feat: add complete frontend application with backend API

.coveragerc

@@ -0,0 +1,15 @@
+[run]
+source = src/llama_prompt_ops
+omit =
+    */tests/*
+    */site-packages/*
+    setup.py
+
+[report]
+exclude_lines =
+    pragma: no cover
+    def __repr__
+    raise NotImplementedError
+    if __name__ == .__main__.:
+    pass
+    raise ImportError

frontend/README.md

@@ -0,0 +1,189 @@
+# Llama Prompt Ops - Frontend
+
+A modern React frontend interface for [llama-prompt-ops](https://github.com/meta-llama/llama-prompt-ops), providing an intuitive web interface for prompt optimization workflows.
+
+## Features
+
+- **Prompt Enhancement**: Optimize prompts for better performance with Llama models
+- **Prompt Migration**: Migrate prompts between different model architectures
+- **Real-time Optimization**: Monitor optimization progress with live updates
+- **Dataset Management**: Upload and manage datasets for optimization
+- **Configuration Management**: Flexible configuration for different optimization strategies
+- **Clean UI**: Modern, accessible interface with Meta's design language
+
+## Technology Stack
+
+- **Frontend**: React 18 + TypeScript
+- **UI Components**: Radix UI + shadcn/ui
+- **Styling**: Tailwind CSS with Meta/Facebook design system
+- **Build Tool**: Vite
+- **Backend**: FastAPI with llama-prompt-ops integration
+
+## Quick Start
+
+### Prerequisites
+
+- **Node.js 18+** and npm
+- **Python 3.8+** (for backend)
+- **OpenRouter API Key** (get one at [OpenRouter](https://openrouter.ai/))
+
+### Installation
+
+1. **Clone the repository**
+   ```bash
+   git clone https://github.com/meta-llama/llama-prompt-ops.git
+   cd llama-prompt-ops/frontend
+   ```
+
+2. **Install frontend dependencies**
+   ```bash
+   npm install
+   ```
+
+3. **Set up backend environment**
+   ```bash
+   cd backend
+   python -m venv venv
+   source venv/bin/activate  # On Windows: venv\Scripts\activate
+   pip install -r requirements.txt
+   ```
+
+4. **Configure environment variables**
+
+   Create a `.env` file in the `frontend/backend` directory:
+   ```bash
+   # In frontend/backend/.env
+   OPENROUTER_API_KEY=your_openrouter_api_key_here
+   OPENAI_API_KEY=your_openai_api_key_here  # Optional: for fallback enhance feature
+   ```
+
+### Running the Application
+
+#### Option 1: Use the Development Script (Recommended)
+```bash
+# From the frontend directory
+chmod +x start-dev.sh
+./start-dev.sh
+```
+
+#### Option 2: Manual Start
+```bash
+# Terminal 1: Start backend
+cd backend
+source venv/bin/activate
+python -m uvicorn main:app --reload --port 8000
+
+# Terminal 2: Start frontend
+cd ..
+npm run dev
+```
+
+The application will be available at:
+- **Frontend**: http://localhost:8080
+- **Backend API**: http://localhost:8000
+
+### First Run
+
+1. **Upload a dataset**: Click "Manage Dataset" and upload a JSON file with your training data
+2. **Configure optimization**: Select your preferred model, metrics, and optimization strategy
+3. **Enter your prompt**: Paste your existing prompt in the text area
+4. **Click "Optimize"**: Watch the real-time progress and get your optimized prompt!
+
+## Dataset Format
+
+Upload JSON files in this format:
+```json
+[
+  {
+    "question": "Your input query here",
+    "answer": "Expected response here"
+  },
+  {
+    "question": "Another input query",
+    "answer": "Another expected response"
+  }
+]
+```
+
+## Troubleshooting
+
+### Common Issues
+
+**Backend won't start:**
+- Ensure you've activated the virtual environment
+- Check that all requirements are installed: `pip install -r requirements.txt`
+- Verify your API keys are set in the `.env` file
+
+**Frontend can't connect to backend:**
+- Make sure the backend is running on port 8000
+- Check browser console for CORS errors
+- Verify the backend URL in the frontend code
+
+**Optimization fails:**
+- Check that you've uploaded a valid dataset
+- Verify your OpenRouter API key is correct
+- Ensure your dataset has the expected format
+
+**Port already in use:**
+- Kill existing processes: `pkill -f "uvicorn\|vite"`
+- Or use different ports in the configuration
+
+## Development
+
+### Frontend Development
+
+```bash
+# Start with hot reload
+npm run dev
+
+# Build for production
+npm run build
+
+# Preview production build
+npm run preview
+
+# Lint code
+npm run lint
+```
+
+### Backend Development
+
+```bash
+# Start with auto-reload
+uvicorn main:app --reload --port 8000
+
+# Run with debug logging
+uvicorn main:app --reload --port 8000 --log-level debug
+```
+
+## Project Structure
+
+```
+frontend/
+├── backend/                 # FastAPI backend
+│   ├── main.py             # API server
+│   ├── requirements.txt    # Python dependencies
+│   └── uploaded_datasets/  # Dataset storage
+├── src/
+│   ├── components/         # React components
+│   │   ├── ui/            # Reusable UI components
+│   │   ├── ConfigurationPanel.tsx
+│   │   ├── PromptInput.tsx
+│   │   └── ...
+│   ├── context/           # React context
+│   ├── hooks/             # Custom hooks
+│   └── pages/             # Page components
+├── package.json
+└── start-dev.sh           # Development startup script
+```
+
+## Contributing
+
+1. Follow the existing code style and patterns
+2. Add tests for new features
+3. Update documentation for any changes
+4. Ensure the application builds and runs successfully
+
+## License
+
+This project is licensed under the same terms as llama-prompt-ops.

