I added a page without signup so you can try my project
Hi! I am looking for feedback on my project.. UI/UX and to see how well it works for your use case! What you can try: - Receive an answer to any question on your most complex documents, with coordinates (most ask pdf only bring citations, not actual bboxes). - Batch questions. - Redaction detection (this is an experiment, which I think will pave the way for other endpoints, maybe signature...
Ninjadoc beats Google's Document Ai
I compared Google's Document Ai with my project on a 12 page document to get an answer and bounding boxes / coordinates. Google's Document Ai took about 1 minute to respond, didn't reply / didn't bring any coordinates back (I was expecting the checkbox to be highlighted) My tool identified the page number, answered the question and gave coordinates for the correct checkbox. We use a combination...
I am building a document api suite that gives you coordinates for every answer
I've been working on a document processing API suite that solves a few problems I encountered in my career.. - LLMs are great to provide answers on documents but not so great when you need bounding boxes for them. - OCRs give you bounding boxes but they don't understand context. - Mixing them both is a pain. So we are using vision models to solve this. The result is Ninjadoc, an easy to use api...
I am building a document api suite that gives you coordinates for every answer
I've been working on a document processing API suite that solves a few problems I encountered in my career.. - LLMs are great to provide answers on documents but not so great when you need bounding boxes for them. - OCRs give you bounding boxes but they don't understand context. - Mixing them both is a pain. So we are using vision models to solve this. The result is Ninjadoc, an easy to use api...
