LangChain- Develop AI Agents with LangChain & LangGraph 🦜🔗

Learn LangChain and LangGraph by building real world AI Agents (Python, Latest Version 0.3.0+)

This course is designed to teach you how to QUICKLY harness the power of the LangChain library for LLM applications. Build 3 end-to-end working LangChain based generative AI applications with no fluff, no toy examples - just real projects using real APIs and real-world skills.

💡 What You'll Build

This course takes you through building 7 real-world AI agent projects, from simple hello-world applications to advanced agentic systems:

Project	Type	Description
👋 Hello World Agent	Branch (project/hello-world)	Your first AI agent - basic structure and LLM integration
💻 Code Interpreter	Branch (project/code-interpreter)	AI-powered code execution and analysis
🧠 ReAct Under the Hood	Branch (project/react-under-hood)	Understanding reasoning and acting patterns in AI agents
🔍 Ice Breaker	External Repo	Social media profile analyzer
📝 Medium Analyzer	External Repo	Content analysis and insights generator
📚 Documentation Helper	External Repo	Intelligent documentation assistant
🪞 Reflection Agent	External Repo	Self-improving agent with reflection and critique capabilities
🔄 Reflexion Agent	External Repo	Advanced self-correcting agent using reflexion techniques
🤖 Agentic RAG	External Repo	Advanced retrieval-augmented generation system

📚 Course Highlights

• 7 Complete Projects - From beginner to advanced implementations including Ice Breaker, Documentation Helper, and Code Interpreter
• Real-World Applications - Build agents that solve actual problems with live APIs
• Modern Tech Stack - LangChain v0.3+, LangGraph, Pinecone, FAISS, Streamlit
• Practical Skills - Learn RAG, vector databases, prompt engineering, and agent workflows
• Interactive Learning - Follow commits chronologically for step-by-step learning

🤔 Learning Path

Phase 1: Foundations

1. Hello World Chain - Basic agent structure and LLM integration
2. Code Interpreter - Tool calling and code execution capabilities

Phase 2: Real-World Applications

3. Ice Breaker - Data collection and social media integration
4. Documentation Helper - RAG implementation and knowledge management

Phase 3: Advanced Concepts

5. Blog Analyzer - Multi-step reasoning and content analysis
6. Agentic RAG - Self-correcting agents with memory and planning

▶️ Getting Started

🛠️ Prerequisites

• This is not a beginner course - Basic software engineering concepts needed
• Familiarity with: git, Python, environment variables, classes, testing and debugging
• Python 3.10+
• Any Python package manager (uv, poetry, pipenv) - but NOT conda!
• Access to an LLM (can be open source via Ollama, or cloud providers like OpenAI, Anthropic, Gemini)
• No Machine Learning experience needed

⚙️ Setup Instructions

1. Clone the repository

   git clone https://github.com/emarco177/langchain-course
   cd langchain-course

2. Choose your learning path

   For branch-based projects:

   # Start with Hello World
   git checkout project/hello-world
   uv sync
   uv run python main.py
   
   # Progress to Code Interpreter
   git checkout project/code-interpreter
   uv sync
   uv run python main.py

   For external repository projects:

   # Clone specific project repositories
   git clone https://github.com/emarco177/ice_breaker
   cd ice_breaker
   # Follow project-specific setup instructions

3. Follow the commits

   • Each commit represents a lesson or feature implementation
   • Use git log --oneline to see the learning progression
   • Checkout previous commits to understand the development process

📁 Branches Structure

langchain-course/
├── project/hello-world/          # Basic Chain 
├── project/code-interpreter/     # Slim Code execution 
└── project/react-under-hood/     # ReAct Algorithm Deep Dive

External Projects:

• Ice Breaker - Social media profile analyzer
• Medium Analyzer - Content analysis and insights generator
• Documentation Helper - AI documentation assistant
• Reflection Agent - Self-improving agent with reflection and critique capabilities
• Reflexion Agent - Advanced self-correcting agent using reflexion techniques
• Agentic RAG - Advanced retrieval-augmented generation system

📚 Learning Objectives

By the end of this course, you'll be able to:

• Build AI agents from scratch using modern frameworks
• Implement tool calling and external API integrations
• Create RAG systems with vector databases
• Design multi-step reasoning workflows
• Deploy agents to production environments
• Handle error correction and self-improvement in agents
• Optimize agent performance and cost efficiency

🙏 Acknowledgements

Big thanks to the LangChain / LangGraph team and their excellent documentation and tutorials that make this course possible.

🌟 Support

If you find this project helpful, please consider:

• ⭐ Starring the repository
• 🐛 Reporting issues
• 💡 Contributing improvements
• 📢 Sharing with others

---

🔗 Connect with Me

Built with ❤️ by Eden Marco