frontend/backend/README.md

@@ -0,0 +1,79 @@
+# Llama Prompt Ops Frontend Backend
+
+This is a FastAPI backend for the llama-prompt-ops frontend interface. It provides API endpoints for optimizing prompts using OpenAI's GPT models and the llama-prompt-ops library.
+
+## Setup
+
+1. Create a virtual environment:
+```bash
+python -m venv venv
+source venv/bin/activate  # On Windows: venv\Scripts\activate
+```
+
+2. Install dependencies:
+```bash
+pip install -r requirements.txt
+```
+
+3. Set up your environment variables:
+   - Copy `.env.example` to `.env` (if available)
+   - Add your OpenAI API key and OpenRouter API key to the `.env` file
+
+## Running the Server
+
+Start the FastAPI server with:
+```bash
+uvicorn main:app --reload --port 8000
+```
+
+The API will be available at http://localhost:8000
+
+## API Endpoints
+
+### POST /api/enhance-prompt
+
+Enhances a prompt using OpenAI's GPT model.
+
+**Request Body:**
+```json
+{
+  "prompt": "Your prompt text here"
+}
+```
+
+**Response:**
+```json
+{
+  "optimizedPrompt": "Enhanced prompt text"
+}
+```
+
+### POST /api/migrate-prompt
+
+Optimizes a prompt using the llama-prompt-ops library.
+
+**Request Body:**
+```json
+{
+  "prompt": "Your prompt text here",
+  "config": {
+    "taskModel": "Llama 3.3 70B",
+    "proposerModel": "Llama 3.1 8B",
+    "optimizer": "MiPro",
+    "dataset": "Q&A",
+    "metrics": "Exact Match",
+    "useLlamaTips": true
+  }
+}
+```
+
+**Response:**
+```json
+{
+  "optimizedPrompt": "Optimized prompt text"
+}
+```
+
+## Integration with llama-prompt-ops
+
+This backend serves as a development interface for the llama-prompt-ops library, providing web API access to prompt optimization features. When this frontend is eventually integrated into the main llama-prompt-ops repository, this backend functionality will be incorporated into the library's core API structure.