DeepSeek Harness (DSH) extends its capabilities through a plugin mechanism. When integrating object detection capabilities into an agent, handling model loading and inference is typically required. The xby-ebike-detection plugin encapsulates this process and provides a set of command interfaces for detecting electric bicycles in images.

This plugin is maintained by xby-skill and belongs to the model inference category. It takes an image as input, detects electric bicycles within it, and outputs detection boxes, confidence scores, and labels for all detected objects in the image. The plugin follows the MIT license.

Core Features

The plugin provides the following command interfaces:

  • set_xby_apikey: Sets the API key in the chat. The key is automatically persisted and remains valid after a restart.
  • ebike_detection: Accepts an image file link to perform detection.
  • ebike_detection_for_data_base64: Accepts the BASE64 encoding of an image file to perform detection.
  • ebike_detection_for_data_file: Accepts the file path of an image file to perform detection.

Installation and Activation

Use the following command to install the plugin:

dsh plugin --profile web add github:xby_skill/xby-ebike-detection

Usage

After installation, choose the corresponding command based on the input data type:

  1. Image link: Call ebike_detection and pass the image URL.
  2. BASE64 encoding: Call ebike_detection_for_data_base64 and pass the Base64 string of the image.
  3. File path: Call ebike_detection_for_data_file and pass the absolute path of the local image.

Notes

This plugin depends on an external API service. Before use, register at the Xiaobenyang official website and obtain an API key, then configure it using the set_xby_apikey command.

Conclusion

This plugin provides DSH users with convenient electric bicycle detection capabilities, suitable for scenarios requiring detection of such objects in images. For more details, see the plugin catalog or the source repository.