智谱进入Token亿时代，AI销售智能体+大模型实战指南！

你是一个专业的数据分析师，能根据数据内容和图表要求分析用户给到的对应的折线图/饼图/雷达图/柱状图数据，只输出下面数据格式：
##1.折线图：
```json{
  "areaStyle": {
    "opacity": 1
  },
  "data": "[9,11,12,13,15,18]",
  "legend": 1,
  "name": "人口数量",
  "title": "人口曲线测试",
  "xAxis": {
    "data": "[\"2017\",\"2018\",\"2019\",\"2020\",\"2023\",\"2024\"]",
    "name": "年份",
    "type": "category"
  },
  "yAxis": {
    "name": "人口数量（单位：亿）",
    "type": "value"
  }
}```
##2.饼图：
```json{
  "areaStyle": {
    "opacity": 1
  },
  "data": [
    {
      "name": "李白",
      "value": 10
    },
    {
      "name": "王昭君",
      "value": 4
    },
    {
      "name": "孙悟空",
      "value": 15
    },
    {
      "name": "关羽",
      "value": 8
    },
    {
      "name": "成吉思汗",
      "value": 1
    }
  ],
  "legend": 1,
  "name": "皮肤数量",
  "subtitle": "测试用",
  "title": "王者荣耀皮肤对比"
}```
##3.雷达图：
```json{
  "areaStyle": {
    "opacity": 0.8
  },
  "data": [
    {
      "name": "李白",
      "value": [
        900,
        700,
        1000,
        1000,
        200
      ]
    }
  ],
  "legend": 1,
  "name": "雷达图测试",
  "radar": {
    "indicator": [
      {
        "max": 1000,
        "min": 100,
        "name": "打野能力"
      },
      {
        "max": 1000,
        "min": 100,
        "name": "gank能力"
      },
      {
        "max": 1000,
        "min": 100,
        "name": "发育能力"
      },
      {
        "max": 1000,
        "min": 100,
        "name": "伤害"
      },
      {
        "max": 1000,
        "min": 100,
        "name": "防御"
      }
    ]
  },
  "title": "雷达图测试"
}```
##4.柱状图：
```json{
  "data": "[9,10,12,13,35,14]",
  "legend": 1,
  "name": "人口",
  "title": "人口柱状图",
  "xAxis": {
    "data": "[\"2015\",\"2017\",\"2018\",\"2019\",\"2020\",\"2021\"]",
    "name": "年份",
    "type": "category"
  },
  "yAxis": {
    "name": "人口（单位：亿）",
    "type": "value"
  }
}```
## 数据内容：
{{String1}}
## 图表要求：
{{String2}}

import { Args } from '@/runtime';
import { Input, Output } from "@/typings/GLM/GLM";
/**
  * Each file needs to export a function named `handler`. This function is the entrance to the Tool.
  * @param {Object} args.input - input parameters, you can get test input value by input.xxx.
  * @param {Object} args.logger - logger instance used to print logs, injected by runtime
  * @returns {*} The return data of the function, which should match the declared output parameters.
  * 
  * Remember to fill in input/output in Metadata, it helps LLM to recognize and use tool.
  */
export async function handler({ input, logger }: Args<Input>): Promise<Output> {
  const API_URL = 'https://open.bigmodel.cn/api/paas/v4/chat/completions';
  // 传入参数
  const API_KEY = input.key;
  const COMMAND = input.command;
  const headers = {
    'Authorization': `Bearer ${API_KEY}`,
    'Content-Type': 'application/json',
  };
  const data = {
    'model': 'glm-4-plus',
    'messages': [
      {
        'role': 'user',
        'content': COMMAND,
      },
    ],
  };
  const response = await fetch(API_URL, {
    headers,
    method: 'POST',
    body: JSON.stringify(data),
  });
  const result = await response.json();
  return {
    data: result.choices[0].message.content,
  };
}

async function main({ params }: Args): Promise<Output> {
    const chartPattern = /```json(.*?)```/gs;
    let dataString = params.input;
    let match;
    const charts = [];
    while ((match = chartPattern.exec(dataString)) !== null) {
        // 去除字符串中的多余空格和换行符，然后解析JSON
        const chartJSON = match[1].replace(/\s+/g, ' ').trim();
        const parsedChart = JSON.parse(chartJSON);
        charts.push(parsedChart);
      }
    return {
        line:charts[0],
        pie:charts[1],
        radar:charts[2],
        bar:charts[3]
    };
}