Agent skill · research science · aradotso
deepseek-ocr
Expert skill for using DeepSeek-OCR, a vision-language model for optical character recognition with context optical compression supporting documents, PDFs, and images.
Why this skill is useful
Provides specific commands and configurations for using DeepSeek-OCR that are not widely known or documented.
What it needs
Requires cuda, python, pytorch, vllm installed locally. About 5k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
DeepSeek-OCR Skill by ara.so — Daily 2026 Skills collection. DeepSeek-OCR is a vision-language model for Optical Character Recognition with "Contexts Optical Compression." It supports native and dynamic resolutions, multiple prompt modes (document-to-markdown, free OCR, figure parsing, grounding), and can be run via vLLM (high-throughput) or HuggingFace Transformers. It processes images and PDFs, outputting structured text or markdown. --- Installation Prerequisites CUDA 11.8+, PyTorch 2.6.0 Python 3.12.9 (via conda recommended) Setup Alternative: upstream vLLM (nightly) --- Model Download Model is available on HuggingFace: deepseek-ai/DeepSeek-OCR --- Inference: vLLM (Recommended for Production) Single Image — Streaming Batch Images PDF Processing (via vLLM scripts) Benchmark Evaluation --- Inference: HuggingFace Transformers Transformers Script --- Prompt Reference Use Case Prompt --- --- Document → Markdown <image>\n< grounding >Convert the document to markdown. General OCR <image>\n< grounding >OCR this image. Free OCR (no layout) <image>\nFree OCR. Parse figure/chart <image>\nParse the figure. General description <image>\nDescribe this image in detail. Grounded REC <image>\nLocate <\ ref\ >TARGETTEXT<\ /ref\ > in the image. --- Supported Resolutions Mode Resolution Vision Tokens --- --- --- Tiny 512×512 64 Small 640×640 100 Base 1024×1024 256 Large 1280×1280 400 Gundam (dynamic) n×640×640 + 1×1024×1024 variable --- Configuration (vLLM) Edit DeepSeek-OCR-master/DeepSeek-OCR-vllm/config.py: --- Common Patterns Process a Directory of Images Convert PDF Pages to Markdown Grounded Text Location (REC) --- Troubleshooting transformers version conflict with vLLM vLLM 0.8.5 requires transformers>=4.51.1 — if running both in the same env, this error is safe to ignore per the project docs. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/deepseek-ocr