天地图

🚀 Building a Location Service Proxy Robot with Python and Qianfan Platform

This project leverages Python and the Qianfan platform to create a location service proxy robot. It offers a straightforward way to handle location - related queries.

🚀 Quick Start

Prerequisites

Before you start, make sure you have the necessary environment and permissions to install dependencies and access the Qianfan platform.

📦 Installation

1. Install Dependencies

To run this project, you need to install the following dependencies first:

pip install -r requirements.txt

2. Configure MCP Server

Create a config.py file and add the following content:

class MCPConfig:
    def __init__(self):
        self.app_id = "your_app_id"  # Replace with your Qianfan app ID
        self.token = "your_token"    # Replace with your Qianfan token

3. Download and Install Qianfan SDK

You can download and install the SDK from the Qianfan official documentation.

4. Create an Agent Application

Create a new application on the Qianfan platform and obtain the app_id and token.

5. Configure MCP Server Environment Variables

Set the MCP Server environment variables to your app ID and token:

export APPBUILDER_TOKEN="your_token"

6. Start the MCP Server

Run the following command to start the MCP Server:

python main.py

💻 Usage Examples

Basic Usage

Save the following code as app.py and modify the paths and parameters as needed:

import os
import asyncio
import appbuilder
from appbuilder.core.console.appbuilder_client.async_event_handler import (
    AsyncAppBuilderEventHandler,
)
from appbuilder.mcp_server.client import MCPClient

class MyEventHandler(AsyncAppBuilderEventHandler):
    def __init__(self, mcp_client):
        super().__init__()
        self.mcp_client = mcp_client
    
    def get_current_weather(self, location=None, unit="摄氏度"):
        return "{} 的温度是 {} {}".format(location, 20, unit)
    
    async def interrupt(self, run_context, run_response):
        thought = run_context.current_thought
        # Green print
        print("\033[1;31m", "-> Agent 中间思考: ", thought, "\033[0m")
        tool_output = []
        for tool_call in run_context.current_tool_calls:
            tool_res = ""
            if tool_call.function.name == "get_current_weather":
                tool_res = self.get_current_weather(**tool_call.function.arguments)
            else:
                print(
                    "\033[1;32m",
                    "MCP工具名称: {}, MCP参数:{}\n".format(tool_call.function.name, tool_call.function.arguments),
                    "\033[0m",
                )
                mcp_server_result = await self.mcp_client.call_tool(
                    tool_call.function.name, tool_call.function.arguments
                )
                print("\033[1;33m", "MCP结果: {}\n\033[0m".format(mcp_server_result))
                for i, content in enumerate(mcp_server_result.content):
                    if content.type == "text":
                        tool_res += mcp_server_result.content[i].text
            tool_output.append(
                {
                    "tool_call_id": tool_call.id,
                    "tool_response": tool_res
                }
            )
        return tool_output

async def main():
    # Initialize the MCP client
    mcp_client = MCPClient()
    await mcp_client.start()

    # Create an EventHandler and connect it to the MCP client
    event_handler = MyEventHandler(mcp_client)
    await mcp_client.register_event_handler(event_handler)

    # Wait for user input
    while True:
        query = input("请输入查询: ")
        response = await mcp_client.process_query(query)
        print("\033[1;34m", "Agent 响应:", response, "\033[0m")

if __name__ == "__main__":
    asyncio.run(main())

Running the Robot

Run app.py, and you will see an interactive interface where you can enter location queries.

Example Usage

# Start the MCP Server
python main.py

# Start the Agent in another terminal
python app.py

Enter queries like "北京天气如何？" or "附近有哪些酒店？", and the robot will process and return the results.

✨ Features

Extended Functionality

• Custom Geolocation Services: You can extend the MCPConfig class as needed to add more location - related services.
• Multilingual Support: Support multiple languages by adjusting logs and prompt messages.
• Advanced Analysis: Integrate more data analysis tools to provide more detailed reports.

📄 License

This project is licensed under the MIT License. Please read the license terms carefully before use.

The above is a complete English guide to help you quickly get started with building a location service proxy robot using Python and the Qianfan platform.