November 6th, 2024

Launch HN: Midship (YC S24) – Turn PDFs and Images into usable data

Midship, founded by Max, Kieran, and Aahel, specializes in extracting data from unstructured documents using OCR and language models, catering to both non-technical users and developers with subscription and API pricing.

Launch HN: Midship (YC S24) – Turn PDFs and Images into usable data

Midship, founded by Max, Kieran, and Aahel, specializes in extracting data from unstructured documents such as PDFs and images. Initially, the team aimed to create a natural language workflow builder as an alternative to platforms like Zapier. However, they pivoted to focus on document extraction after observing significant user interest in this feature. Many businesses still rely on PDFs and images for data, and while OCR technology exists, it often fails to provide clean, structured data. Midship addresses this issue by combining OCR with language models, enabling the extraction of specific fields and tables while correcting OCR errors and understanding context. The platform caters to two main user groups: non-technical users who utilize the web app for data extraction and developers who access the extraction API. Midship offers a subscription model for the web app and volume-based pricing for the API. The founders are eager to receive feedback from the community on their product.

- Midship focuses on extracting data from unstructured documents like PDFs and images.

- The platform combines OCR with language models to improve data extraction accuracy.

- It serves both non-technical users through a web app and developers via an API.

- The company offers a subscription model for the web app and volume-based pricing for the API.

- Feedback from the community is welcomed as the founders continue to develop their product.

Link Icon 20 comments
By @monkeydust - 5 months
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 task of automating webpage interactions systematically?

By @ctippett - 5 months
Congrats on the launch. I just sent y'all an email – I'm curious with what you can do with airline crew rosters.
By @crossroadsguy - 5 months
I would like a tool that converts x months of credit card bills into a csv (the txn table from across PDFs and pages in each PDF) or something very easily.
By @rco8786 - 5 months
Can you speak to the accuracy, particularly of numerical value extraction, that you’re achieving? I have a use case for pulling tabular financial data out of PDFs and accuracy is our main concern with using AI for that type of task.
By @abhgh - 5 months
Congratulations on the launch! Its a crowded space but I think there is place for a good and accurate tool!

Tried the examples - they seem tailored for specific document types. I have two questions around that: (a) is their a "best-effort" extraction you can perform or plan to support if you don't know the document type? (b) do you plan to support extraction from academic papers, i.e., potentially multi-column, with images, tables that are either single column or span two columns, equations, etc.?

By @fluxode - 5 months
Congrats on the launch! Just some friendly advice: financial documents such as quarterly earnings are actually highly structured via xrbl. If you are positioning the company as an unstructured -> structured process, then using these types of financial documents is probably not a great example even though everybody seems to do it.
By @nostrebored - 5 months
How does your accuracy compare with VLMs like ColFlor and ColPali?
By @misstercool - 5 months
Saw your demo video. Are you focusing on the finance sector primarily? It is a challenging industry IMO, requiring high accuracy and has strict privacy/security bar. How do you address these concerns?

Curious what are the biggest complain from your users? Are they willing to manually auditing the numbers in the table, make sure the output is 1. accurate. 2. formatted in the table they expected.

By @ivanvanderbyl - 5 months
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?

By @serjester - 5 months
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.
By @zh2408 - 5 months
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
By @drcongo - 5 months
I may or may not be the target audience, but it may help you to know a "book demo" link instead of a pricing page in the primary nav is a good heuristic shortcut for me to decide I'm not the target audience.
By @prithvi24 - 5 months
Whats pricing look like with HIPAA compliance?
By @seany62 - 5 months
Are users able to export their organized data?
By @hk1337 - 5 months
This is interesting.

Can you do this with emails?

By @tlofreso - 5 months
Congrats on the launch... You're in a crowded space. What differentiates Midship? What are you doing that's novel?
By @747-8F - 5 months
.
By @hubraumhugo - 5 months
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?