[alpineidyll3]

I am glad to see people focusing on this.

If this tool could parse drug patents and draw molecular structures with associated data, I know we would pay 200k/yr+ for that service, and there's a market for it.

In my own field, there's an incredibly important application to parse patents and scientific papers, but this would require specific image=>text models in order to get the required information out with high fidelity. Do you guys have plans to enable user supplied workflows where perhaps image patches can be sent to bespoke encoders, or finetunes?

[mnrozhkov]

You can use the https://github.com/iterative/datachain mentioned by @dmpetrov to predict and draw (in SaaS) a molecular structure. Not only can you predict, but you can also - enrich the PDF data with external PDB data, - calculate and evaluate sequence and structure-based predictions made by multiple custom models, - and optimize time and resources.

I created some simple examples in this area a few months ago. Feel free to email me at [e-mail] if you're interested in sharing my findings.

[richardmeng]

Today's large vision models like GPT-4o can parse the content heavy papers pretty well (and respect their structures).

Yah basically it allows you to send PDFs as image patches into GPT-4o model that workflow can be easily built.

Feel free to send me an email [e-mail], happy to evaluate your case and try to save that 200K :p

[Irishsteve]

When you say parse - do you mean for prior art or to generate ideas?

[richardmeng]

I think by parse it means more like document understanding