docling Javascript alternative?

Check out airesearch.js.org for a lot of similar pdf and html to markdown tools. It'd be great for a serverless and frontend js version so I can integrate the algorithms

Nov 02 '24 16:11 vtempest

If anyone wants to team up, I'd be up to creating a Typescript port of this for React.

Nov 03 '24 11:11 cr4yfish

Sounds good. It can also have a cite like airesearch.js.org

Nov 07 '24 08:11 vtempest

1 for javascript / typescript

Nov 09 '24 08:11 mtin79

I created a repo for it: docling-js

Nov 09 '24 14:11 cr4yfish

This will be really interesting, you can leverage this backend API which I built for Docling here docling-api

Nov 09 '24 18:11 drmingler

We want a tool that can run in serverless Node.js not something that needs to have a python server running.

It could be based on pdfjs like this https://github.com/vtempest/ai-research-agent/blob/master/src/extractor/url-to-content/pdf-to-content.js#L21

Nov 09 '24 19:11 vtempest

@vtempest @drmingler @cr4yfish This is not an issue we want to address here, but we do love the idea of it. Hence, we think it is great to convert it as a discussion.

Nov 11 '24 09:11 PeterStaar-IBM