traditional rule-based extraction methods inadequate for complex layouts. The tool performs comparably to Unstructured and Textract at similar costs, using AI vision models to handle the visual nature of documents more effectively than conventional approaches.
written from the facts on this page · September 2026
From the sources
OCR & Document Extraction using vision models. Contribute to getomni-ai/zerox development by creating an account on GitHub.
In the maker’s words, at launch
This started out as a weekend hack with gpt-4-mini, using the very basic strategy of "just ask the ai to ocr the document". But this turned out to be better performing than our current implementation of Unstructured/Textract. At pretty much the same cost. I've tested almost every variant of document OCR over the…
Does a similar job
all alternatives →
- BVBenchmarking VLMs vs. Traditional OCR2025 · getomni.ai · ▲146
Vision models have been gaining popularity as a replacement for traditional OCR. Especially with Gemini 2.0 becoming cost competitive with the cloud platforms. We've been continuously evaluating different models since we released the Zerox package last year (https://github.com/getomni-ai/zerox). And we wanted to put some numbers behind it. So we’re open sourcing our internal OCR benchmark + evaluation datasets. Full writeup + data explorer here: https://getomni.ai/ocr-benchmark Github: https://github.com/getomni-ai/benchmark Huggingface:…
OCR pipeline for ML training (tables, diagrams, math, multilingual)2025 · github.com · ▲170Hi HN, I’ve been working on an OCR pipeline specifically optimized for machine learning dataset preparation. It’s designed to process complex academic materials — including math formulas, tables, figures, and multilingual text — and output clean, structured formats like JSON and Markdown. Some features: • Multi-stage OCR combining DocLayout-YOLO, Google Vision, MathPix, and Gemini Pro Vision • Extracts and understands diagrams, tables, LaTeX-style math, and multilingual text (Japanese/Korean/English) • Highly tuned for ML training pipelines, including dataset generation and…
- YCYou can now cut and paste from scanned documents in Firefox2024 · ▲33
I just realized you can now open a PDF document in Firefox and select text directly from scanned images embedded in the document (so basically transparently reliable doing OCR). It is also surprisingly reliable, only sometimes mistaking a "oh" for a "zero" in a long string of numbers. I neither know when this was introduced nor who added this feature, but from the bottom of my heart: thank you, thank you, thank you, you have made my daily life a lot easier. I also haven't really explored the limits of the feature and under what conditions it starts failing, but: in my daily workflow so far,…
OCR Benchmark Focusing on Automation2025 · nanonets.com · ▲58OCR/Document extraction field has seen lot of action recently with releases like Mixtral OCR, Andrew Ng's agentic document processing etc. Also there are several benchmarks for OCR, however all testing for something slightly different which make good comparison of models very hard. To give an example, some models like mixtral-ocr only try to convert a document to markdown format. You have to use another LLM on top of it to get the final result. Some VLM’s directly give structured information like key fields from documents like invoices, but you have to either add business rules on top…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, July 2024
the whole month →
Many years ago, I made VJ softwares (to mix live visuals in clubs) for unexpected platforms like the Game Boy Advance, the Playstation 2 and the Raspberry Pi. This year, I’m back with a new web-app: Pikimov. Inspired by Photopea (a free Photoshop clone), I created this web-based motion design & video editor as an alternative to After Effects, to fill empty void. It's free, without signup, without cloud uploads (your files stay on your machine), and your projects are not used for AI models training.
AI · 2024 · pikimov.com
