Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Roe AI (YC W24) – AI-powered data warehouse to query multimodal data

news.ycombinator.com

Post reply on HN
Print view View original

31–39 of 39 posts

Re: Launch HN: Roe AI (YC W24) – AI-powered data warehouse to query multimodal data

#31

Post by 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?

Re: Launch HN: Roe AI (YC W24) – AI-powered data warehouse to query multimodal data

#32

Post by Irishsteve »

alpineidyll3 wrote: post #31

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 fidel…

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

Re: Launch HN: Roe AI (YC W24) – AI-powered data warehouse to query multimodal data

#34

Post by richardmeng »

namanyayg wrote: post #24

Congrats on the launch! What are you using to make the LLM understand a video file? Are you doing transcription + sending frames to a vision or is there a third party service for this?

We use Gemini to analyze the video in its raw format.

Re: Launch HN: Roe AI (YC W24) – AI-powered data warehouse to query multimodal data

#35

Post by richardmeng »

alpineidyll3 wrote: post #31

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 fidel…

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 richard@roe-ai.com, happy to evaluate your case and try to save that 200K :p

Re: Launch HN: Roe AI (YC W24) – AI-powered data warehouse to query multimodal data

#36

Post by richardmeng »

Irishsteve wrote: post #32
alpineidyll3 wrote: post #31

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 fidel…

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

I think by parse it means more like document understanding

Re: Launch HN: Roe AI (YC W24) – AI-powered data warehouse to query multimodal data

#37

Post by mnrozhkov »

alpineidyll3 wrote: post #31

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 fidel…

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 mikhail@iterative.ai if you're interested in sharing my findings.

Re: Launch HN: Roe AI (YC W24) – AI-powered data warehouse to query multimodal data

#39

Post by richardmeng »

nextworddev wrote: post #23

Why not just focus on the UI part and make it integrate with different data sources?

A lot of infrastructure work is needed to make the SQL experience seamless work for unstructured data. And at the most part we do fork the open core data warehouse and build on top of it.
Post reply on HN