当前位置：首页 > 文章列表 > 文章 > 前端 > 使用 nodeJS 从头开始创建 ReAct Agent（维基百科搜索）

使用 nodeJS 从头开始创建 ReAct Agent（维基百科搜索）

来源：dev.to 2024-10-01 19:31:01 0浏览收藏

推广推荐

支持 PC / 移动端，安全直达

哈喽！今天心血来潮给大家带来了《使用 nodeJS 从头开始创建 ReAct Agent（维基百科搜索）》，想必大家应该对文章都不陌生吧，那么阅读本文就都不会很困难，以下内容主要涉及到，若是你正在学习文章，千万别错过这篇文章~希望能帮助到你！

介绍

我们将创建一个能够搜索维基百科并根据找到的信息回答问题的人工智能代理。该 react（理性与行动）代理使用 google generative ai api 来处理查询并生成响应。我们的代理将能够：

搜索维基百科获取相关信息。
从维基百科页面中提取特定部分。
对收集到的信息进行推理并制定答案。

[2] 什么是react代理？

react agent 是一种遵循反射-操作循环的特定类型的代理。它根据可用信息和它可以执行的操作反映当前任务，然后决定采取哪个操作或是否结束任务。

[3] 规划代理

3.1 所需工具

node.js
用于 http 请求的 axios 库
google 生成式 ai api (gemini-1.5-flash)
维基百科 api

3.2 代理结构

我们的 react agent 将具有三个主要状态：

思想（反思）
行动（执行）
答案（回复）

3.3 思想状态

思想状态是reactagent反思收集到的信息并决定下一步应该做什么的时刻。

async thought() {
 .....
}

4.4 动作状态（action）

在动作状态下，代理根据先前的想法执行可用功能之一。
请注意，存在操作（执行）和操作的决策。
这只是一个 llm 通话，内容为：
保证发送到函数的参数。
避免在 javascript 中使用大量正则表达式或转换。

async action() {
 // call the decision 
 // execute the action and return a actionresult
}

async decideaction() {
 // call the llm based on the thought ( reflection ) to format and adequate the functioncall.
// look around for a function-tool mode at [google dapi docs](https://ai.google.dev/gemini-api/docs/function-calling)
}

[4] 实现代理

让我们逐步构建 react agent，突出显示每个状态。

4.1 初始设置

首先，设置项目并安装依赖项：

mkdir react-agent-project
cd react-agent-project
npm init -y
npm install axios dotenv @google/generative-ai

在项目根目录创建一个 .env 文件：

google_ai_api_key=your_api_key_here

在这里获取 apikey

4.2 创建tools.js文件

使用以下内容创建 tools.js：

const axios = require("axios");

class tools {
  static async wikipedia(q) {
    try {
      const response = await axios.get("https://en.wikipedia.org/w/api.php", {
        params: {
          action: "query",
          list: "search",
          srsearch: q,
          srwhat: "text",
          format: "json",
          srlimit: 4,
        },
      });

      const results = await promise.all(
        response.data.query.search.map(async (searchresult) => {
          const sectionresponse = await axios.get(
            "https://en.wikipedia.org/w/api.php",
            {
              params: {
                action: "parse",
                pageid: searchresult.pageid,
                prop: "sections",
                format: "json",
              },
            },
          );

          const sections = object.values(
            sectionresponse.data.parse.sections,
          ).map((section) => `${section.index}, ${section.line}`);

          return {
            pagetitle: searchresult.title,
            snippet: searchresult.snippet,
            pageid: searchresult.pageid,
            sections: sections,
          };
        }),
      );

      return results
        .map(
          (result) =>
            `snippet: ${result.snippet}\npageid: ${result.pageid}\nsections: ${json.stringify(result.sections)}`,
        )
        .join("\n\n");
    } catch (error) {
      console.error("error fetching from wikipedia:", error);
      return "error fetching data from wikipedia";
    }
  }

  static async wikipedia_with_pageid(pageid, sectionid) {
    if (sectionid) {
      const response = await axios.get("https://en.wikipedia.org/w/api.php", {
        params: {
          action: "parse",
          format: "json",
          pageid: parseint(pageid),
          prop: "wikitext",
          section: parseint(sectionid),
          disabletoc: 1,
        },
      });
      return object.values(response.data.parse?.wikitext ?? {})[0]?.substring(
        0,
        25000,
      );
    } else {
      const response = await axios.get("https://en.wikipedia.org/w/api.php", {
        params: {
          action: "query",
          pageids: parseint(pageid),
          prop: "extracts",
          exintro: true,
          explaintext: true,
          format: "json",
        },
      });
      return object.values(response.data?.query.pages)[0]?.extract;
    }
  }
}

module.exports = tools;

