README.md

---
title: Image Captioning Api
emoji: 😻
colorFrom: indigo
colorTo: blue
sdk: docker
pinned: false
license: mit
short_description: API Endpoint for Image Captioning
---

# Image Captioning API

A RESTful API for generating captions from images using a Transformer-based
model. This service is designed to be deployed on Hugging Face Spaces.

## Features

- Upload any image file (jpg, png, etc.)
- Get AI-generated captions based on image content
- FastAPI-based REST API with documentation

## API Endpoints

- `GET /` - API information and usage
- `POST /generate` - Upload an image and get a caption
- `GET /health` - Health check endpoint
- `GET /docs` - Swagger UI documentation

## How to Use

### API Request Example

```bash
curl -X POST "https://your-space-name.hf.space/generate" \
  -H "accept: application/json" \
  -H "Content-Type: multipart/form-data" \
  -F "image=@your_image.jpg" \
  -F "max_length=20"
```

### API Response Example

```json
{
  "caption": "a person riding a snowboard down a snow covered slope",
  "image": "base64_encoded_image_data..."
}
```

## Local Development

### Prerequisites

- Python 3.9+
- pip

### Setup

1. Clone the repository
2. Install dependencies:
   ```
   pip install -r requirements.txt
   ```
3. Run the application:
   ```
   python app.py
   ```
4. Visit http://localhost:7860/docs to access the API documentation

## Deployment on Hugging Face Spaces

This application is designed to be deployed on
[Hugging Face Spaces](https://huggingface.co/spaces) using Docker.

1. Create a new Space on Hugging Face
2. Select Docker as the SDK
3. Upload all files to the repository
4. Hugging Face will automatically build and deploy the application

## Technical Details

- **Model**: ResNet50 encoder with Transformer decoder
- **Framework**: PyTorch
- **API**: FastAPI
- **Image Processing**: torchvision and PIL
- **Model Hosting**: Hugging Face Hub

## License

MIT