🤖 Google A2A RAG with Spring, Java, and MongoDB Atlas

This project demonstrates how to build a powerful Retrieval-Augmented Generation (RAG) search application that integrates Google's Agent-to-Agent (A2A) protocol with Spring Boot and MongoDB Atlas. It is deployed live on Hugging Face at:

https://vishalmysore-a2amcpmongo.hf.space/

You can discover active agents via:

https://vishalmysore-a2amcpmongo.hf.space/.well-known/agent.json

a2ajava is a Swiss Army knife for building agentic applications. It is multi-protocol — works seamlessly with both A2A (Agent-to-Agent) and MCP (Model Context Protocol). It is multi-language — supports Java, Kotlin, and Groovy. It is multi-platform — compatible with Gemini, OpenAI, Claude, and Grok. It is multi-client — includes A2A and MCP clients with connectors in Java, Node, and Python. It offers multi-integration — out-of-the-box support for Selenium, human-in-the-loop workflows, and multi-LLM voting for consensus-based decision making. Agents built using the A2A protocol with a2ajava run seamlessly on MCP as well, ensuring maximum interoperability across platforms.

🌟 Key Features

• A2A Protocol Integration: Seamless communication between AI agents
• Vector-Based Search: Powered by MongoDB Atlas for semantic task retrieval
• Real-time Task Storage: Automatic storage of A2A tasks in vector database
• RESTful API: Easy-to-use endpoints for task management
• Spring Boot Framework: Built with enterprise-grade Java technology
• Extensible Architecture: Adaptable for various use cases

🛠️ Technology Stack

• Backend: Spring Boot 3.x
• Database: MongoDB Atlas with Vector Search
• Protocol: Google A2A (Agent-to-Agent)
• Search: Vector-based semantic search
• API Documentation: OpenAPI/Swagger

📝 How It Works

Vector Storage Integration

@Override
public void preProcessing(String method, Object params) {
    vectorService.ragStorage(method, params);
}

Task Management

public void ragStorage(String method, Object params) {
    switch (method) {
        case "tasks/send":
            addTask(new ObjectMapper().convertValue(params, TaskSendParams.class));
            break;
        case "tasks/get":
            addTask(new ObjectMapper().convertValue(params, TaskQueryParams.class));
            break;
    }
}

📸 Visual Guide

1. Agent Setup

2. Chat Interface

3. Data Storage

4. Event Monitoring

5. Claude

6. Claude tool chain

🔍 Using the API

Swagger

https://vishalmysore-a2amcpmongo.hf.space/swagger-ui/index.html

Task Retrieval Example

GET https://vishalmysore-a2amcpmongo.hf.space/taskText?name="cricket"

A2A Curl

🧺 Laundry Machine Agent Curl Commands for Claude

# List Tool
curl -H "Content-Type: application/json" -d '{
"jsonrpc": "2.0",
"method": "tools/list",
"params": {

}
},
"id": 1
}' https://vishalmysore-a2amcpmongo.hf.space/

# Start Washing
curl -H "Content-Type: application/json" -d '{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "startWashing",
    "arguments": {
      "provideAllValuesInPlainEnglish": {}
    }
  },
  "id": 1
}' https://vishalmysore-a2amcpmongo.hf.space/

# Stop Washing
curl  -H "Content-Type: application/json" -d '{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "stopWashing",
    "arguments": {
      "provideAllValuesInPlainEnglish": {}
    }
  },
  "id": 2
}' https://vishalmysore-a2amcpmongo.hf.space/

# Set Temperature to 40
curl -H "Content-Type: application/json" -d '{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "setTemperature",
    "arguments": {
      "provideAllValuesInPlainEnglish": {
        "arg0": 40
      }
    }
  },
  "id": 3
}' https://vishalmysore-a2amcpmongo.hf.space/

# Set Cycle Type to 'delicate'
curl -u user:password -H "Content-Type: application/json" -d '{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "setCycleType",
    "arguments": {
      "provideAllValuesInPlainEnglish": {
        "arg0": "delicate"
      }
    }
  },
  "id": 4
}' https://vishalmysore-a2amcpmongo.hf.space/

# Get Quote for Laundry
curl -u user:password -H "Content-Type: application/json" -d '{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "getQuoteForLaundry",
    "arguments": {
      "provideAllValuesInPlainEnglish": {
        "arg0": "cotton",
        "arg1": "3kg"
      }
    }
  },
  "id": 5
}' https://vishalmysore-a2amcpmongo.hf.space/

# Get Machine Status
curl -u user:password -H "Content-Type: application/json" -d '{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "getStatus",
    "arguments": {
      "provideAllValuesInPlainEnglish": {}
    }
  },
  "id": 6
}' https://vishalmysore-a2amcpmongo.hf.space/

🚀 Getting Started

1. Clone the repository
2. Configure MongoDB Atlas connection in application.yml
3. Set up environment variables:
   • DB_USER
   • DB_PASSWORD
   • OPENAI_API_KEY
4. Build and run with Maven:

   mvn spring-boot:run

📄 License

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

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.