ocr-and-documents

To extract text from a scanned PDF, the Skill applies marker-pdf for OCR processing, converting image-based pages into searchable text. It defaults to pymupdf for text-based PDFs but switches to OCR automatically when needed.

Yes, you can convert PDFs to Markdown for research archiving using pymupdf4llm. This transforms documents like Arxiv papers into editable text and markdown representations for quick reading and content processing.

Yes, the text extraction tool supports DOCX and PPTX files alongside standard PDFs. It handles multi-format document workflows, enabling automated text capture from various source files into searchable text.

The best way to process a remote PDF URL is using the web_extract feature. This fetches documents directly from the web, applying local extraction options like pymupdf or OCR to capture the text automatically.

Use pymupdf for standard text-based PDFs to achieve fast extraction, and switch to marker-pdf when handling scanned documents that require OCR. This ensures accurate text capture across different document types.

Yes, local OCR and document parsing require Python dependencies including pymupdf, pymupdf4llm, and marker-pdf. These libraries enable the automated text extraction workflows for both local and remote files.