feat: Add NGUI end-to-end example with improved configuration and docs

ngui-e2e/MODEL_CONFIGURATION.md

@@ -0,0 +1,95 @@
+# Model Configuration Guide
+
+This guide explains how to configure your own AI model for the Next Gen UI API.
+
+## Quick Start
+
+The API is pre-configured to work with Ollama and `llama3.2:3b`. To get started:
+
+1. Install Ollama: https://ollama.ai/download
+2. Pull the model: `ollama pull llama3.2:3b`
+3. Start the server: `uvicorn main:app --reload`
+
+## Configuration Options
+
+### Option 1: Edit main.py directly
+
+Open `main.py` and modify these lines:
+
+```python
+MODEL_NAME = "your-preferred-model"    # Line ~39
+BASE_URL = "your-api-url"              # Line ~40
+```
+
+### Option 2: Use Environment Variables
+
+Set environment variables before starting the server:
+
+```bash
+export MODEL_NAME=llama3.2:7b
+export BASE_URL=http://localhost:11434/v1
+uvicorn main:app --reload
+```
+
+## Supported Models
+
+### Ollama Models (Recommended for local development)
+
+```bash
+# Lightweight - good for development
+ollama pull llama3.2:3b
+
+# Better quality - requires more RAM
+ollama pull llama3.2:7b
+
+# Balanced performance
+ollama pull llama3.1:8b
+
+# Good for code-related tasks
+ollama pull codellama:7b
+
+# Alternative option
+ollama pull mistral:7b
+```
+
+### OpenAI API
+
+```bash
+export MODEL_NAME=gpt-3.5-turbo
+export OPENAI_API_KEY=your-api-key
+export BASE_URL=  # Leave empty for OpenAI
+```
+
+### Other OpenAI-Compatible APIs
+
+For services like LocalAI, Oobabooga, vLLM, etc.:
+
+```bash
+export MODEL_NAME=your-model-name
+export BASE_URL=http://your-api-url/v1
+```
+
+## Testing Your Configuration
+
+1. Start the server: `uvicorn main:app --reload`
+2. Check the startup messages for your model configuration
+3. Test with curl:
+
+```bash
+curl -X POST "http://localhost:8000/generate" \
+     -H "Content-Type: application/json" \
+     -d '{"prompt": "Tell me about Toy Story"}'
+```
+
+## Troubleshooting
+
+- **Model not found**: Ensure your model is pulled/available
+- **Connection refused**: Check if your model server is running
+- **API key issues**: Verify your API key is set correctly
+- **Memory issues**: Try a smaller model like `llama3.2:3b`
+
+## Performance Tips
+
+- For development: Use `llama3.2:3b` (fastest)
+- For quality: Use `llama3.2:7b` or `llama3.1:8b`
+- For production: Consider using OpenAI API or a dedicated server

ngui-e2e/NGUI-e2e/.gitignore

@@ -0,0 +1,24 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+pnpm-debug.log*
+lerna-debug.log*
+
+node_modules
+dist
+dist-ssr
+*.local
+
+# Editor directories and files
+.vscode/*
+!.vscode/extensions.json
+.idea
+.DS_Store
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?

ngui-e2e/NGUI-e2e/NODE_UPGRADE_GUIDE.md

@@ -0,0 +1,102 @@
+# Node.js Upgrade Guide
+
+## Issue
+
+You're currently using Node.js v12.22.12, but this project requires Node.js 18+ to run Vite 7.
+
+**Error you're seeing:**
+
+```
+SyntaxError: Unexpected token '.'
+    at Loader.moduleStrategy (internal/modules/esm/translators.js:140:18)
+```
+
+## Solution: Upgrade Node.js
+
+### Option 1: Using Homebrew (Recommended for macOS)
+
+```bash
+# Install latest Node.js LTS
+brew install node
+
+# Verify installation
+node --version
+```
+
+### Option 2: Using Node Version Manager (nvm)
+
+```bash
+# Install nvm (if not already installed)
+curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash
+
+# Restart terminal or run:
+source ~/.bashrc
+
+# Install and use Node.js 18 LTS
+nvm install 18
+nvm use 18
+nvm alias default 18
+
+# Verify installation
+node --version
+```
+
+### Option 3: Download from Official Website
+
+1. Go to [https://nodejs.org/](https://nodejs.org/)
+2. Download the LTS version (18.x or 20.x)
+3. Run the installer
+4. Restart your terminal
+
+## After Upgrading
+
+1. **Verify Node.js version:**
+
+   ```bash
+   node --version
+   # Should show v18.x.x or v20.x.x
+   ```
+
+2. **Clear npm cache (optional but recommended):**
+
+   ```bash
+   npm cache clean --force
+   ```
+
+3. **Reinstall dependencies:**
+
+   ```bash
+   cd /Users/anujrajak/Projects/research/ngui-e2e/NGUI-e2e
+   rm -rf node_modules package-lock.json
+   npm install
+   ```
+
+4. **Start the development server:**
+   ```bash
+   npm run dev
+   ```
+
+## Expected Result
+
+After upgrading, `npm run dev` should start successfully and you'll see:
+
+```
+  VITE v7.x.x  ready in Xms
+
+  ➜  Local:   http://localhost:5173/
+  ➜  Network: use --host to expose
+  ➜  press h + enter to show help
+```
+
+## Features Available After Fix
+
+- ✅ Full-screen AI chatbot interface
+- ✅ Dark mode toggle (sun/moon icons in header)
+- ✅ Two pre-loaded mock messages
+- ✅ Real-time message input with send button
+- ✅ Typing indicator when AI is responding
+- ✅ Auto-scroll to latest messages
+- ✅ Keyboard shortcuts (Enter to send)
+- ✅ Professional PatternFly styling
+
+Your chatbot will be ready to use with all the features you requested!