dsh-llm-vision

Reliable vision + OCR for text-only models on DeepSeek Harness: describe_image (normal/critical) + extract_text tools, auto-preprocessing, retries, and a persistent answer cache.

Install dsh-llm-vision

dsh plugin --profile web add github:1710782766/dsh-llm-vision

Plugin details

Author

1710782766

Category

Tools & Capabilities

Added

2026-08-17

View the source on GitHub

More tools & capabilities plugins

• dsh-plugin-text-translation
• dsh-plugin-memory
• DevTools-Custom-Beautification-Plugin-for-DeepseekHarness-Class
• dsh-plugin-tts
• dsh-data-analysis-plugin
• dsh-plugin-tavily
• dsh-git-graph
• dsh-music
• mirage
• modlens
• agentrq
• dsh-market