https://github.com/passadis/ai-foundry-multimodels
Azure AI Foundry multimodel utilization and performance metrics Web App.
https://github.com/passadis/ai-foundry-multimodels
azure azureai azureaistudio containerapps fastapi vite-react
Last synced: about 2 months ago
JSON representation
Azure AI Foundry multimodel utilization and performance metrics Web App.
- Host: GitHub
- URL: https://github.com/passadis/ai-foundry-multimodels
- Owner: passadis
- License: mit
- Created: 2025-02-04T15:45:14.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-04T22:08:41.000Z (over 1 year ago)
- Last Synced: 2025-02-06T15:45:49.576Z (over 1 year ago)
- Topics: azure, azureai, azureaistudio, containerapps, fastapi, vite-react
- Language: TypeScript
- Homepage: https://www.cloudblogger.eu/2025/02/04/how-to-azureaifoundry/
- Size: 355 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Security: SECURITY.md
Awesome Lists containing this project
README
Azure AI Foundry Models Demo
## Introduction
A serverless web application demonstrating the capabilities of different Azure AI Foundry models. This project provides an interactive interface to test and compare three powerful AI models:
- DeepSeek (Problem-solving focus)
- GPT-4 (Complex reasoning)
- Phi-3 (Efficient general tasks)
## Features
- Interactive UI for model testing
- Real-time performance metrics
- Response history tracking
- Performance comparison between models
- Token usage analytics
- Response time measurements
## Tech Stack
### Frontend
- React + TypeScript
- Vite
- TailwindCSS
- shadcn/ui components
- Environment-based configuration
### Backend
- Python FastAPI
- Azure Key Vault integration
- Azure Managed Identity
- Docker containerization
## Architecture
The application uses:
- Azure Container Apps for hosting
- Azure Key Vault for secrets
- Azure AI Foundry models
- User-assigned Managed Identity
## Development
1. Clone the repository
2. Set up environment variables:
Frontend (.env):
```
VITE_BACKEND_URL=/api/v1
```
Backend (.env):
```
KEY_VAULT_URL=your-keyvault-url
MANAGED_IDENTITY_CLIENT_ID=your-managed-identity
```
3. Start the development servers:
Frontend:
```bash
cd frontend
npm install
npm run dev
```
Backend:
```bash
cd backend
python -m venv venv
source venv/bin/activate # or `venv\Scripts\activate` on Windows
pip install -r requirements.txt
python run.py
```
## Contributing
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
## Architecture
