metadata

title: Inference Provider Dashboard
emoji: 📊
colorFrom: blue
colorTo: purple
sdk: docker
pinned: false
license: mit

Inference Provider Dashboard

A modern web dashboard built with FastAPI that compares monthly requests between different AI inference providers by scraping data from their HuggingFace profiles.

Features

Real-time Data: Scrapes monthly request statistics from HuggingFace profiles
Beautiful UI: Modern, responsive dashboard with charts and tables
API Endpoints: RESTful API for accessing provider data programmatically
Auto-refresh: Dashboard automatically updates every 5 minutes
Async Performance: Uses async/await for efficient concurrent data fetching

Screenshots

The dashboard includes:

Statistics cards showing total providers, total requests, and top provider
Interactive bar chart comparing monthly requests
Detailed table with provider information and links to HuggingFace profiles

Installation

Clone or navigate to the project directory
Install dependencies:
```
pip install -r requirements.txt
```

Usage

Start the FastAPI server:

python app.py

Or using uvicorn directly:

uvicorn app:app --host 0.0.0.0 --port 8000 --reload

Open your browser and navigate to:
```
http://localhost:8000
```
API Endpoints:
- GET / - Dashboard web interface
- GET /api/providers - Get all providers data
- GET /api/providers/{provider} - Get specific provider data

API Examples

Get all providers data:

curl http://localhost:8000/api/providers

Get specific provider data:

curl http://localhost:8000/api/providers/togethercomputer

Configuration

To add more providers, edit the PROVIDERS list in app.py:

PROVIDERS = [
    "togethercomputer",
    "fireworks-ai",
    "your-new-provider",
]

Project Structure

inference_provider_dashboard/
├── app.py                 # FastAPI application
├── templates/
│   └── dashboard.html     # Web dashboard template
├── requirements.txt       # Python dependencies
└── README.md             # This file

Dependencies

FastAPI: Modern web framework for building APIs
Uvicorn: ASGI server for running FastAPI
Jinja2: Template engine for HTML rendering
aiohttp: Async HTTP client for concurrent requests
BeautifulSoup4: HTML parsing for web scraping
Requests: HTTP library (fallback)

Development

The application uses:

Async/await for concurrent HTTP requests
Chart.js for interactive visualizations
Modern CSS with gradients and animations
Responsive design for mobile devices

License

MIT License