This project is a simple API built using Hapi.js that integrates with a TensorFlow.js machine learning model. It provides endpoints for loading the model and making predictions.

hapi-tfjs-api
├── src
│   ├── server.js            # Entry point of the application
│   ├── routes
│   │   └── model.js         # API routes for the TensorFlow model
│   ├── controllers
│   │   └── modelController.js # Controller for handling model requests
│   ├── services
│   │   └── tensorflowService.js # Service for TensorFlow model interactions
│   └── types
│       └── index.d.ts       # TypeScript types and interfaces
├── package.json              # NPM configuration file
└── README.md                 # Project documentation

1. Clone the repository:

   git clone <repository-url>
   cd hapi-tfjs-api
   

2. Install dependencies:

   npm install
   

To start the server, run:

node src/server.js

The server will start and listen for incoming requests.

• Endpoint: POST /model/load
• Description: Loads the TensorFlow.js model.
• Request Body:

  {
    "modelPath": "path/to/model.json"
  }

• Response:

  {
    "message": "Model loaded successfully"
  }

• Endpoint: POST /model/predict
• Description: Makes a prediction using the loaded model.
• Request Body:

  {
    "inputData": [1, 2, 3, 4]
  }

• Response:

  {
    "prediction": [0.5, 0.2, 0.3]
  }

Feel free to submit issues or pull requests for improvements or bug fixes.

This project is licensed under the MIT License.