picturereader
Unified image understanding, OCR, document conversion, and local image editing plugin for text-only models in DeepSeek Harness.
Install
$ dsh plugin --profile web add picturereader # npm 包；或从源码: dsh plugin --profile web add .Plugin 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
- Visual twin adapter wrapping text-only models to enable native thumbnail rendering and auto-analysis
- Local pixel-level analysis tools including image_scan, image_sample, image_crop, image_palette, image_compare, and image_batch
- Multi-engine OCR support for Windows native, macOS Vision, PaddleOCR, and RapidOCR
- Local document-to-image conversion for PDF, DOCX, XLSX, and PPTX files
- CPU-based local image editing (image_edit) for resizing, watermarking, background removal, perspective correction, and filtering
- Three-mode intelligent routing (Privacy, Smart, Strict) with optional external VLM API integration
- Native visual capability detection to pass images directly to multimodal models without text degradation
Useful For
- Enabling text-only LLMs to inspect screenshots, charts, and diagrams via structured pixel scanning and OCR
- Extracting text from local documents and images using platform-native or neural OCR engines without external data leaks
- Performing local batch image transformations, crops, watermarks, and background removals directly within DSH agent sessions
- Providing hybrid visual workflows that default to local inspection and escalate complex imagery to external VLMs on demand
Who It Fits
- DeepSeek Harness users working with text-only models who need visual comprehension
- Developers and analysts needing offline, privacy-safe document conversion and OCR
- Users managing local multimodal pipelines and automated desktop image editing workflows
Documented Limitations
- WebP input is not directly supported by standard scan tools and must be converted to PNG or JPEG first
- Platform-specific OCR engines (windows/macos) require their corresponding operating systems
- Advanced photo editing actions like background removal and super-resolution require optional virtualenv dependencies or external CLI tools
- Visual twin adapter model selection requires a DSH restart to apply configuration changes
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 4 runtime, 0 development, 3 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
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
- jing-hy/picturereader
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 619a67e · 2026-10-06
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
- 37GitHub stars
- Forks
- 5
- Open issues
- 0
- Last commit
- 2026-09-30
- Last release
- 2026-09-11
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Multimodal vision router and deep pixel tools for text-only DeepSeek Harness agents with free fallback chains.
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 →Bundle of 88 open-source Agent Skills for research, business intelligence, marketing, and SEO in DeepSeek Harness.
View plugin →