Zerox

I used this approach extensively over the past couple of months with GPT-4 and GPT-4o while building https://hotseatai.com. Two things that helped me: 1. Prompt with examples. I…

In my own experiments I have had major failures where much of the text is fabricated by the LLM to the point where I just find it hard to trust even with great prompt…

I'm surprised by the name choice, there's a large company with an almost identical name that has products that do this. May be worth changing it sooner rather than later.…

Even if they don't sue, do you really want to deal with people getting confused and thinking you mean one of the many pre-existing OCR tools that Xerox produces? A search for…

> Are we really suggesting this issue is worth defending and spending resources on? Absolutely. Sure, sometimes non-competing products have the same name. Or products sold…

Traditional OCR neural networks like tesseract crucially they have strong measures of their accuracy levels, including when they employ dictionaries or the like to help with…

It's all fun and games until you need to prove something in court or to the tax office. I don't think that throwing an LLM into this mix helps.

In my own experiments I have had major failures where much of the text is fabricated by the LLM to the point where I just find it hard to trust even with great prompt…

It should be noted for some reason OpenAI prices GPT-4o-mini image requests at the same price as GPT-4o. I have a similar library but we found OpenAI has subtle OCR…

Check gpt-4o, gpt-4o-mini uses around 20 times more tokens for the same image: https://youtu.be/ZWxBHTgIRa0?si=yjPB1FArs2DS_Rc9&t=655

I'd be more curious to see the performance over local models like LLaVa etc.

I would really love something like this that could be run locally.

Very interesting project, thank you for sharing. Are you supporting the Batch API from OpenAI? This would lower costs by 50%. Many OCR tasks are not time-sensitive, so this might…

The problem I've not found one OCR solution to handle well is complex column based layouts in magazines. Perhaps one problem is that there are often images spanning anything from…

Does it also produce a confidence number?

It should be noted for some reason OpenAI prices GPT-4o-mini image requests at the same price as GPT-4o. I have a similar library but we found OpenAI has subtle OCR…

I think i'm missing something.. why would i pay to ocr the images when i can do it locally for free? Tesseract runs pretty well on just cpu, wouldn't even need something crazy…

I did this for images using Tesseract for OCR + Ollama for AI. Check it out, https://cluttr.ai Runs entirely in browser, using OPFS + WASM.

I am using AWS Textract + LLM (OpenAI/Claude) to read grocery receipts for <https://www.5outapp.com> So far, I have collected over 500 receipts from around 10 countries with 30…

Azure document AI accuracy I would categorize as high not "mid". Including hand writing. However for the $1.5/1000 pages, it doesn't include layout detection. The $10/1000 pages…

If you want to do document OCR/PDF text extraction with decent accuracy without using an LLM, do give LLMWhisperer[1] a try. Try with any PDF document in the playground -…