update ai services & readme

.env-example

@@ -0,0 +1,17 @@
+DATABASE_URL=
+SECRET_KEY=
+
+AWS_ACCESS_KEY_ID=
+AWS_ENDPOINT_URL_S3=
+AWS_REGION=
+AWS_SECRET_ACCESS_KEY=
+BUCKET_NAME=
+
+CORS_ORIGINS=
+FORWARDED_ALLOW_IPS=
+
+GOOGLE_API_KEY=
+TOGETHER_API_KEY=
+HYPERBOLIC_API_KEY=
+
+AUTH_TOKEN=

README.md

@@ -1,3 +1,123 @@
+# VisuLinx API
+
+A robust FastAPI-based backend service for managing organizations, projects, and file processing with secure authentication.
+
+## 🚀 Features
+
+- **User Management**: Secure user authentication and authorization
+- **Organization Management**: Create and manage organizations with multiple users
+- **Project Management**: Organize work into projects within organizations
+- **File Processing**: Handle file uploads with S3 integration
+- **Preferences System**: Flexible system-wide preferences management
+- **RESTful API**: Modern, fast, and well-documented API endpoints
+- **CORS Support**: Configured for cross-origin resource sharing
+
+## 🏗 Project Structure
+
+```
+app/
+├── api.py              # FastAPI application configuration
+├── database.py         # Database connection and settings
+├── models.py           # SQLAlchemy ORM models
+├── routers/           # API route handlers
+├── schemas.py         # Pydantic models for request/response
+├── security.py        # Authentication and authorization
+├── services/         # Business logic services
+└── settings.py        # Application settings
+```
+
+## 🔧 Technical Stack
+
+- **Framework**: FastAPI
+- **Database**: SQLAlchemy ORM
+- **Authentication**: JWT-based authentication
+- **Storage**: AWS S3 integration
+- **Data Validation**: Pydantic
+- **API Documentation**: Automatic OpenAPI/Swagger docs
+
+## 💻 Key Components
+
+### Models
+- **User**: Manages user accounts and authentication
+- **Organization**: Handles multi-user organizations
+- **Project**: Organizes work within organizations
+- **File**: Manages file uploads and processing
+- **Preference**: Stores system-wide preferences
+
+### API Endpoints
+- `/users`: User management endpoints
+- `/auth`: Authentication endpoints
+- `/organizations`: Organization management
+- `/projects`: Project-related operations
+- `/preferences`: System preferences management
+
+### 🤖 AI Services
+
+The project integrates with multiple AI providers for advanced image analysis and object detection:
+
+#### Supported AI Providers
+- **Together AI**: Uses the Qwen2-VL-72B-Instruct model for high-quality visual analysis
+- **Hyperbolic AI**: Implements the same Qwen model through a different API endpoint
+- **Google Gemini**: Utilizes Gemini 1.5 Pro for advanced image processing
+
+#### Features
+- **Object Detection**: Extract bounding boxes for objects in images
+- **Image Processing**: Automatic image resizing and compression for optimal AI processing
+- **Multi-Provider Support**: Fallback options across different AI services
+- **Standardized Interface**: Consistent API across all providers through the `AiService` abstract base class
+
+#### Configuration
+The AI services require the following environment variables:
+```
+GOOGLE_API_KEY=     # For Gemini AI
+TOGETHER_API_KEY=   # For Together AI
+HYPERBOLIC_API_KEY= # For Hyperbolic AI
+```
+
+## 🔒 Security Features
+
+- Secure password hashing
+- JWT token-based authentication
+- Role-based access control
+- CORS middleware configuration
+
+## 🚀 Getting Started
+
+### Prerequisites
+
+- Python >= 3.13
+- uv (Python package installer)
+
+### Installation
+
+1. Clone the repository
+2. Install dependencies using uv:
+   ```bash
+   uv sync
+   ```
+3. Configure environment variables
+4. Run the application:
+   ```bash
+   uv run fastapi dev
+   ```
+
+## 📝 API Documentation
+
+Once the server is running, access the API documentation at:
+- Swagger UI: `http://localhost:8000/docs`
+
+## 🤝 Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Commit your changes
+4. Push to the branch
+5. Create a Pull Request
+
+## 📄 License
+
+MIT License
+
 ## Autogenerate migration
 
 ```sh
@@ -8,4 +128,3 @@ uv run alembic revision --autogenerate -m "add ... table"
 
 ```sh
 python -c "import secrets; print(secrets.token_urlsafe(32))"
-```

app/routers/projects.py

@@ -428,7 +428,9 @@ async def extract_bounding_boxes(
         if document.contents is not None
     }
 
-    bounding_boxes = ai_service.extract_bounding_boxes(
+    ai = ai_service.GeminiAiService()
+
+    bounding_boxes = ai.extract_bounding_boxes(
         image_url=download_url,
         document_contents=document_contents,
         system_prompt=preferences['system_prompt'],