๐ฏ
openai-image-vision
๐ฏSkillfrom zhayujie/chatgpt-on-wechat
|What it does
Analyzes images using OpenAI's vision capabilities, extracting detailed descriptions, identifying objects, and providing contextual insights within WeChat conversations.
Part of
zhayujie/chatgpt-on-wechat(5 items)
openai-image-vision
Installation
git cloneClone repository
git clone https://github.com/zhayujie/chatgpt-on-wechatpip installInstall dependencies
pip3 install -r requirements.txtpip installInstall dependencies
pip3 install -r requirements-optional.txtPythonRun Python server
python3 app.py # windows็ฏๅขไธ่ฏฅๅฝไปค้ๅธธไธบ python app.pyDockerRun with Docker
docker compose version๐ Extracted from docs: zhayujie/chatgpt-on-wechat
3Installs
-
AddedFeb 6, 2026
More from this repository4
๐ฏ๐ฏ๐ฏ๐ฏ
bocha-search๐ฏSkill
Performs high-quality web searches with AI-optimized results, returning web pages, images, and detailed metadata across customizable parameters.
web-fetch๐ฏSkill
Fetches and extracts readable text content from web pages using curl with minimal processing.
skill-creator๐ฏSkill
Generates and structures skills by creating SKILL.md files, bundling resources, and defining specialized agent capabilities with concise, targeted instructions.
linkai-agent๐ฏSkill
Executes LinkAI applications and workflows by calling a bash script with an app code and question via API.