CherryHQ/cherry-studio

[Discussion]: Scanned PDFs cannot be read

Open

#15094 opened on May 14, 2026

View on GitHub
 (0 comments) (2 reactions) (0 assignees)TypeScript (45,688 stars) (4,338 forks)batch import
discussionhelp wantedneeds-more-info

Description

[!NOTE] This issue was translated by Claude.

Issue Checklist

  • I understand that issues are meant for feedback and problem-solving, not for venting, and I will provide as much detail as possible to help resolve the issue.
  • I have checked the pinned issues and searched through the existing open issues, closed issues, and discussions and did not find a similar suggestion.
  • I confirm that I am here to ask questions and discuss issues, not to report bugs or request features.

Platform

Windows

Version

v1.9.5

Your Question

I have integrated MinerU into the document processing settings, filled in the API, and can build the knowledge base. According to the documentation, I should be able to read scanned PDFs, but in reality, I cannot read them.

Context

Additional Information

Priority

High (Blocking progress)

Issue Checklist

  • I understand that issues are meant for feedback and problem-solving, not for venting, and I will provide as much detail as possible to help resolve the issue.
  • I have checked the pinned issues and searched through the existing open issues, closed issues, and discussions and did not find a similar suggestion.
  • I confirm that I am here to ask questions and discuss issues, not to report bugs or request features.

Platform

Windows

Version

v1.9.5

Your Question

我已经在文档处理中的文档处理里接入了MinerU，填写了API，已经可以构建知识库，按照说明应该可以读取扫描版了，但实际上无法读取。

Context

Additional Information

Priority

High (Blocking progress)

Contributor guide

Tech stack
typescriptpython
Domain
backenddocumentation
Issue type
bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
needs investigation
Prerequisites
MinerU API familiarityPDF processing basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30
Research direction
Investigate the MinerU integration in the document processing pipeline. Check the configuration settings, verify API key and endpoint correctness, and examine application logs for errors. Look at the MinerU documentation for scanned PDF support and ensure the correct API parameters are used. Consider adding more explicit error handling and user feedback when scanned PDF reading fails.