gugu123a/dsh-tool-see-image

README excerpt

dsh-tool-see-image Glad to make a plugin for deepseekharness （or dsh）. Give a text-only model (e.g. deepseek-v4-flash ) the ability to "see" images : the see image tool sends an image file to a configurable vision model (default: Zhipu GLM-4V-Flash, free), which describes it in text; the text-only model relays that description back to you. How it works Install (DSH web profile) 1. Copy the plugin into your profile directory, e.g. $DSH HOME/profiles/web/plugins/dsh-tool-see-image/ ( $DSH HOME is usually /.dsh ). 2. Declare the dependency in $DSH HOME/profiles/web/package.json : Then run pnpm install (creates a junction to the source under profiles/node modules ). 3. Compose it into the profile in $DSH HOME/profiles/web/cordis.patch.yml : 4. Set your API key : create one at the Zhipu (bigmodel) console (format id.secret ), then set the environment variable (Windows example): Restart your terminal , then restart dsh web (the web profile does not hot-reload patch layers yet — tested). 5. Verify : in a new session the see image tool should appear. Try it: Configuration (tool-see-image line in cordis.patch.yml) Key Default Description baseURL https://open.bigmodel.cn/api/paas/v4 OpenAI-c…

Category