Cheng-cheng9669/dsh-deepseek-vision

README excerpt

dsh-deepseek-vision A DSH plugin that gives text-only DeepSeek models image recognition. It registers the deepseek vision tool, which calls the local deepseek-vision-cli (browser automation driving chat.deepseek.com's vision mode) and returns the image description as text to the model. Tool - deepseek vision(image, prompt?) - image : absolute path to a local image (PNG/JPG/WebP/GIF; HEIC is not supported) - prompt : optional question or analysis request for the image Installation Or use the release tarball: First login DeepSeek web vision requires a web login session. The current web UI uses password / third-party login, so the recommended way is the manual login helper: It opens an Edge window to the DeepSeek login page. After you log in manually, the helper saves the token to D:\Dsh\.cache\dsv token . Token login (alternative) If you already have a DeepSeek web session in your normal browser, you can copy the token directly: 1. Open https://chat.deepseek.com and log in. 2. Press F12 → Application → Local Storage → https://chat.deepseek.com . 3. Find userToken , copy its value field. 4. Save it to D:\Dsh\.cache\dsv token (no quotes, no newline): The token is only stored locally in…

Category