What it does
Written by AI from the READMERuns OCR and AI workflows on documents from the right sidebar. It recognises PDFs and images with MinerU, PaddleOCR, Marker or an AI vision model, creates parent items, fills metadata, and writes summaries, translations and reader outlines. Mainly aimed at Chinese-language use. You supply your own OCR and AI services.
Scanned or unprocessed documents arrive in Zotero without text or metadata. This chains recognition, item creation, translation and summarising into one right-sidebar workflow.
What you'll need
Detected automaticallyWe haven't detected any setup requirements. That isn't the same as none: check the developer's README.
Where your data goes
We found: only contacts services we could identify. 7 addresses in 4 groups.
return { mode, baseURL: (read("url") || (mode === "cloud" ? "https://paddleocr.aistudio-app.com/api/v2/ocr" : "")).replace(/\/+$/, ""),baseURL(address){const base=String(address||'https://www.datalab.to/api/v1').trim().replace(/\/+$/,'').replace(/\/convert$/,'');if(new URL(base).protocol!=='https:')throw Error('Datalab 在线 API 必须使用 Hndpoint = settings.deeplPlan === "pro" ? "https://api.deepl.com/v2/translate" : "https://api-free.deepl.com/v2/translate";
Forks and copies
No forks listed.
The developer's response
Ratings and reviews
What people who use it say. This is separate from the grade, which is what the code does, and never changes it.
No ratings yet.