Agentic (System Monitoring & RAG)

🚀 Self-Agentic Enterprise

Agentic is an example system designed to provide intelligent business services through an agent-based architecture. This project consists of multiple services working in collaboration, offering a comprehensive solution via MCP (Model Control Protocol).

🚀 Quick Start

To get started with the Agentic system, follow the steps below:

Environment Preparation

Ensure the following tools are installed:

• Java 11 or higher
• Maven 3.6 or higher
• Redis 6.x

Build the Project

Run the following command in the root directory:

mvn clean install

Start the Services

Application Agent

cd application-agent && mvn spring-boot:run

RAG Service

cd rag && mvn spring-boot:run

Monitoring Service

cd monitor-service && mvn spring-boot:run

✨ Features

• Agent - Based Architecture: The system is built on an agent - based architecture, with multiple services collaborating to provide intelligent business services.
• MCP - Enabled: It uses the Model Control Protocol (MCP) to communicate between different components, providing a comprehensive solution.
• RAG Service: The RAG (Retrieval Augmented Generation) service offers retrieval - enhanced generation based on stored knowledge.
• Monitoring Service: A monitoring service provides system status information, which is exposed via MCP.

📚 Documentation

Architecture

The system architecture is based on communication between three main components:

• A central application agent that receives user requests.
• A RAG (Retrieval Augmented Generation) service that provides context - aware knowledge to answer queries via MCP.
• A monitoring service that provides system status information, exposed via MCP.

flowchart TD
    subgraph application["application-agent (Port: 8080)"]
        app["🤖 应用程序代理"]
        style app fill:#f0f0f0,stroke:#333,stroke-width:2px
        mc1["监控 MCP 客户端"]
        mc2["RAG MCP 客户端"]
        app --- mc1
        app --- mc2
        style app font-weight:bold
    end
    
    subgraph system-status["Monitor Service (Port: 8081)"]
        status["🤖 系统状态服务"]
        style status fill:#eef7e6,stroke:#333,stroke-width:2px
        status-server["Monitor MCP 服务器"]
        status --- status-server
        style status font-weight:bold
    end

    subgraph rag-service["RAG Service (Port: 8082)"]
        rag["🤖 RAG 代理"]
        style rag fill:#e6f7ff,stroke:#333,stroke-width:2px
        rag-server["Rag MCP 服务器"]
        kb["Redis 向量存储"]
        rag --- rag-server
        rag --- kb
        style rag font-weight:bold
    end

    %% 增加组件之间的间距
    invisible1[" "]
    invisible2[" "]
    
    application ~~~ invisible1 ~~~ rag-service
    application ~~~ invisible2 ~~~ system-status
    
    %% 使用更长的边连接组件
    mc1 --> rag-server
    mc2 --> status-server

    %% 隐藏不可见节点
    style invisible1 fill:none,stroke:none
    style invisible2 fill:none,stroke:none

    classDef server fill:#f0f0f0,stroke:#666,stroke-width:1px
    class rag-server,status-server server

    classDef client fill:#f0f0f0,stroke:#666,stroke-width:1px
    class mc1,mc2 client

    classDef data fill:#f9f9f9,stroke:#999,stroke-width:1px
    class kb,api data

Modules

Application Agent

The main agent that receives user requests via REST endpoints and coordinates other services.

Configuration:

• Port: 8080
• Dependencies: Connects to the rag and monitor services via MCP clients. Configuration File: application.yml

RAG

A Retrieval Augmented Generation (RAG) agent that provides retrieval - enhanced generation based on stored knowledge.

Configuration:

• Port: 8082
• Dependencies: Interacts with a Redis vector store. Configuration File: application.yml

Monitoring Service

A service that monitors the system's running status and metrics.

Configuration:

• Port: 8081
• Dependencies: Uses a standard monitoring protocol. Configuration File: monitor-config.yml

💻 Usage Examples

Basic Usage

Access http://localhost:8080 to enable the application agent. The monitoring panel can be accessed via http://localhost:8081.

🎥 Video Demo

Watch the full video demonstration: Agentic System Overview

(Note: This link is an example. Please replace it with the actual video link.)