Rumah >hujung hadapan web >tutorial js >Mencipta Ejen ReAct dari awal dengan nodeJS ( carian wikipedia )
Kami akan mencipta ejen AI yang mampu mencari Wikipedia dan menjawab soalan berdasarkan maklumat yang ditemuinya. Ejen ReAct (Reason and Act) ini menggunakan API AI Generatif Google untuk memproses pertanyaan dan menjana respons. Ejen kami akan dapat:
Ejen ReAct ialah jenis ejen tertentu yang mengikuti kitaran Refleksi-Tindakan. Ia mencerminkan tugas semasa, berdasarkan maklumat yang tersedia dan tindakan yang boleh dilakukannya, dan kemudian memutuskan tindakan yang perlu diambil atau sama ada untuk menyelesaikan tugasan itu.
Ejen ReAct kami akan mempunyai tiga keadaan utama:
Mari bina Ejen ReAct langkah demi langkah, menyerlahkan setiap keadaan.
Mula-mula, sediakan projek dan pasang kebergantungan:
mkdir react-agent-project cd react-agent-project npm init -y npm install axios dotenv @google/generative-ai
Buat fail .env pada akar projek:
GOOGLE_AI_API_KEY=your_api_key_here
Buat Tools.js dengan kandungan berikut:
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;
Buat ReactAgent.js dengan kandungan berikut:
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"); 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;
Buat index.js dengan kandungan berikut:
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);
Interaksi dengan Wikipedia dilakukan dalam dua langkah utama:
Carian awal (fungsi wikipedia):
Carian terperinci (wikipedia_with_pageId function):
Proses ini membolehkan ejen mendapat gambaran keseluruhan topik yang berkaitan dengan pertanyaan dahulu dan kemudian menyelam lebih dalam ke bahagian tertentu seperti yang diperlukan.
Atas ialah kandungan terperinci Mencipta Ejen ReAct dari awal dengan nodeJS ( carian wikipedia ). Untuk maklumat lanjut, sila ikut artikel berkaitan lain di laman web China PHP!