Phantoscope is an image search engine developed on Milvus and neutral networks.
🚀 Extremely high speed in processing and searching billions of images.
🎭 Compatible with Tensorflow, Pytorch, TensorRT, ONNX, XGBoost, and more.
📝 Provides abundant extensions. You can build an extension using your own model within five minutes.
📇 Provides GUI for verifying self-developed extensions and managing data.
🏭 Soon to provide an extension market, where you can share your extension with the world.
🚢 Soon to provide extension runtime mode with native support for Docker and kubernetes.
English | 中文版
$ git clone https://github.com/zilliztech/phantoscope.git && cd phantoscope
$ export LOCAL_ADDRESS=$(ip a | grep -Eo 'inet (addr:)?([0-9]*\.){3}[0-9]*' | grep -Eo '([0-9]*\.){3}[0-9]*' | grep -v '127.0.0.1'| head -n 1)
$ docker-compose up -d
Click here to set up a simple Phantoscope application. You can use it to upload and search images.
From here, you can get an idea as to how you can apply Phantoscope to different scenarios:
- Search by human face
- Search by object
The following figure illustrates the basic concepts of the Phantoscope project.
| Tutorial |
Level |
|---|---|
| What is operator | Simple |
| What is pipeline | Simple |
| What is application | Simple |
Contributions are welcomed and greatly appreciated.
Please read our contribution guidelines for detailed contribution workflow.
We use GitHub issues to track issues and bugs.
For general questions and public discussions, please join our community.
- Go to our Slack Channel, if you run into issues and want to consult our experts.
- Click here to learn more about Zilliz.
GitHub milestones lays out the development plan for Phantoscope.
We hope you could join us in developing operators. From here, you can find more information about how to develop an operator.
If you have further questions, contact phantoscope@zilliz.com
Apache License 2.0