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

Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data

news.ycombinator.com

Post reply on HN
Print view View original

31–40 of 66 posts

Re: Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data

#31

Post by maxmaio »

monkeydust wrote: post #28

Heres a real world use case, our company has moved our pension provider. This provider like the old one sucks at providing me with a good way to navigate through the 120 funds I can invest in. I want to create something that can paginate through 12 pages of html, perform clicks, download pdf fund factsheet, extract data from this factsheet into excel or CSV. Can this help? What's the best way to deal with the initial…

This is an interesting use case! We've heard similar stories from people dealing with pensions. Today we are ready to solve out of the box the extract data from a factsheet into excel or CSV step. Shoot me an email at max@midship.dev!

Re: Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data

#33

Post by arjvik »

serjester wrote: post #26

Honest question but how do you see your business being affected as foundational models improve? While I have massive complaints about them, Gemini + structured outputs is working remarkably well for this internally and it's only getting better. It's also an order of magnitude cheaper than anything I've seen commercially.

Curious - have you compared Gemini against Anthropic and OpenAI’s offerings here? Am needing to do something similar for a one-off task and simply need to choose a model to use.

Re: Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data

#34

Post by hermitcrab »

hubraumhugo wrote: post #7

Congrats on the launch! A quick search in the YC startup directory brought up 5-10 companies doing pretty much the same thing: - https://www.ycombinator.com/companies/tableflow - https://www.ycombinator.com/companies/reducto - https://www.ycombinator.com/companies/mindee - https://www.ycombinator.com/companies/omniai - https://www.ycombinator.com/companies/trellis At the same time, accurate document extraction is bec…

Do you know if there any good (pref C++) libraries for extracting data tables from PDFs?

Re: Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data

#35

Post by serjester »

arjvik wrote: post #33
serjester wrote: post #26

Honest question but how do you see your business being affected as foundational models improve? While I have massive complaints about them, Gemini + structured outputs is working remarkably well for this internally and it's only getting better. It's also an order of magnitude cheaper than anything I've seen commercially.

Curious - have you compared Gemini against Anthropic and OpenAI’s offerings here? Am needing to do something similar for a one-off task and simply need to choose a model to use.

Gemini is an awful developer experience but accuracy for OCR tasks is close to perfect. The pricing is also basically unbeatable - works out to 1k 10k pages per dollar depending on the model. OpenAI has subtle hallucinations and I haven’t profiled Anthropic.

Re: Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data

#37

Post by calufa »

monkeydust wrote: post #28

Heres a real world use case, our company has moved our pension provider. This provider like the old one sucks at providing me with a good way to navigate through the 120 funds I can invest in. I want to create something that can paginate through 12 pages of html, perform clicks, download pdf fund factsheet, extract data from this factsheet into excel or CSV. Can this help? What's the best way to deal with the initial…

Have you looked into tools https://www.multion.ai or https://www.browserbase.com.

Re: Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data

#38

Post by calufa »

erulabs wrote: post #23
hubraumhugo wrote: post #7

Congrats on the launch! A quick search in the YC startup directory brought up 5-10 companies doing pretty much the same thing: - https://www.ycombinator.com/companies/tableflow - https://www.ycombinator.com/companies/reducto - https://www.ycombinator.com/companies/mindee - https://www.ycombinator.com/companies/omniai - https://www.ycombinator.com/companies/trellis At the same time, accurate document extraction is bec…

Execution is everything. Not to drop a link in someone else’s HN launch but I’m building https://therapy-forms.com and these guys are way ahead of me on UI, polish, and probably overall quality. I do think there’s plenty of slightly different niches here, but even if there were not, execution is everything. Heck it’s likely I’ll wind up as a midship customer, my spare time to fiddle with OCR models is desperately lim…

Just a heads up, but I tried to signup but the button doesn't seem to work.

Re: Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data

#39

Post by arjvik »

serjester wrote: post #35
arjvik wrote: post #33

Earlier quoted context omitted.

Curious - have you compared Gemini against Anthropic and OpenAI’s offerings here? Am needing to do something similar for a one-off task and simply need to choose a model to use.

Gemini is an awful developer experience but accuracy for OCR tasks is close to perfect. The pricing is also basically unbeatable - works out to 1k 10k pages per dollar depending on the model. OpenAI has subtle hallucinations and I haven’t profiled Anthropic.

Thanks!
Post reply on HN