Viewing profile — kapitalx

Fixed some bugs and much more stable now. https://github.com/doctly/switchboard/releases/tag/v0.0.8

Thank you. Yeah I looked at a few, another one is air.dev. The problem is they are recreating the actualy coding pane. Switchboard runs terminal directly.

https://doctly.ai We're building Doctly.ai - PDF Extraction with AI. We started out with document conversions to Markdown but quickly realized that most use cases were for JSON con…

Check it out at https://doctly.ai

This is approximately the approach we're taking also at https://doctly.ai , add to that a "multiple experts" approach for analyzing the image (for our 'ultra' version), and we get …

To be fair, they didn't include themselves at all in the graph.

In addition, gemini Pro 2.5 does really well with bounding boxes, but yeah not open source :(

If you're limited to open source models, that's very true. But for larger models and depending on your document needs, we're definitely seeing very high accuracy (95%-99%) for dire…

I'll dig deeper into your code, but scanning your post does look like your are addressing this. That's great. If I do find anything, I'll share with you for comments before I publi…

Exactly. You still have to be explicit in order to remove bias. Either by sorting the keys, or looking up specific keys. For arrays, I would say order still matters. For example wh…

Great list! I’ll definitely run your benchmark against Doctly.ai (our PDF-to-Markdown service) specially as we publish our workflow service, to see how we stack up. One thing I’ve …

Customers are willing to pay for accuracy compared to existing solutions out there. We started out in need of an accurate solution for a RAG product we were building, but none of t…

Looks to be API only for now. Documentation here: https://docs.mistral.ai/capabilities/document/

We've been getting great results with those aswell. But ofcourse there is always some chance of not getting it perfect, specially with different handwritings. Give it a try, no cre…

Yes I used the API. They have examples here: https://docs.mistral.ai/capabilities/document/ I used base64 encoding of the image of the pdf page. The output was an object that has t…

Great question. The language models are definitely beating the old tools. Take a look at Gemini for example. Doctly runs a tournament style judge. It will run multiple generations …

Haha for sure. Naming isn't just the hardest problem in computer science, it's always hard. But at some point you just have to pick something and move forward.

We'll definitely be doing more tests, but the results I got on the complex tests would result in a lower score and might not be worth the extra cost of the judgement itself. In our…