I worked recently on an internal tool to achieve this kind of things, mostly plugging mistral OCR to gemini to extract structured data from documents. We then perform automated diffs too.
There seems to be an insane amount of competition in the "Intelligent Document Processing" market, like for instance parseur, whose founder is often on HN himself.
What do you think sets you apart from competition like :
1) Mistral document AI : depending on the model, it looks way cheaper than yours, OCR model pricing ranges from 0.001 to 0.004 EUR / page and they have structured output wired in the OCR API if needed (things then get fed to one of their LLMs) + EU-based and GDPR ready
2) parseur / rossum / docsumo / nanonets (which is YC 2017) ?
you show this in the first paragraph, before many other details
> We would love to welcome builders and tinkerers
Love? really .. cognitive dissonance here.. I read this as " we are security state friendly so we can get that big security state funding" plus "people who work for free like love, so we say that word"
coupled with the free-riding of VC capital on decades of open work, I just can not, not say this
I learnt a lot at Palantir, though always worked in commercial so no ties to security state (for the better or worse).
(Also side-note, we are working towards enabling frontier performance with smaller open models that allows our customers to protect their data. https://www.parsewise.ai/officeqa-sota )
And I do get genuine joy from helping our users, so love it is:)
I worked recently on an internal tool to achieve this kind of things, mostly plugging mistral OCR to gemini to extract structured data from documents. We then perform automated diffs too.
There seems to be an insane amount of competition in the "Intelligent Document Processing" market, like for instance parseur, whose founder is often on HN himself.
What do you think sets you apart from competition like : 1) Mistral document AI : depending on the model, it looks way cheaper than yours, OCR model pricing ranges from 0.001 to 0.004 EUR / page and they have structured output wired in the OCR API if needed (things then get fed to one of their LLMs) + EU-based and GDPR ready 2) parseur / rossum / docsumo / nanonets (which is YC 2017) ?
> implemented AI workflows at Palantir
you show this in the first paragraph, before many other details
> We would love to welcome builders and tinkerers
Love? really .. cognitive dissonance here.. I read this as " we are security state friendly so we can get that big security state funding" plus "people who work for free like love, so we say that word"
coupled with the free-riding of VC capital on decades of open work, I just can not, not say this
I learnt a lot at Palantir, though always worked in commercial so no ties to security state (for the better or worse). (Also side-note, we are working towards enabling frontier performance with smaller open models that allows our customers to protect their data. https://www.parsewise.ai/officeqa-sota )
And I do get genuine joy from helping our users, so love it is:)
Ah probably should add a link to our website: https://www.parsewise.ai/api
"retaining lineage"
"That is a great catch!"