Complete tutorials and examples for building with the YG3 API (also known as CLM or Elysia API). From quick starts to production applications.

🚀 Quick Start • 📚 Tutorials • 💡 Examples • 📖 API Docs

Get started with the YG3 API in under 2 minutes!

Sign up at https://app.yg3.ai and create an API key.

pip install openai

The YG3 API is OpenAI-compatible, so you can use the familiar OpenAI SDK!

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key-here",
    base_url="https://elysia-api.ngrok.io/api/public/v1"
)

response = client.chat.completions.create(
    model="elysia",
    messages=[
        {"role": "user", "content": "Hello! Tell me about yourself."}
    ]
)

print(response.choices[0].message.content)

That's it! You're now using the YG3 API. 🎉

• 💡 The API is OpenAI-compatible - swap your base URL and you're good to go
• 🔄 Supports streaming responses
• 🛠️ Works with function calling and tool use
• 📦 Compatible with LangChain, LlamaIndex, and other frameworks

Status: ✅ Complete | Difficulty: Beginner | Time: 10 minutes

Learn how to build an AI agent that can search knowledge bases, check orders, and provide automated customer support using the ReAct (Reasoning + Acting) pattern.

What You'll Build:

• Intelligent customer support agent
• Tool calling with function execution
• Interactive Gradio web interface
• Production-ready code

Key Concepts:

• ReAct pattern
• Tool/function calling
• Prompt engineering
• Agent loops

👉 Start Tutorial →

Quick Stats: This is the #1 most popular agent pattern in 2025 (45.8% of AI agents use it)

We're building a comprehensive tutorial library covering:

• 📖 Different application types
• 🎯 Various use cases
• 💼 Production patterns
• 🔧 Integration guides
• 🚀 Deployment strategies

Want to see something specific? Open an issue to suggest a tutorial!

The YG3 API (also known as the CLM or Elysia API) is a powerful, OpenAI-compatible API for building intelligent applications.

• 🔌 OpenAI Compatible - Drop-in replacement, use the same code
• ⚡ Fast & Reliable - Production-grade infrastructure
• 💰 Cost-Effective - Competitive pricing
• 🛠️ Developer-Friendly - Excellent documentation and support
• 🎯 Powerful - Advanced language understanding and generation with the YG3 family of Concentrated Language Models (CLMs)

✅ Chat Completions - Conversational AI ✅ Function Calling - Tool use and actions ✅ Streaming - Real-time responses ✅ Context Windows - Handle long conversations ✅ Framework Support - LangChain, LlamaIndex, and more

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="elysia",
    openai_api_key="your-api-key",
    openai_api_base="https://elysia-api.ngrok.io/api/public/v1"
)

response = llm.invoke("What can you help me build?")
print(response.content)

from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="elysia",
    api_key="your-api-key",
    api_base="https://elysia-api.ngrok.io/api/public/v1",
    is_chat_model=True
)

response = llm.complete("Explain quantum computing")
print(response)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string"}
                }
            }
        }
    }
]

response = client.chat.completions.create(
    model="elysia",
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
    tools=tools
)

https://elysia-api.ngrok.io/api/public/v1

• elysia - Main production model

# Add to header
Authorization: Bearer YOUR_API_KEY

# Or in SDK
client = OpenAI(api_key="YOUR_API_KEY", base_url="...")

Full API documentation: https://help.yg3.ai

yg3-tutorials/
├── README.md                          # This file
├── tutorials/                         # Complete tutorials
│   └── react-customer-support-agent/ # Part 1: ReAct agent
│       ├── README.md
│       └── Customer_Support_Demo.ipynb 
│
├── examples/                          # Quick examples [COMING SOON]
│   ├── quickstart/                   # Getting started examples [COMING SOON]
│   ├── streaming/                    # Streaming responses [COMING SOON]
│   ├── function-calling/             # Tool use examples [COMING SOON]
│   └── integrations/                 # Framework integrations [COMING SOON]
│
└── resources/                         # Additional resources [COMING SOON]
    ├── api-reference.md              # Detailed API docs [COMING SOON]
    ├── best-practices.md             # Tips and patterns [COMING SOON]
    └── troubleshooting.md            # Common issues [COMING SOON]

What can you build with the YG3 API?

• 🤖 Customer Support - Automated support agents
• 📧 Email Automation - Smart email responses
• 📊 Data Analysis - Natural language to insights
• 💼 Sales Assistance - Lead qualification and follow-up

• 💻 Code Assistance - Code generation and review
• 📝 Documentation - Auto-generated docs
• 🧪 Testing - Test case generation
• 🔍 Code Search - Natural language code search

• ✍️ Writing - Blog posts, articles, copy
• 🎨 Marketing - Ad copy, social media
• 📚 Education - Lesson plans, explanations
• 🌐 Translation - Multilingual content

• 🧠 AI Agents - Autonomous decision-making systems
• 🔗 Workflows - Intelligent automation
• 🎯 Personalization - Tailored user experiences
• 📈 Analytics - Conversational business intelligence

Goal: Learn the basics

1. Read the Quick Start
2. Make your first API call
3. Try different parameters
4. Explore Tutorial 1

Time: 30 minutes

Goal: Build production apps quickly

1. Skim Quick Start
2. Review API Reference
3. Check Integration Examples
4. Build your use case
5. Review Best Practices

Time: 15 minutes to first app

Goal: Integrate with existing tools

1. Find your framework in Integration Examples
2. Swap base URL in your existing code
3. Test with YG3 API
4. Deploy

Frameworks Supported:

• LangChain
• LlamaIndex
• Haystack
• Semantic Kernel
• AutoGen
• CrewAI

Time: 5 minutes

Ready to deploy? Make sure you have:

• Error Handling - Catch and handle API errors
• Rate Limiting - Implement backoff strategies
• API Key Security - Never expose in client-side code
• Logging - Track usage and errors
• Monitoring - Alert on failures
• Cost Tracking - Monitor token usage
• Fallbacks - Handle API downtime
• Testing - Unit and integration tests

See Best Practices for details.

We welcome contributions! Here's how:

1. Fork this repository
2. Create a new folder in tutorials/
3. Include: README, code, notebook
4. Submit a pull request

• Fix bugs
• Add new examples
• Improve documentation
• Share your use case

• Found a bug? Open an issue
• Have a question? Start a discussion

• 📖 Documentation: help.yg3.ai
• 💬 Discussions: GitHub Discussions
• 🐛 Issues: Report bugs
• 📧 Email: support@yg3.ai

Built something cool? Share it!

• Show and Tell
• Tag #YG3API on social media
• Submit to our showcase

• ✅ Quick Start guide
• ✅ Tutorial 1: ReAct Customer Support Agent
• ✅ Integration examples
• ✅ API reference

• 🚧 More comprehensive tutorials
• 🚧 Additional code examples
• 🚧 Video walkthroughs
• 🚧 Community showcase
• 🚧 Advanced patterns and use cases

Want to influence the roadmap? Share your ideas

This project is licensed under the MIT License - see the LICENSE file for details.

You're free to use, modify, and distribute this code for any purpose.

• YG3 Team - For building an amazing API
• OpenAI - For the API standard
• Community Contributors - Everyone who improves these tutorials
• You - For building with YG3!

If these tutorials helped you, give us a star! ⭐

It helps others discover these resources.