Chatbot-nextjs-webui is a sleek, responsive frontend for interacting with powerful local agents. It supports natural language chat, speech-to-text, text-to-speech, vision tasks, and more — all wrapped in a modern Next.js interface.
🚀 NEW: Full-Stack Integration Setup! This repository now includes scripts to run the complete AI chatbot stack with Chatbot-Python-Core and Multimodal-DB.
The main interface featuring draggable components, audio visualization, anime-style avatar, and the animated starfish triangle background
The api split terminal interface showcasing the different backend api routes
Rendering features include:
- Darcula-style markdown code blocks
- Mermaid diagrams
- LaTeX formulas
- HTML with embedded JavaScript
Just type prompts like:
- "please use LaTeX to explain..."
- "please code me a Python script for a transformers chatbot that..."
- "please create a mermaid chart for..."
- "please create an HTML app with embedded JavaScript that..."
- 🖥️ Modern UI made using Next.js 14 & shadcn/ui with custom theming
- 🔧 Draggable Dashboard with resizable components and magnetic grid layout
- 🌟 Animated Background featuring slow-growing starfish patterns on triangle tessellation
- 💬 Real-time Chat interface with streaming responses and markdown rendering
- 🎵 Audio Visualization with dual-channel waveform display (user/AI)
- 🎭 Add your own Anime-style Avatars integration with customizable character display
- 👁️ Vision Models support for various image analysis tasks (YOLO)
- 🎙️ Speech Integration using Whisper STT and Kokoro/VibeVoice/F5 TTS
- 📊 Responsive Design with rust-orange and banana-yellow color scheme
If you want to run the entire AI chatbot stack including Python backends:
# Clone all three repositories in the same parent folder:
git clone https://github.com/xXSup3rN0v4Xx/chatbot-nextjs-webui.git
git clone https://github.com/xXSup3rN0v4Xx/chatbot-python-core.git
git clone https://github.com/xXSup3rN0v4Xx/multimodal-db.git
# Setup Python environments (first time only)
cd chatbot-nextjs-webui\scripts
.\setup_python_environments.ps1
# Start all services
.\start_all_services.ps1
# Open http://localhost:3000 in your browserThat's it! 🎉 The scripts will:
- ✅ Create Python virtual environments
- ✅ Install all dependencies
- ✅ Start Ollama
- ✅ Start Chatbot-Python-Core (port 8000)
- ✅ Start Multimodal-DB (port 8001)
- ✅ Start WebSocket Bridge (port 2020)
- ✅ Start Next.js WebUI (port 3000)
If you already have backend services running:
cd chatbot-next
npm install
npm run devThen open http://localhost:3000
- Node.js 18+ - For Next.js frontend
- Python 3.10+ - For backend services (if using full stack)
- Ollama - For LLM execution
- Windows - PowerShell scripts (adaptable to Linux/Mac)
chatbot-nextjs-webui/
├── chatbot-next/ # Next.js application
│ ├── src/
│ │ ├── components/ # React components
│ │ │ ├── SpeechRecognition/ # NEW: Microphone recording
│ │ │ ├── TextToSpeech/ # NEW: Audio playback
│ │ │ ├── VisionDetection/ # NEW: YOLO integration
│ │ │ └── ...
│ │ └── app/
│ └── package.json
├── docs/ # Documentation
│ ├── FULLSTACK_SETUP_GUIDE.md # Complete integration guide
│ ├── QUICKSTART_COMPONENTS.md # Component usage guide
│ ├── FRONTEND_COMPONENTS_GUIDE.md # Detailed component docs
│ └── CHANGES_SUMMARY.md # Recent updates
├── scripts/ # Automation scripts
│ ├── setup_python_environments.ps1 # Setup Python backends
│ └── start_all_services.ps1 # Start all services
└── README.md # This file
- FULLSTACK_SETUP_GUIDE.md - Complete setup and architecture
- QUICKSTART_COMPONENTS.md - Quick component integration
- FRONTEND_COMPONENTS_GUIDE.md - Detailed component API
| Service | Port | Purpose |
|---|---|---|
| Next.js WebUI | 3000 | Frontend interface |
| WebSocket Bridge | 2020 | Connects frontend to backends |
| Chatbot-Python-Core | 8000 | AI execution (Ollama, YOLO, Whisper, etc.) |
| Multimodal-DB | 8001 | Storage, memory, RAG, analytics |
| Ollama | 11434 | LLM backend |
cd chatbot-next
npm installnpm run devnpm run build
npm start# Check if bridge is running
curl http://localhost:2020/health# Make sure you ran the setup script
cd scripts
.\setup_python_environments.ps1# Find what's using a port
netstat -ano | findstr :3000
# Kill process
taskkill /F /PID <PID>This WebUI integrates with:
- multimodal-db - Database and storage
- ✅ Added full-stack setup scripts
- ✅ Created SpeechRecognition component
- ✅ Created TextToSpeech component
- ✅ Created VisionDetection component
- ✅ Created ImageGeneration component
- ✅ WebSocket bridge integration
- ✅ Comprehensive documentation
See CHANGES_SUMMARY.md for complete details.
See LICENSE file in this directory.
Built with:
- Next.js + React
- shadcn/ui components
- FastAPI (Python backends)
- Ollama (LLMs)
- YOLO (Object Detection)
- Whisper (Speech Recognition)
- Kokoro/VibeVoice/F5 (Text-to-Speech)
- And many more amazing open-source tools!
Ready to build something amazing? Start with the Quick Start guide above! 🚀