TimurKramar
Joined 2 years ago
Karma
12
Submissions
11
Member since
Mar 22
Recent submissions
Comment · 1 month ago
Comment · 3 months ago
yeah, the value is the price. And its not cheap because its open, its just the cost of running GPUs. Perhaps other providers have similar costs, just 1000% margins on top. this is just pure GPU cost with basically no markup.
But being open-weight model, there is no vendor-lockin. if you stop liking the api endpoint, or we were to increase prices, just run the model yourself elsewhere. So in a sense it is open. At least more than openAI or openrouter :)
Comment · 3 months ago
aws
Comment · 3 months ago
Comment · 3 months ago
Thats exactly what it is. Its just an api for PaddleOCR-VL-1.6. I wasn't trying to hide that, im sorry if it came out that way. 'Open' because its just an open-weight model under the hood.
Results come with confidences attached, so you know which fields need a double check and approval from a human. And this human-in-the-loop mechanism, where humans only check low confidence results,. can be used effectively to speed up existing backoffice operations that deal with document workflows.
You can try it right now at openparser.dev , or read this (https://www.openparser.dev/blog/how-openparser-uses-lineage) on how we built it and why one-shotting an llm to extract data from documents simply didn't work for us and our users.
oh and if you want to build with full lineage yourself, we opensourced it: https://github.com/eigenpal/openparser/tree/main/packages/li...