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:
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。
我们的 react agent 将具有三个主要状态:
让我们逐步构建 react agent,突出显示每个状态。
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
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;
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. >>>>>>>", finalanswer); return finalanswer; } } module.exports = reactagent;
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 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);
与维基百科的交互主要分为两个步骤:
初始搜索(维基百科功能):
详细搜索(wikipedia_with_pageid函数):
此过程允许代理首先获得与查询相关的主题的概述,然后根据需要深入研究特定部分。