index.js

/**
 * WHAT THIS FILE DOES
 *
 * The front door. Defines the two HTTP endpoints and starts the server.
 *
 *   POST /ingest  -> hands the uploaded PDF to ingest.js
 *   POST /chat    -> hands the question to query.js
 *
 * This file deliberately contains no RAG logic of its own. It validates the
 * request, calls one function, and turns the result (or the error) into JSON.
 *
 * See docs/04-code-walkthrough.md for a line-by-line explanation.
 *
 * @author  Raqibul Hasan Moon <rhmoon21@gmail.com>
 * @created 2026-08-12
 */

require("dotenv").config();
const express = require("express");
const multer = require("multer");
const { initDb } = require("./db");
const { ingestDocument } = require("./ingest");
const { queryDocuments } = require("./query");

const app = express();
// memoryStorage() keeps the uploaded file in a buffer instead of writing it to disk. We parse it and store the chunks immediately, so there's nothing to save.

const upload = multer({ storage: multer.memoryStorage() });

app.use(express.json());

app.post("/ingest", upload.single("file"), async (req, res) => {
  if (!req.file) {
    return res.status(400).json({ error: "No file uploaded" });
  }

  // mimetype comes from the client's multipart headers, so this is a
  // convenience check that produces a clean 400 for honest mistakes — not a
  // security control. A forged Content-Type still reaches the parser, which
  // rejects non-PDF bytes on its own and surfaces as a 500 below.
  if (!req.file.mimetype.includes("pdf")) {
    return res.status(400).json({ error: "Only PDF files are supported" });
  }

  try {
    const count = await ingestDocument(req.file.buffer, req.file.originalname);
    res.json({
      message: `Ingested ${count} chunks from "${req.file.originalname}"`,
    });
  } catch (err) {
    console.error(err);
    res.status(500).json({ error: "Ingestion failed", detail: err.message });
  }
});

app.post("/chat", async (req, res) => {
  const { question } = req.body;

  if (!question || typeof question !== "string") {
    return res.status(400).json({ error: "question is required" });
  }

  try {
    const result = await queryDocuments(question);
    res.json(result);
  } catch (err) {
    console.error(err);
    res.status(500).json({ error: "Query failed", detail: err.message });
  }
});

const PORT = process.env.PORT || 3000;

// Listen only after the schema is ready, so the server never accepts a request
// it cannot serve. If Postgres is unreachable this rejects and the process
// exits non-zero — the correct behaviour: a supervisor should restart it rather
// than leave a half-working server accepting traffic.
initDb().then(() => {
  app.listen(PORT, () => {
    console.log(`RAG chatbot running on port ${PORT}`);
  });
});