A powerful backend API built with LangChain.js and Hono, demonstrating various LLM agent capabilities and use cases.

• Streaming Chat API - Real-time streaming responses from LLM
• Memory-enabled Chat - Conversational memory with LangGraph
• Ollama Integration - Local LLM support with configurable models
• Hono Framework - Fast, lightweight web framework
• TypeScript Support - Full type safety and IntelliSense

• Bun (recommended) or Node.js 18+
• Ollama installed and running locally

1. Clone the repository

   git clone <your-repo-url>
   cd langchain

2. Install dependencies

   bun install

3. Set up environment variables Create a .env file in the root directory:

   MODEL_NAME=llama3.2:3b
   MODEL_URL=http://localhost:11434
   MODEL_TEMPERATURE=0.7

4. Start Ollama and pull a model

   ollama serve
   ollama pull llama3.2:3b

5. Run the development server

   bun run dev

6. Access the API Open http://localhost:3000

curl -X POST http://localhost:3000/llm/stream \
  -H "Content-Type: application/json" \
  -d '{"message": "Explain quantum computing in simple terms"}'

curl -X POST http://localhost:3000/llm/memory \
  -H "Content-Type: application/json" \
  -d '{"message": "What did we talk about earlier?"}'

// Streaming example
const response = await fetch('http://localhost:3000/llm/stream', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({ message: 'Tell me a joke' })
});

const reader = response.body?.getReader();
const decoder = new TextDecoder();

while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  console.log(decoder.decode(value));
}

src/
├── index.ts          # Main Hono app and routes
└── llm/
    ├── model.ts      # LLM configuration (Ollama)
    ├── memory.ts     # Memory-enabled chat with LangGraph
    └── stream.ts     # Streaming chat implementation

• Document Q&A Agent - Upload and query documents
• Code Assistant - Code generation and debugging
• Multi-modal Support - Image and text processing
• Tool Calling - Function calling and external API integration

• Research Agent - Web search and information gathering
• Data Analysis Agent - CSV/JSON data processing
• Email Assistant - Email composition and management
• Calendar Agent - Schedule management and planning

• Authentication & Rate Limiting
• Database Integration - Persistent conversation storage
• WebSocket Support - Real-time bidirectional communication
• Agent Orchestration - Multi-agent workflows
• Monitoring & Analytics - Performance tracking

• Customer Support Bot - Ticket classification and responses
• Content Generation - Blog posts, social media content
• Translation Service - Multi-language support
• Code Review Agent - Automated code analysis
• Financial Analysis - Market data processing

1. Create new LLM module in src/llm/
2. Add API endpoint in src/index.ts
3. Update documentation and examples
4. Add tests for new functionality

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

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

• LangChain.js - LLM framework
• Hono - Web framework
• Ollama - Local LLM server
• Bun - JavaScript runtime

Ready to build the future of AI-powered applications! 🚀