LangGraph Tutorial Chatbot

A sophisticated conversational AI chatbot built with LangGraph that demonstrates advanced conversation management, tool integration, memory persistence, and human-in-the-loop functionality for complex query handling.

🌟 Features

• 🧠 Memory Persistence: Maintains conversation context across sessions
• 🔍 Web Search Integration: Real-time information retrieval via Tavily Search API
• 🤖 Google Gemini 2.0 Flash: Fast, efficient AI responses with experimental model support
• 🔄 State Management: Robust conversation flow with conditional routing
• 📝 Interactive CLI: User-friendly command-line interface
• 🛡️ Error Handling: Comprehensive error management and graceful exits
• 📊 Real-time Streaming: Live response generation and display
• 🤝 Human-in-the-Loop: AI can request human assistance for complex queries
• ⏸️ Smart Interrupts: Graph execution pauses for human intervention when needed
• 🔄 Seamless Resumption: Conversation flow continues naturally after human input

🏗️ Architecture

The chatbot is built using a modern, scalable architecture:

• LangGraph StateGraph: Structured conversation flow management
• Tool-based Architecture: Conditional routing with external tool integration
• Memory Checkpointer: Conversation persistence across sessions
• Interrupt-based Human Assistance: Seamless human intervention integration
• Stream-based Processing: Real-time response generation and display

📋 Prerequisites

• Python 3.10 or higher
• Google AI API key (for Gemini access)
• Internet connection (for web search functionality)

🚀 Installation

1. Clone the repository:

   git clone <repository-url>
   cd "LangGraph Tutorial Chatbot"

2. Create and activate a virtual environment:

   python -m venv .venv
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate

3. Install dependencies:

   pip install -r requirements.txt

4. Set up environment variables:

   cp .env.example .env

   Edit the .env file and add your API keys:

   GOOGLE_API_KEY=your_google_api_key_here
   LANGSMITH_API_KEY=your_langsmith_api_key_here  # Optional
   LANGSMITH_TRACING=true  # Optional

🔑 API Keys Setup

Google AI API Key (Required)

1. Visit Google AI Studio
2. Create a new API key
3. Add it to your .env file as GOOGLE_API_KEY

LangSmith API Key (Optional)

1. Visit LangSmith
2. Create an account and get your API key
3. Add it to your .env file as LANGSMITH_API_KEY
4. Set LANGSMITH_TRACING=true to enable tracing

🎯 Usage

Basic Usage

Run the chatbot:

python bot.py

Example Conversations

Simple Query:

User: What's the weather like today?
Assistant: I'll search for current weather information for you...

Complex Query with Human Assistance:

User: Help me plan a detailed itinerary for a 2-week trip to Japan
Assistant: This is a complex request that would benefit from human expertise. Let me get some assistance...
[Human assistance requested - you can provide additional context]

Web Search Integration:

User: What are the latest developments in AI?
Assistant: [Searches web and provides current information with sources]

Commands

• Exit: Type quit, exit, or q to end the conversation
• Help: The chatbot will guide you through its capabilities

🛠️ Configuration

Model Configuration

The chatbot uses Google's Gemini 2.0 Flash model by default. You can modify the model settings in bot.py:

LLM_MODEL = "gemini-2.0-flash-exp"  # Model name
temperature=0.7  # Creativity level (0.0-1.0)
max_tokens=2048  # Maximum response length

Search Configuration

Tavily search settings can be adjusted:

MAX_SEARCH_RESULTS = 10  # Maximum search results
MAX_RESULT_CONTENT_LENGTH = 500  # Content length per result
TOP_RESULTS_LIMIT = 3  # Top results to display

📁 Project Structure

LangGraph Tutorial Chatbot/
├── bot.py                 # Main chatbot application
├── requirements.txt       # Python dependencies
├── .env.example          # Environment variables template
├── .env                  # Your environment variables (create this)
├── CHANGELOG.md          # Project changelog
├── README.md             # This file
├── chatbot.log           # Application logs
└── .venv/                # Virtual environment (created after setup)

🔧 Dependencies

• langgraph: Graph-based conversation flow management
• langchain: Core LangChain functionality
• langchain-google-genai: Google Gemini integration
• langchain-tavily: Web search capabilities
• langsmith: Optional tracing and monitoring
• python-dotenv: Environment variable management

📝 Logging

The application logs all activities to chatbot.log with timestamps and detailed information for debugging and monitoring purposes.

🤝 Human-in-the-Loop

The chatbot can request human assistance for complex queries. When this happens:

1. The AI identifies a query that would benefit from human expertise
2. Graph execution pauses and requests human input
3. You can provide additional context or guidance
4. The conversation resumes with enhanced information

🐛 Troubleshooting

Common Issues

API Key Errors:

• Ensure your Google API key is correctly set in the .env file
• Verify the API key has the necessary permissions

Network Errors:

• Check your internet connection
• Verify firewall settings allow outbound connections

Import Errors:

• Ensure all dependencies are installed: pip install -r requirements.txt
• Verify you're using Python 3.10 or higher

Error Messages

The application provides detailed error messages and suggestions for resolution. Check the console output and chatbot.log for detailed error information.

📊 Version History

See CHANGELOG.md for detailed version history and updates.

👨‍💻 Author

Ebube Imoh

• Version: 1.3.0
• License: MIT

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Update documentation
6. Submit a pull request

📄 License

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

🙏 Acknowledgments

• Built with LangGraph for conversation flow management
• Powered by Google Gemini for AI responses
• Web search provided by Tavily
• Monitoring and tracing via LangSmith