Tools: 🎓 Science Teacher Chatbot — Full Explanation (Everything)

🌱 0️⃣ What We Are Building ## 🧠 1️⃣ How System Works ## 🧰 2️⃣ Technologies ## 📦 3️⃣ Create Project ## 📦 4️⃣ Install Dependencies ## 📁 5️⃣ Folder Structure ## 🔐 6️⃣ OpenAI Key ## 💾 7️⃣ memory.mjs ## What it does ## 🧠 8️⃣ llm.mjs ## What it does ## 🔬 9️⃣ filter.mjs ## What it does ## 🌐 1️⃣0️⃣ route.mjs ## What it does ## 🚀 1️⃣1️⃣ server.mjs ## What it does ## ▶️ 1️⃣2️⃣ Run Project ## 🧪 1️⃣3️⃣ Test API ## 🧠 1️⃣4️⃣ Memory Demo ## ⚠️ 1️⃣5️⃣ Important Notes ## 🏆 1️⃣6️⃣ What You Built (Hero Level) ## 🎓 1️⃣7️⃣ How to Explain to Students We are building a Science Teacher AI chatbot backend. Student: What is gravity? AI: Gravity is a force… Student: explain again AI: As I explained earlier… 👉 AI remembers context. Add script in package.json POST → http://localhost:3000/ask AI remembers context. ✅ LLM backend ✅ LangChain integration ✅ Memory chatbot ✅ Science filter ✅ Express API ✅ Teacher AI This is real AI app architecture. We built an AI teacher using OpenAI. Express receives student questions. LangChain connects AI and memory. Memory stores conversation. Filter ensures science-only answers. Templates let you quickly answer FAQs or store snippets for re-use. Are you sure you want to ? It will become hidden in your post, but will still be visible via the comment's permalink. as well , this person and/or CODE_BLOCK: Student → API → Filter → LangChain → OpenAI → Answer ↑ Memory CODE_BLOCK: Student → API → Filter → LangChain → OpenAI → Answer ↑ Memory CODE_BLOCK: Student → API → Filter → LangChain → OpenAI → Answer ↑ Memory CODE_BLOCK: mkdir science-teacher-bot cd science-teacher-bot pnpm init CODE_BLOCK: mkdir science-teacher-bot cd science-teacher-bot pnpm init CODE_BLOCK: mkdir science-teacher-bot cd science-teacher-bot pnpm init CODE_BLOCK: pnpm add express cors dotenv langchain @langchain/openai nodemon CODE_BLOCK: pnpm add express cors dotenv langchain @langchain/openai nodemon CODE_BLOCK: pnpm add express cors dotenv langchain @langchain/openai nodemon CODE_BLOCK: science-teacher-bot/ │ ├── src/ │ ├── memory.mjs │ ├── llm.mjs │ ├── filter.mjs │ ├── route.mjs │ └── server.mjs │ ├── .env └── package.json CODE_BLOCK: science-teacher-bot/ │ ├── src/ │ ├── memory.mjs │ ├── llm.mjs │ ├── filter.mjs │ ├── route.mjs │ └── server.mjs │ ├── .env └── package.json CODE_BLOCK: science-teacher-bot/ │ ├── src/ │ ├── memory.mjs │ ├── llm.mjs │ ├── filter.mjs │ ├── route.mjs │ └── server.mjs │ ├── .env └── package.json CODE_BLOCK: OPENAI_API_KEY=your_key_here PORT=3000 CODE_BLOCK: OPENAI_API_KEY=your_key_here PORT=3000 CODE_BLOCK: OPENAI_API_KEY=your_key_here PORT=3000 CODE_BLOCK: import { BufferMemory } from "langchain/memory"; export const memory = new BufferMemory({ returnMessages: true, memoryKey: "chat_history", }); CODE_BLOCK: import { BufferMemory } from "langchain/memory"; export const memory = new BufferMemory({ returnMessages: true, memoryKey: "chat_history", }); CODE_BLOCK: import { BufferMemory } from "langchain/memory"; export const memory = new BufferMemory({ returnMessages: true, memoryKey: "chat_history", }); CODE_BLOCK: import "dotenv/config"; import { ChatOpenAI } from "@langchain/openai"; import { ConversationChain } from "langchain/chains"; import { memory } from "./memory.mjs"; const llm = new ChatOpenAI({ model: "gpt-4o-mini", temperature: 0.3, }); const template = ` You are a science teacher. Answer only science questions. Explain in simple way. Conversation: {chat_history} Student: {input} Teacher: `; export const chatChain = new ConversationChain({ llm, memory, prompt: template, }); CODE_BLOCK: import "dotenv/config"; import { ChatOpenAI } from "@langchain/openai"; import { ConversationChain } from "langchain/chains"; import { memory } from "./memory.mjs"; const llm = new ChatOpenAI({ model: "gpt-4o-mini", temperature: 0.3, }); const template = ` You are a science teacher. Answer only science questions. Explain in simple way. Conversation: {chat_history} Student: {input} Teacher: `; export const chatChain = new ConversationChain({ llm, memory, prompt: template, }); CODE_BLOCK: import "dotenv/config"; import { ChatOpenAI } from "@langchain/openai"; import { ConversationChain } from "langchain/chains"; import { memory } from "./memory.mjs"; const llm = new ChatOpenAI({ model: "gpt-4o-mini", temperature: 0.3, }); const template = ` You are a science teacher. Answer only science questions. Explain in simple way. Conversation: {chat_history} Student: {input} Teacher: `; export const chatChain = new ConversationChain({ llm, memory, prompt: template, }); CODE_BLOCK: export function isScience(text) { const words = [ "physics","chemistry","biology", "atom","cell","energy","force", "gravity","plant","reaction", "photosynthesis","molecule" ]; return words.some(w => text.toLowerCase().includes(w) ); } CODE_BLOCK: export function isScience(text) { const words = [ "physics","chemistry","biology", "atom","cell","energy","force", "gravity","plant","reaction", "photosynthesis","molecule" ]; return words.some(w => text.toLowerCase().includes(w) ); } CODE_BLOCK: export function isScience(text) { const words = [ "physics","chemistry","biology", "atom","cell","energy","force", "gravity","plant","reaction", "photosynthesis","molecule" ]; return words.some(w => text.toLowerCase().includes(w) ); } COMMAND_BLOCK: import express from "express"; import { chatChain } from "./llm.mjs"; import { isScience } from "./filter.mjs"; export const router = express.Router(); router.post("/", async (req, res) => { const { text } = req.body; if (!text) { return res.json({ error: "Question required", }); } if (!isScience(text)) { return res.json({ answer: "I only answer science questions.", }); } const response = await chatChain.predict({ input: text, }); res.json({ answer: response }); }); COMMAND_BLOCK: import express from "express"; import { chatChain } from "./llm.mjs"; import { isScience } from "./filter.mjs"; export const router = express.Router(); router.post("/", async (req, res) => { const { text } = req.body; if (!text) { return res.json({ error: "Question required", }); } if (!isScience(text)) { return res.json({ answer: "I only answer science questions.", }); } const response = await chatChain.predict({ input: text, }); res.json({ answer: response }); }); COMMAND_BLOCK: import express from "express"; import { chatChain } from "./llm.mjs"; import { isScience } from "./filter.mjs"; export const router = express.Router(); router.post("/", async (req, res) => { const { text } = req.body; if (!text) { return res.json({ error: "Question required", }); } if (!isScience(text)) { return res.json({ answer: "I only answer science questions.", }); } const response = await chatChain.predict({ input: text, }); res.json({ answer: response }); }); COMMAND_BLOCK: import express from "express"; import cors from "cors"; import "dotenv/config"; import { router } from "./route.mjs"; const app = express(); app.use(cors()); app.use(express.json()); app.use("/ask", router); app.get("/", (req, res) => { res.send("Science Teacher AI running"); }); const PORT = process.env.PORT || 3000; app.listen(PORT, () => { console.log("Server running on", PORT); }); COMMAND_BLOCK: import express from "express"; import cors from "cors"; import "dotenv/config"; import { router } from "./route.mjs"; const app = express(); app.use(cors()); app.use(express.json()); app.use("/ask", router); app.get("/", (req, res) => { res.send("Science Teacher AI running"); }); const PORT = process.env.PORT || 3000; app.listen(PORT, () => { console.log("Server running on", PORT); }); COMMAND_BLOCK: import express from "express"; import cors from "cors"; import "dotenv/config"; import { router } from "./route.mjs"; const app = express(); app.use(cors()); app.use(express.json()); app.use("/ask", router); app.get("/", (req, res) => { res.send("Science Teacher AI running"); }); const PORT = process.env.PORT || 3000; app.listen(PORT, () => { console.log("Server running on", PORT); }); CODE_BLOCK: "scripts": { "dev": "node src/server.mjs" } CODE_BLOCK: "scripts": { "dev": "node src/server.mjs" } CODE_BLOCK: "scripts": { "dev": "node src/server.mjs" } CODE_BLOCK: pnpm dev CODE_BLOCK: { "text": "What is photosynthesis?" } CODE_BLOCK: { "text": "What is photosynthesis?" } CODE_BLOCK: { "text": "What is photosynthesis?" } CODE_BLOCK: { "answer": "Photosynthesis is the process..." } CODE_BLOCK: { "answer": "Photosynthesis is the process..." } CODE_BLOCK: { "answer": "Photosynthesis is the process..." } - answers science questions - explains like teacher - remembers chat - ignores non-science - Student sends question - Express API receives - Science filter checks - LangChain adds memory - OpenAI generates answer - API returns response - Node.js → backend - Express → API - LangChain → LLM framework - OpenAI → AI brain - BufferMemory → chat memory - dotenv → API key - pnpm → package manager - stores chat history - remembers messages - gives context to AI - creates AI model - defines teacher behavior - connects memory - creates chatbot - checks if question is science - blocks other topics - receives question - validates text - checks science - sends answer - creates server - enables JSON - mounts API route - starts backend - What is gravity - explain again - shared for all users - resets on restart - vector store