dsh-vision-plugin: Adding Image Understanding to DSH Sessions
The DSH plugin `dsh-vision-plugin` provides image understanding capabilities for AI sessions, built on the "everything is a plugin" architecture. Installation requires DSH 0.1.7-rc.2 or a compatible version. Users can configure the Base URL, Model ID, API Key (with authentication support for OpenAI, Anthropic, and others), and retry policies via the web interface or a YAML file. The plugin is compatible with the OpenAI standard interface and supports services such as OpenRouter and Volcano Ark. It features robust fault-tolerance mechanisms and is well suited for handling multimodal input.
Read MoreDeepSeek Harness Plugin: dsh-vision-plugin
The dsh-vision-plugin for DeepSeek Harness resolves the cumbersome issue of manually describing images in multimodal conversations by automatically generating a description of image content before a message is sent and injecting it into the message. The plugin supports uploading or pasting images and uses DashScope vision models or Windows offline OCR to parse them. Users can select an OCR-only or vision-based description mode in the chat box; after a successful description, the system automatically inserts the description at the beginning of the message. The plugin follows a strict routing policy, processes images in memory as base64, and never writes them to disk. This tool simplifies multimodal interaction workflows and is suitable for developers.
Read Moredsh-vision-plugin: Empowering DeepSeek Harness Text Models with Vision Capabilities
The `dsh-vision-plugin` is a plugin for DeepSeek Harness (DSH) that enables visual analysis capabilities for text-only models, such as DeepSeek v4. It uses an intermediate layer to send images to a vision model, such as Qwen3.7-plus, for transcription into text, which is then processed by the main model. The plugin supports pasting images directly into a conversation to ask questions and provides the `vision_analyze` tool for analyzing local files. Before use, image input support for the model must be declared in the configuration file. The plugin is compatible with DSH v0.1.0-rc.8 and later.
Read Moredsh-vision-plugin: Add an "Image Input" declaration checkbox to the DSH model directory
# Introduction When integrating custom models into DSH, you may encounter a scenario where the endpoint itself supports multimodal capabilities, but sending an image directly in the chat dialog results in an error stating "Image input not supported." The reason is that the DSH host reads the `input: ["text","image"]` declaration on the model entry to decide whether to pass the original image directly to the model, while the interface in "Settings → Models → Model Catalog" has never exposed an entry point for this declaration. dsh-vision-plugin aims to address this step: by adding an "Image Input" checkbox on the model page in the Model Catalog. Once checked, the declaration is written into DSH settings, allowing the custom model to directly receive images in the chat dialog. # What is it dsh-vision-p
Read MoreDSH-Vision-Plugin: Adding Image Understanding Capabilities to DSH
dsh-vision-plugin is a plugin developed specifically for DeepSeek Harness (DSH), designed to address the limitation that pure text models cannot directly process images. This plugin leverages OpenRouter's free multimodal models (`:free`) to automatically convert images into text descriptions before sending, thereby endowing text-based models like DeepSeek with image understanding capabilities, all at zero API cost. Key features include: providing a `describe_image` tool to read local images; intercepting and converting images automatically via the `llm/stream` hook when the model does not support image inputs; and automatically writing a `deepseek-vision` provider pointing to OpenRouter into the configuration file on first startup.
Read More