Hacker News new | past | comments | ask | show | jobs | submit

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

46maxmaio | | 30 | HN
loading story #42070829
loading story #42069925
serjester | parent | next
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.
ivanvanderbyl | parent | next
Congrats on the launch!

I’m curious to hear more about your pivot from AI workflow builder to document parsing. I can see correlations there, but that original idea seems like a much larger opportunity than parsing PDFs to tables in what is an already very crowded space. What verticals did you find have this problem specifically that gave you enough conviction to pivot?

loading story #42069121
zh2408 | parent | next
Saw reducto released benchmark related to your product: https://reducto.ai/blog/rd-tablebench Curious your take on the benchmark and how well midship performs
maxmaio | parent
The reducto guys are great! Their benchmark is not exactly how we would index our product because we extract into a user specified template vs. extracting into markdown (wysiwyg). That being said their eval aligns with our internal findings of commercial OCR offerings.
nostrebored | parent | next
How does your accuracy compare with VLMs like ColFlor and ColPali?
kietay | parent
We think about accuracy in 2 ways

Firstly as a function of the independent components in our pipeline. For example, we rely on commercial models for document layout and character recognition. We evaluate each of these and select the highest accuracy, then fine-tune where required.

Secondly we evaluate accuracy per customer. This is because however good the individual compenents are, if the model "misinterprets" a single column, every row of data will be wrong in some way. This is more difficult to put a top level number on and something we're still working on scaling on a per-customer basis, but much easier to do when the customer has historic extractions they have done by hand.

tlofreso | parent | next
Congrats on the launch... You're in a crowded space. What differentiates Midship? What are you doing that's novel?
kietay | parent
Cofounder here.

Great Q - there is definitely a lot of competition in dev tool offerings but less so in end to end experiences for non technical users.

Some of the things we offer above and beyond dev tools: 1. Schema building to define “what data to extract” 2. A hosted web app to review, audit and export extracted data 3. Integrations into downstream applications like spreadsheets

Outside of those user facing pieces, the biggest engineering effort for us has been in dealing with very complex inputs, like 100+ page PDFs. Just dumping into ChatGPT and asking nicely for the structured data falls over in both obvious (# input/output tokens exceeded) and subtle ways (e.g. missing a row in the middle of the extraction).

seany62 | parent | next
Are users able to export their organized data?
maxmaio | parent
Yes today we support exports to csv or excel from our web app!
hk1337 | parent | next
This is interesting.

Can you do this with emails?

tlofreso | parent | next
And if yes, be specific in answering. Emails are a bear! Emails can have several file types as attachemtns. Including: Other emails, Zip files, in-line images where position matters for context.
maxmaio | parent
We currently support pdf, docx, most image types (jpeg/jpg, png, heic), and excel.

saving the email as a pdf would work!

hubraumhugo | parent | next
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 becoming a commodity with powerful VLMs. Are you planning to focus on a specific industry, or how do you plan to differentiate?

loading story #42068776
mitchpatin | parent | next
TableFlow co-founder here - I don't want to distract from the Midship launch (congrats!) but did want to add my 2 cents.

We see a ton of industries/use-cases still bogged down by manual workflows that start with data extraction. These are often large companies throwing many people at the issue ($$). The vast majority of these companies lack technical teams required to leverage VLMs directly (or at least the desire to manage their own software). There’s a ton of room for tailored solutions here, and I don't think it's a winner-take-all space.

loading story #42067996
| parent | next
{"deleted":true,"id":42067529,"parent":42067242,"time":1730919865,"type":"comment"}
| parent | next
{"deleted":true,"id":42067521,"parent":42067242,"time":1730919834,"type":"comment"}
tlofreso | parent | next
"accurate document extraction is becoming a commodity with powerful VLMs"

Agree.

The capability is fairly trivial for orgs with decent technical talent. The tech / processes all look similar:

User uploads file --> Azure prebuilt-layout returns .MD --> prompt + .MD + schema set to LLM --> JSON returned. Do whatever you want with it.

loading story #42069425
loading story #42068181
maxmaio | parent
Yes there is definitely a boom in document related startups. We see our niche as focusing on non technical users. We have focused on making it easy to build schemas, an audit and review experience, and integrating into downstream applications.
loading story #42070339