Document Processing

Simply put:This is Cherry Studio's central configuration for reading "PDF / complex-layout documents" as clean, structured text.

PDFs with tables, multi-column layouts, and scanned pages (academic papers, contracts, research reports, etc.) often become a mess if handed directly to the model. Document processing first uses a dedicated parsing engine to convert them into clearly structured text, and then passes it to chat or Knowledge base use.

Document Processing vs OCR: the two are separate pages of settings.

• Document processing(this page): handles PDF / complex-layout documents structured parsing of.
• OCR: handles images / scans text recognition in.

For ordinary plain-text PDFs,.md/.txt/.docx text paragraphs don't need either of the two; they can be read directly.

Configuration entry

Open [Settings] → [Document Processing], and select a parsing engine from the dropdown in the upper right,the selected engine will be used as the default.

Document Processing Settings: ① Use the dropdown at the top right to select a parsing engine (default MinerU); fill in the API key and API address for the selected engine below

Built-in parsing engines

Document Processing includes 5 built-in engines, default MinerU:

engine	Explanation	Connection method
MinerU(default)	A high-quality PDF extraction tool open-sourced by OpenDataLab	API key (mineru.net/apiManage)
PaddleOCR	Baidu Paddle OCR recognition system	Fill in API key (PaddlePaddle Star River Community; if self-deployed, point the API address to your service
Doc2x	Advanced file restoration engine	API key (open.noedgeai.com)
Mistral	File parsing and understanding service	API key (mistral.ai)
Open MinerU	A self-deployable MinerU service, suitable for teams that want to control the processing pipeline themselves	After self-deployment, fill in the API address (fill in the API key if needed)

Configure MinerU (default option)

1

Enter the API key

In the [API Key] field, enter the key obtained from MinerU (click "Get key" on the right to jump to the application page; multiple keys can be separated by commas).

2

Confirm API address

Leave the [API Address] as default.

3

Use directly in the knowledge base / chat

When importing complex PDFs, this parsing setting will be used automatically; no additional configuration is needed when switching to the knowledge base or chat.

Switch to another engine: select it from the dropdown, enter that engine's [API Key] / [API Address], and it becomes the default once selected. Among them PaddleOCR and Open MinerU supports self-deployment — after deployment, set the [API Address] to your own service address.

Relationship with the knowledge base

• Document processing only handles the step "complex documents → clean text";
• the converted text continues to Embedding model vectorization, and ingestion;
• See the detailed "Enable in the knowledge base" process in Knowledge Base Document Preprocessing.

Tips and tricks

• MinerU performs significantly better on PDFs with tables / multi-column layouts, and is the first choice for academic papers and similar documents;
• What needs to be recognized is the text in images(screenshots, scans) rather than the PDF structure, please use OCR.

---

Get help and submit feedback

If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to Feedback and Suggestions for the official channels provided.