dsh-image-vision
Multimodal image recognition and inspection plugin for DeepSeek Harness with automated model routing and fine-grained visual tools.
Install
$ dsh plugin --profile web add https://github.com/xiaoyuink/dsh-image-vision/releases/latest/download/xiaoyuink-dsh-image-vision-latest.tgzPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Automatic detection and routing between native model vision and secondary vision providers
- Provides a four-tool inspection suite: image_vision, image_vision_ocr, image_vision_ground, and image_vision_crop
- Direct chat input support for drag-and-drop, clipboard pasting, and file uploads
- Built-in specialized prompt presets for histopathology, cell biology, anatomy, and scientific figures
- Multi-provider management UI with discovery, connection testing, and balance checks
- Support for OpenAI-compatible, Anthropic-compatible, Qwen-Omni Realtime, and OVHcloud endpoints
- Automatic conversion and preprocessing for TIFF, SVG, AI, and EPS formats
Useful For
- Enabling non-vision text models in DeepSeek Harness to analyze user-uploaded screenshots and images
- Inspecting biomedical and scientific images such as pathology slides, Western blots, and CT scans
- Performing precision OCR and reading dense text on charts or diagrams
- Cropping, magnifying, and localizing specific elements within complex compound figures
Who It Fits
- DeepSeek Harness users working with text-only models who need visual intelligence
- Biomedical and academic researchers analyzing experimental images and figures
- Developers seeking granular visual grounding, cropping, and OCR toolchains
Documented Limitations
- AI/EPS vector image conversion requires a local Python environment with PyMuPDF and Ghostscript
- Default image attachment size is constrained by local attachment settings (e.g. 5MB default limit)
- Secondary vision model routing depends on external API availability and valid credentials or provider quotas
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 2 runtime, 0 development, 8 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub did not report an SPDX license for this repository snapshot.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- xiaoyuink/dsh-image-vision
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- a445f84 · 2026-10-08
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 3GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-04
- Last release
- 2026-09-04
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Vision routing and pixel-level tools for text-only DeepSeek Harness agents with built-in free fallback.
View plugin →DeepSeek Harness web-search plugin that adds web search, X search, and focused page fetching with structured evidence.
View plugin →Full office suite integration for DeepSeek Harness supporting spreadsheets, docs, slides, bases, and canvases.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →