mirror of
https://github.com/hanzoai/store.git
synced 2026-10-30 14:54:46 +00:00
zeekay
8fd4fd4bd9
All 457 icon and screenshot urls across all 202 apps were presigned links to a single bucket, signed 2025-11-05 with X-Amz-Expires=86400. They have answered 403 ExpiredRequest since the day after, and a presigned url cannot be re-signed by whoever holds it, so the images are unrecoverable through the only address anyone had for them and no copy exists elsewhere. There is nothing to re-host. A url that cannot resolve is not artwork, it is an outbound request that always fails, so the fields are removed rather than repointed. AppIcon already renders the initial when icon is absent and the Screenshots panel already hides on an empty list, so the page looks the same and loses 202 failing requests and 245 KB of catalog per visit: store.json goes 494 KB to 249 KB. Artwork is served from this site's own origin as a root-relative path. data/ is the one source both generate-store.js and the hanzoai/cdn market build copy from verbatim, so the rule holds in one place.
40 lines
2.2 KiB
JSON
40 lines
2.2 KiB
JSON
{
|
|
"id": "images-folder-classifier-using-vision-llm",
|
|
"name": "Images folder classifier - using vision LLM",
|
|
"description": "This tool uses a vision capable LLM to classify images in a folder based on your custom labels, organizes them into subfolders (optional), and creates a COCO-format JSON dataset. It provides a clear summary of results, including any issues like low-confidence labels.\n\nHow to Use :\n\n1. Put your images (.jpg, .png, etc.) in a folder.\n\n2. Specify the folder path, a list of labels (e.g., \"cat\", \"dog\"), and your vision AI model.\n\n3. Choose how to handle images : just label them, copy to label subfolders, or move to subfolders.\n\n4. Set optional preferences, like picking the highest-confidence label instead of all labels, or defining a minimum confidence score.\n\n5. Run the tool to classify images, save a COCO JSON file, and organize images (if selected).\n\n6. Check the JSON file for classifications, subfolders with classified images, and a summary of results.\n\nNotes :\n\n- The tool checks AI outputs for errors, implement retries, and reports issues like invalid labels.\n\n- Supports multiple labels per image.\n\n- If moving images, originals are deleted only after successful organization.\n\n- In configuration you can pick which types of errors to include in the output.\n\nWARNING : possible high LLM usage, depending on the number of images in the folder.\n\n",
|
|
"version": "1.0.0",
|
|
"author": "hanzo.ai",
|
|
"homepage": "local:::__gilles_test2_sep_hanzo:::images_folder_classifier___using_vision_llm",
|
|
"license": "MIT",
|
|
"category": "Photo & Video",
|
|
"tags": [
|
|
"image",
|
|
"classification",
|
|
"vision LLM",
|
|
"COCO",
|
|
"folder",
|
|
"labeling",
|
|
"sorting"
|
|
],
|
|
"installCommand": "",
|
|
"mcpConfig": {
|
|
"command": "any",
|
|
"args": [
|
|
"local:::__gilles_test2_sep_hanzo:::images_folder_classifier___using_vision_llm"
|
|
],
|
|
"env": {}
|
|
},
|
|
"downloads": 17,
|
|
"createdAt": "2025-04-30T15:52:12.893Z",
|
|
"updatedAt": "2025-04-30T15:52:12.893Z",
|
|
"type": "Tool",
|
|
"toolLanguage": "Python",
|
|
"operatingSystem": [
|
|
"linux",
|
|
"macos",
|
|
"windows"
|
|
],
|
|
"runner": "any",
|
|
"featured": true,
|
|
"price": 0
|
|
} |