af0d4edd74
- Introduced `image_generate` tool for generating images from text prompts, with options for specifying output file paths and image dimensions. - Updated `image_read` functionality to allow optional provider specification for enhanced image analysis. - Implemented new `GenerateImage` method in the LLM API for seamless integration of image generation capabilities. - Enhanced documentation to include detailed usage examples for both image reading and generation tools. - Updated tests to validate new image generation features and ensure robust functionality across image tools.
30 lines
1.2 KiB
JSON
30 lines
1.2 KiB
JSON
{
|
|
"name": "image_read",
|
|
"description": "Read and analyze an image using a vision-capable model.",
|
|
"process": "tools.image_read",
|
|
"inputSchema": {
|
|
"type": "object",
|
|
"properties": {
|
|
"image_path": {
|
|
"type": "string",
|
|
"description": "Path or URI of the image to analyze. Accepts: local file path, URL (http/https), workspace://, attach://, yao://, or data URI."
|
|
},
|
|
"prompt": {
|
|
"type": "string",
|
|
"description": "What to analyze about the image (default: describe in detail)",
|
|
"default": "Please describe this image in detail."
|
|
},
|
|
"max_size": {
|
|
"type": "integer",
|
|
"description": "Max dimension in pixels for the longest edge. Image is resized (preserving aspect ratio) before sending to the vision model. Default 1080.",
|
|
"default": 1080
|
|
},
|
|
"provider": {
|
|
"type": "string",
|
|
"description": "Vision provider connector ID (e.g. from image_providers with capability='vision'). If omitted, uses the default vision model."
|
|
}
|
|
},
|
|
"required": ["image_path"]
|
|
},
|
|
"x-process-args": ["$args.image_path", "$args.prompt", "$args.max_size", "$args.provider"]
|
|
}
|