angxuejian
MCP Serverangxuejianpublic

langgraph start

一个简单的 langGraph 示例,帮助快速上手。

Repository Info

0
Stars
0
Forks
0
Watchers
0
Issues
Python
Language
MIT License
License

About This Server

一个简单的 langGraph 示例,帮助快速上手。

Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.

Documentation

LangGraph Start

这是一个简单的langGraph示例,快速入门即上手😊


已使用的文档如下:

1、Langchain LLM 、LLM key

2、Langgraph Quickstart

3、How to create and query vector stores => 使用的为OpenAIEmbeddings需要付费,替换为HuggingFaceEmbeddings即可


已实现功能如下:

1、Chatbot

2、Function calling

3、RAG

安装指南

确保已有Python环境,当前使用Python v3.13.2

1、克隆仓库

git clone https://github.com/angxuejian/langgraph-start.git

2、安装依赖

pip install -r requirements.txt

配置说明

需要配置LLM、Web,步骤如下

1、在config目录下创建config.py文件 (可从config.example.py文件复制)

2、添加API密钥,可申请百炼LLM、Tavily Web,均有免费Token使用


# Global LLM configuration
# 阿里云百炼 https://bailian.console.aliyun.com/?tab=model#/model-market
llm = {
    "openai_api_key": 'YOUR_API_KEY',
    "openai_api_base": 'https://dashscope.aliyuncs.com/compatible-mode/v1',
    "model_name": 'qwen-max' # 根据千问文档选择合适的模型,例如 qwen-turbo 或 qwen-plus
}


# Global Web configuration
# tavily https://app.tavily.com/home
web = {
    "tavily_api_key": "YOUR_API_KEY"
}

运行说明

需要科学上网,才能运行;以下命令都在langgraph-start目录下执行

1、运行chatbot,根据配置可使用toolsmemory功能

python main.py

2、运行chatbot rag

默认读取faiss_index文件,可修改file_name来选择读取文件; faiss_index源文件为basedata.txt

python run_rag.py

3、运行embedding model,将自定义文本内容转换为向量(Vectors)的浮点数数组

  • file_name:向量化后的文件名称
  • source_file_name:源文件名称
python run_vector.py

本地会加载BAAI/bge-base-zh模型,推理速度因电脑差异会有快慢之分,没看到控制台输出HuggingFaceEmbeddings done !前,均还在推理,切勿退出。只有运行run_rag.pyrun_vector.py才会使用到向量化

4、使用mcp server,在cursor、windsurf、claude等应用上,打开mcp.json,将以下配置复制粘贴

Windows

{
  "mcpServers": {
    "tools-server": {
      "command": "python",
      "args": [
        "C:\\ABSOLUTE-PATH\\XXXXXXX\\langgraph-start\\mcp\\server.py" 
      ]
    }
  }
}

MacOS or Linux

{
  "mcpServers": {
    "tools-server": {
      "command": "python",
      "args": [
        "/ABSOLUTE-PATH/XXXXXXX/langgraph-start/mcp/server.py" 
      ]
    }
  }
}

目前只有get_current_time_mcpfunction一个函数,询问当前时间,即可调用。

5、运行mcp client,使用本地mcp server工具

python .\mcp\client.py .\mcp\server.py

可替换成其他mcp工具,修改client.py文件中的StdioServerParameters(command='', args=[], env=None)参数即可

交流

可通过 ✉️ 邮箱联系@angxuejian: xuejian.ang@gmail.com

or Issues

希望 LangGraph Start 可以帮助你快速了解 + 上手AI应用😎

Quick Start

1

Clone the repository

git clone https://github.com/angxuejian/langgraph-start
2

Install dependencies

cd langgraph-start
npm install
3

Follow the documentation

Check the repository's README.md file for specific installation and usage instructions.

Repository Details

Ownerangxuejian
Repolanggraph-start
LanguagePython
LicenseMIT License
Last fetched8/10/2025

Recommended MCP Servers

💬

Discord MCP

Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.

integrationsdiscordchat
🔗

Knit MCP

Connect AI agents to 200+ SaaS applications and automate workflows.

integrationsautomationsaas
🕷️

Apify MCP Server

Deploy and interact with Apify actors for web scraping and data extraction.

apifycrawlerdata
🌐

BrowserStack MCP

BrowserStack MCP Server for automated testing across multiple browsers.

testingqabrowsers

Zapier MCP

A Zapier server that provides automation capabilities for various apps.

zapierautomation