Dive Into Langgraph En
LangGraph 1.0 Tutorial – English Version
Ask AI about Dive Into Langgraph En
Powered by Claude · Grounded in docs
I know everything about Dive Into Langgraph En. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
Dive into LangGraph
Chinese | English
1. Project Introduction
In mid-October 2025, LangGraph released version 1.0. The development team promised this is a stable version, and the interfaces are not expected to change significantly in the future. Now is the perfect time to learn it.
This is an open-source e-book project aimed at helping Agent developers quickly master the LangGraph framework. LangGraph is an open-source Agent framework developed by the LangChain team. It is powerful and includes everything you need: Memory, MCP, Guardrails, State Management, and Multi-Agent support. LangGraph is typically used together with LangChain: LangChain provides foundational components and tools, while LangGraph handles workflow and state management. Therefore, both libraries need to be learned. To help everyone get started quickly, this tutorial extracts the main features of both libraries and divides them into 14 chapters.
2. Installation
pip install -r requirements.txt
Dependency List
Below is the list of dependencies in requirements.txt:
pydantic
python-dotenv
langchain[openai]
langchain-community
langchain-mcp-adapters
langchain-text-splitters
langgraph
langgraph-cli[inmem]
langgraph-supervisor
langgraph-checkpoint-sqlite
langgraph-checkpoint-redis
langmem
ipynbname
fastmcp
bs4
scikit-learn
supervisor
jieba
dashscope
tavily-python
ddgs
3. Table of Contents
Overview of this tutorial's content:
| No. | Chapter | Main Content |
|---|---|---|
| 1 | Quickstart | Create your first ReAct Agent |
| 2 | StateGraph | Create workflows using StateGraph |
| 3 | Middleware | Use custom middleware to implement four features: budget control, message truncation, sensitive word filtering, and PII detection |
| 4 | Human-in-the-loop | Implement human-in-the-loop using built-in HITL middleware |
| 5 | Memory | Create short-term and long-term memory |
| 6 | Context Engineering | Manage context using State, Store, and Runtime |
| 7 | MCP Server | Create MCP Server and integrate with LangGraph |
| 8 | Supervisor Pattern | Two methods to implement Supervisor Pattern: tool-calling and langgraph-supervisor |
| 9 | Parallelization | How to implement concurrency: node parallelism, @task decorator, Map-reduce, and Sub-graphs |
| 10 | RAG | Three ways to implement RAG: vector retrieval, keyword retrieval, and hybrid retrieval |
| 11 | Web Search | Implement web search: DashScope, Tavily, and DDGS |
| 12 | Deep Agents | Brief introduction to Deep Agents |
| 13 | Gradio APP | Develop a streaming conversational Agent application based on Gradio |
| 14 | Appendix: Debug Page | Introduce the debug page provided by langgraph-cli |
[!NOTE]
Promise: This tutorial is entirely based on LangGraph v1.0, with no legacy code from v0.6.
4. Debug Page
langgraph-cli provides a debug page that can be launched quickly.
langgraph dev
See details: Appendix: Debug Page
5. Practical Chapter
Chapter 13 open-sources an Agent application implemented with Gradio + LangChain. The effect is shown below. You can add more features to this application and customize your own Agent.
See details: /app
6. Further Reading
Official Documentation:
Official Tutorials:
7. How to Contribute
We welcome any form of contribution!
- 🐛 Report Bugs - Submit an Issue if you find any problems
- 💡 Feature Suggestions - Let us know if you have good ideas
- 📝 Content Improvement - Help improve the tutorial content
- 🔧 Code Optimization - Submit Pull Requests
8. License
This work is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.