Ryzenth Docker API

A containerized AI chat API service built with Express.js and Docker, providing seamless access to multiple AI models through a unified interface.

Features

• Multiple AI Models: Access to various AI models (Kimi, GLM, DeepSeek, GPT-OSS, Qwen)
• Streaming Support: Real-time streaming responses for better user experience
• Dockerized: Easy deployment with Docker and Docker Compose
• Production Ready: Health checks, logging, and monitoring
• Security: Bearer token authentication and secure configuration
• Scalable: Built with scalability in mind

📋 Prerequisites

• Docker
• Docker Compose
• Node.js 18+ (for development)

🛠️ Quick Start

Using Docker Compose (Recommended)

1. Clone the repository

git clone https://github.com/TeamKillerX/Ryzenth-Docker-API
cd Ryzenth-Docker-API

2. Create environment file

cp .env.example .env

Edit .env with your configuration:

AUTHORIZATION_KEY=admin1234
ENABLE_MIDDLEWARE_DEBUG=true
APP_HOST_PORT=7860

3. Start services

docker-compose up -d

4. Verify deployment

curl http://localhost:7980/health

Using Docker Run

docker run -d \
  -p 7980:7860 \
  -e AUTHORIZATION_KEY="admin1234" \
  --name ryzenth-api \
  rendyprojects/chat-api:stable

🔧 Configuration

Environment Variables

Variable	Description	Default
ENDPOINT_API_URL	Ryzenth API endpoint	https://api.ryzenths.dpdns.org/api/chat
RYZENTH_API_KEY	Ryzenth service API key	Required
AUTHORIZATION_KEY	Your secure authentication key	Required
APP_HOST_PORT	Application port	7860
NODE_ENV	Environment mode	production
LOG_LEVEL	Logging level	info

Docker Compose Services

• ryzenth-chat-api: Main API service
• nginx-proxy: Reverse proxy (optional)

📡 API Usage

Chat Completion

import requests
import json

url = "http://localhost:7980/api/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "authorization": "Bearer your_secure_auth_key"
}
payload = {
    "model": "kimi-k2",
    "stream": False,
    "messages": [
        {"role": "user", "content": "What AI models are available?"}
    ]
}

response = requests.post(url, headers=headers, json=payload)
print(response.json())

Streaming Chat

import requests
import json

url = "http://localhost:7980/api/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "authorization": "Bearer your_secure_auth_key"
}
payload = {
    "model": "gpt-oss-stable",
    "stream": True,
    "messages": [
        {"role": "user", "content": "Explain AI in simple terms"}
    ]
}

response = requests.post(url, headers=headers, json=payload, stream=True)
for line in response.iter_lines():
    if line:
        print(line.decode('utf-8'))

cURL Examples

Regular Request:

curl -X POST http://localhost:7980/api/v1/chat/completions \
  -H "authorization: Bearer your_secure_auth_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3.1",
    "stream": false,
    "messages": [
      {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Streaming Request:

curl -X POST http://localhost:7980/api/v1/chat/completions \
  -H "authorization: Bearer your_secure_auth_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2",
    "stream": true,
    "messages": [
      {"role": "user", "content": "Tell me a story"}
    ]
  }'

Available Models

• kimi-k2
• glm-4.6
• deepseek-v3.1
• gpt-oss-dev
• gpt-oss-stable
• qwen3-coder

🔍 Monitoring

Health Check

curl http://localhost:7980/health

Response:

{
  "status": "healthy",
  "service": "Ryzenth Chat API",
  "timestamp": "2025-01-15T10:30:00.000Z",
  "version": "1.0"
}

View Logs

docker-compose logs -f ryzenth-chat-api

🚢 Deployment

Production Deployment

1. Set up reverse proxy (nginx configuration included)
2. Configure SSL certificates
3. Set up monitoring (logs, metrics)
4. Configure backup strategies

Development

# Clone and setup
git clone https://github.com/TeamKillerX/Ryzenth-Docker-API
cd Ryzenth-Docker-API

# Build Docker image
docker build -t ryzenth-api .

🛡️ Security

• Bearer token authentication required
• Environment-based configuration
• Input validation and sanitization
• Rate limiting capabilities (with Redis)
• Secure headers and CORS configuration

📊 API Response Format

Success Response

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "kimi-k2",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

Error Response

{
  "error": "Unauthorized: Invalid API key",
  "status": 401,
  "message": "The provided API key is not valid"
}

🐛 Troubleshooting

Common Issues

1. Connection refused

   • Check if Docker containers are running: docker-compose ps
   • Verify port availability

2. Authentication errors

   • Verify AUTHORIZATION_KEY in environment
   • Check Bearer token in request headers

3. Model not available

   • Check available models list
   • Verify model name spelling

Logs

# View all logs
docker-compose logs

# View specific service logs
docker-compose logs ryzenth-chat-api

# Follow logs in real-time
docker-compose logs -f ryzenth-chat-api

🤝 Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

📄 License

This project is licensed under the GNU Affero General Public License v3.0 - see the LICENSE file for details.

👥 Credits

• Developer: Randy W (@xtdevs, @xtsea)
• Credits: @xpushz on Telegram
• Organization: TeamKillerX
• Channel: @RendyProjects on Telegram

📞 Support

• GitHub Issues: Create an issue
• Telegram Channel: @RendyProjects

🔄 Changelog

v1.0.0

• Initial release
• Docker containerization
• Multiple AI model support
• Streaming capabilities
• Production-ready configuration

---

⭐ Star this repo if you find it useful!