20fc9c24df
- Added `image_read` tool for reading and analyzing images using vision-capable models, with a detailed input schema for image path, prompt, max size, and provider. - Implemented `ReadImage` function to handle image processing and integration with vision models, returning descriptive text. - Created comprehensive tests for image resizing, data URI handling, and various input scenarios to ensure robust functionality. - Updated documentation to include usage examples and parameter descriptions for the new image tools.
8 lines
165 B
JSON
8 lines
165 B
JSON
{
|
|
"name": "yao-vision",
|
|
"transport": "process",
|
|
"description": "Vision tools for image understanding",
|
|
"tools": {
|
|
"image_read": "tools.image_read"
|
|
}
|
|
}
|