@rwese/minimax-image-understanding
MiniMax extension for pi coding agent
Package details
Install @rwese/minimax-image-understanding from npm and Pi will load the resources declared by the package manifest.
$ pi install npm:@rwese/minimax-image-understanding- Package
@rwese/minimax-image-understanding- Version
1.0.0- Published
- Apr 18, 2026
- Downloads
- 72/mo · 6/wk
- Author
- rwese
- License
- unknown
- Types
- extension
- Size
- 6.5 KB
- Dependencies
- 0 dependencies · 2 peers
Pi manifest JSON
{
"extensions": [
"./extensions"
]
}Security note
Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.
README
@wese/pi-minimax-image-understanding
MiniMax Image Understanding extension for pi coding agent.
Installation
pi install git:github.com/rwese/pi-minimax-image-understanding
Configuration
Set your MiniMax API key:
export MINIMAX_API_KEY="your-api-key"
export MINIMAX_API_HOST="https://api.minimax.io" # optional, defaults to api.minimax.io
Usage
The extension registers an image_understanding tool for analyzing images using vision-language models.
Example prompts:
- "Describe this image"
- "Read the text from this screenshot"
- "What does this chart show?"
- "Analyze the diagram"
Features
- Vision-language model via MiniMax API
- Supports local file paths, URLs, and base64 images
- Image format support: PNG, JPEG, WebP, GIF
- Describe screenshots, diagrams, charts, documents
- Extract text from images (OCR-style)