ntkris
Joined 6 years ago
Karma
18
Submissions
14
Member since
Nov 10
Recent submissions
Comment · 1 year ago
This is awesome. Have you seen / heard of any benchmarks where the data is actually a structured JSON vs. markdown?
Comment · 2 years ago
Yes, we needed to solve the problem for our other product (https://kili.so). We spent a lot of time getting accuracy up for dense and multi-page invoices. Then realised other teams have this need as well so decided to ship the API.
On the accuracy point, given our work so far we believe we are best in class in terms of accuracy for document extraction. We've also set up a system of evaluations internally that allow us to keep iterating and improving (hence us mentioning that we want to continue working on it).
Comment · 2 years ago
Not off topic at all!
I can only speak to our experience. Once you get under the hood, you find that this is a hard problem to solve.
There are also a lot of workflows that involve documents in every sector and every function. In other words, the opportunity is massive.
For our product, our customers are either internal engineering teams or folks building products that require document extraction but don’t want to invest time in it.
Comment · 2 years ago
Are you just looking to meet other folks building or have a specific goal in mind (e.g. finding a cofounder)? I can recommend accordingly
Comment · 2 years ago
Not yet, but we're open to creating one
Comment · 2 years ago
We're focussed on company operations (accounting, procurement etc).
The tool is totally self serve and does allow you to set up, upload and access documents.
We clearly need to call that out more so will add this to the landing page
Comment · 2 years ago
Great feedback, we will make this more clear
Comment · 2 years ago
We are seeing a bunch of interest for scraping related use cases and document processing (eg. automatically processing invoices that are emailed in)