4.3 创建reactagent.js文件

使用以下内容创建 reactagent.js：

require("dotenv").config();
const { googlegenerativeai } = require("@google/generative-ai");
const tools = require("./tools");

const genai = new googlegenerativeai(process.env.google_ai_api_key);

class reactagent {
  constructor(query, functions) {
    this.query = query;
    this.functions = new set(functions);
    this.state = "thought";
    this._history = [];
    this.model = genai.getgenerativemodel({
      model: "gemini-1.5-flash",
      temperature: 2,
    });
  }

  get history() {
    return this._history;
  }

  pushhistory(value) {
    this._history.push(`\n ${value}`);
  }

  async run() {
    this.pushhistory(`**task: ${this.query} **`);
    try {
      return await this.step();
    } catch (e) {
      if (e.message.includes("exhausted")) {
        return "sorry, i'm exhausted, i can't process your request anymore. ><";
      }
      return "unable to process your request, please try again? ><";
    }
  }

  async step() {
    const colors = {
      reset: "\x1b[0m",
      yellow: "\x1b[33m",
      red: "\x1b[31m",
      cyan: "\x1b[36m",
    };

    console.log("====================================");
    console.log(
      `next movement: ${
        this.state === "thought"
          ? colors.yellow
          : this.state === "action"
            ? colors.red
            : this.state === "answer"
              ? colors.cyan
              : colors.reset
      }${this.state}${colors.reset}`,
    );
    console.log(`last movement: ${this.history[this.history.length - 1]}`);
    console.log("====================================");
    switch (this.state) {
      case "thought":
        await this.thought();
        break;
      case "action":
        await this.action();
        break;
      case "answer":
        await this.answer();
        break;
    }
  }

  async promptmodel(prompt) {
    const result = await this.model.generatecontent(prompt);
    const response = await result.response;
    return response.text();
  }


  async thought() {
    const availablefunctions = json.stringify(array.from(this.functions));
    const historycontext = this.history.join("\n");

//play around with the prompt to perceive the differences.
//feel free to comment asking for guidance if anything.
//feel free to comment looking for guidance.
//improving the thought part can be as simple as adding this two lines to the beginning of the prompt: becoming :  

//your task to fullfill ${this.query}.
//if you already have an answer for the task, you can go ahead and 
fullfill it.
//otherwise you act accordingly to the following scenario >>>


    const prompt = `your task to fullfill ${this.query}.
context contains all the reflection you made so far and the actionresult you collected.
availableactions are functions you can call whenever you need more data.

context: "${historycontext}" <<

availableactions: "${availablefunctions}" <<

task: "${this.query}" <<

reflect uppon your task using context, actionresult and availableactions to find your next_step.
print your next_step with a thought or fullfill your task `;

    const thought = await this.promptmodel(prompt);
    this.pushhistory(`\n **${thought.trim()}**`);
    if (
      thought.tolowercase().includes("fullfill") ||
      thought.tolowercase().includes("fulfill")
    ) {
      this.state = "answer";
      return await this.step();
    }
    this.state = "action";
    return await this.step();
  }

  async action() {
    const action = await this.decideaction();
    this.pushhistory(`** action: ${action} **`);
    const result = await this.executefunctioncall(action);
    this.pushhistory(`** actionresult: ${result} **`);
    this.state = "thought";
    return await this.step();
  }

  async decideaction() {
    const availablefunctions = json.stringify(array.from(this.functions));
    const historycontext = this.history;
    const prompt = `reflect uppon the thought, query and availableactions

    ${historycontext[historycontext.length - 2]}

    thought <<< ${historycontext[historycontext.length - 1]}

    query: "${this.query}"

    availableactions: ${availablefunctions}

    output only the function,parametervalues separated by a comma. for example: "wikipedia,ronaldinho gaucho, 1450"`;

    const decision = await this.promptmodel(prompt);
    return `${decision.replace(/`/g, "").trim()}`;
  }

  async executefunctioncall(functioncall) {
    const [functionname, ...args] = functioncall.split(",");
    const func = tools[functionname.trim()];
    if (func) {
      return await func.call(null, ...args);
    }
    throw new error(`function ${functionname} not found`);
  }

  async answer() {
    const historycontext = this.history;
    const prompt = `based on the following context, provide a complete, detailed and descriptive formated answer for the following task: ${this.query} .

context:
${historycontext}

task: "${this.query}"`;

    const finalanswer = await this.promptmodel(prompt);
    this.history.push(`answer: ${this.finalanswer}`);
    console.log("we will answer >>>>>>>", finalanswer);
    return finalanswer;
  }
}

module.exports = reactagent;

4.4 运行代理（index.js）

使用以下内容创建index.js：

const ReActAgent = require("./ReactAgent.js");

async function main() {
  const query = "What does England border with?";
  // const query = "what are the neighbourhoods of Joinville?";
  // const query = "what is the capital of France?";
  // const query = "What does england borders with?";
  // const query = "what is the color of the sky?";
  const functions = [
    [
      "wikipedia",
      "params: query",
      "Semantic Search Wikipedia API for snippets, pageIds and sectionIds >> \n ex: Date brazil has been colonized? \n Brazil was colonized at 1500, pageId, sections : []",
    ],
    [
      "wikipedia_with_pageId",
      "params : pageId, sectionId",
      "Search Wikipedia API for data using a pageId and a sectionIndex as params.  \n ex: 1500, 1234 \n Section information about blablalbal",
    ],
  ];

  const agent = new ReActAgent(query, functions);
  try {
    const result = await agent.run();
    console.log("THE AGENT RETURN THE FOLLOWING >>>", result);
  } catch (e) {
    console.log("FAILED TO RUN T.T", e);
  }
}

main().catch(console.error);