skills.rest
joonlab
joonlabCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

deepseek-ocr

Extract text from images and PDFs using the DeepSeek-OCR-8bit model.

8|Updated Jul 26, 2026
Search Tags:#automation#ocr#pdf#mlx#deepseek#image-processing
One-click install
npx skills add https://github.com/joonlab/joonlab-claudecode-setting-for-share --skill deepseek-ocr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deepseek-ocr
Source: https://github.com/joonlab/joonlab-claudecode-setting-for-share/tree/main/claude/skills/deepseek-ocr
Command: npx skills add https://github.com/joonlab/joonlab-claudecode-setting-for-share --skill deepseek-ocr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mlx-vlm, pillow, pymupdf, transformers, mlx, and includes scripts (resource) components.

What problem does it solve?

This skill solves the challenge of accurately extracting text from complex images and multi-page PDF documents locally on Apple Silicon, avoiding the need for cloud-based OCR services.

Core Features & Use Cases

  • Local OCR Processing: Uses the DeepSeek-OCR-8bit model optimized for MLX to perform high-quality text extraction directly on your machine.
  • Multi-Format Support: Handles various image formats (PNG, JPG, WEBP, etc.) and multi-page PDF documents with automatic page marking.
  • Parallel Execution: Leverages multi-core processing to handle large batches of images or long PDF documents efficiently.

Quick Start

Run the deepseek-ocr skill by providing the absolute file paths of the images or PDFs you wish to process in the terminal.

Frequently Asked Questions about deepseek-ocr

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text from images and PDF files locally on Apple Silicon?▼

You can extract text from images and PDFs locally using the DeepSeek-OCR-8bit model optimized for MLX. It processes various image formats and multi-page PDFs directly on your machine without cloud-based OCR services.

Can I use MLX-VLM to perform OCR on multi-page PDF documents?▼

Yes, MLX-VLM works with PyMuPDF and Pillow to perform local vision-language model inference for multi-page PDF parsing. The skill automatically marks pages and handles diverse image formats during extraction.

What is the best way to batch process OCR for large sets of images?▼

Batch processing OCR for large sets of images is handled through parallel execution. The skill leverages multi-core processing on Apple Silicon to efficiently process large batches of images or long PDF documents.

Do I need cloud-based OCR services to parse complex images on my machine?▼

You do not need cloud-based OCR services to parse complex images locally. The DeepSeek-OCR-8bit model uses MLX optimization to perform high-quality text extraction directly on Apple Silicon hardware.

Does the DeepSeek-OCR skill support processing WEBP and PNG image formats?▼

The skill supports processing various image formats including PNG, JPG, and WEBP. It uses local vision-language model inference to extract text from these diverse file formats with parallelized execution.

Related Skills

Explore More Software Engineering Skills→
ml-exploreml-explore
771

swift-mlx-lm

Run local LLM and VLM inference and fine-tuning on Apple Silicon with MLX Swift.

Official
Advanced
carterwayneskhizeinecarterwayneskhizeine
19

ocr-and-documents

Extract text and structured content from PDFs and scanned documents.

Community
Intermediate
TurnaboutHeroTurnaboutHero
12

multimodal-looker

Analyze images and videos to extract descriptions, OCR text, and diagram insights.

Community
Basic
89jobrien89jobrien
4

PDF Processing

Extract text and tables from native and scanned PDFs using pdfplumber.

Community
Advanced