What you can do in DocRead
OCR
- Upload images (JPG, PNG, JPEG).
- Extract text in the OCR Workspace and copy / export the result.
- Default UI format is text. The API also supports json, csv, and docx.
- English is the language shown in the current UI.
Jobs
- History lists jobs with language, size, duration, status, and created time.
- OCR Job looks up a single UUID (for queued / async jobs).
- View, download, or delete a completed job.
Project & account
- Studio project selector (example: AI Project).
- Dark/light theme.
- You only see your own OCR jobs in History.
Reporting & control
- Dashboard: document counts, cluster health, API success vs fail.
- Audit Logs: timestamp, user, action, resource, status, IP, and details.
- Administration: users, role, storage quota, rate limit, max file size.
Optional: API
Same capabilities exist as REST (Swagger). See API if you are not using the Studio UI.