-
|
While researching online, I came across the package Is there another way to use Google Vision for OCR without downgrading Docling? Thank you. |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment 1 reply
-
|
Hi @pradeept! I'm Dosu and I’m helping the docling team. There's no built-in Google Cloud Vision integration in Docling, but you don't need to rely on the third-party Docling uses a pluggy-based plugin architecture that lets you register custom OCR engines. The steps are:
The docling-surya plugin is a good reference implementation to follow — it's a third-party OCR plugin that follows exactly this pattern [4]. Your Google Vision plugin would work similarly, but instead of running a local model, you'd call the Google Cloud Vision API in the One note: there's a reported issue where the To reply, just mention @dosu. Docs are dead. Just use Dosu. |
Beta Was this translation helpful? Give feedback.
Hi @pradeept! I'm Dosu and I’m helping the docling team.
There's no built-in Google Cloud Vision integration in Docling, but you don't need to rely on the third-party
docling-google-ocrpackage (or downgrade Docling) — you can write your own OCR plugin using Docling's plugin system.Docling uses a pluggy-based plugin architecture that lets you register custom OCR engines. The steps are:
Create an options class extending
OcrOptionswith a uniquekinddiscriminator [1].Create an OCR model class extending
BaseOcrModeland implement the__call__()method to process page images and returnTextCellresults [2].Register your plugin via a setuptools entrypoint in your
pyproject.toml[3]:[…