Added a frontend/Chrome Extension

README.md

@@ -1,4 +1,4 @@
-# 🌐 RAGBot 
+# 🤖 RAGBot
 
 A cloud-native, multi-tenant AI chatbot that instantly learns the content of any website and answers questions in real-time. Built for the Cloud Computing final project.
 
@@ -26,14 +26,17 @@ A cloud-native, multi-tenant AI chatbot that instantly learns the content of any
 ## 📂 Project Structure
 
 ```bash
-├── server.py           # Main FastAPI entry point
-├── crawler.py          # Logic for sitemap parsing & scraping
-├── vectorstore.py      # Pinecone batching & management
-├── config.py           # Environment & Logging setup
-├── utils.py            # Security & URL validation
-├── schemas.py          # Pydantic data models
-├── extension/          # Chrome Extension Source Code
+ragbot/
+├── api/                    # 🐍 Backend Logic
+│   ├── server.py           # Main FastAPI entry point
+│   ├── crawler.py          # Logic for sitemap parsing & scraping
+│   ├── vectorstore.py      # Pinecone batching & management
+│   ├── config.py           # Environment & Logging setup
+│   ├── utils.py            # Security & URL validation
+│   ├── schemas.py          # Pydantic data models
+│   └── requirements.txt    # Python Dependencies
+├── extension/              # 🧩 Frontend Client
 │   ├── manifest.json
 │   ├── popup.html
 │   └── popup.js
-└── requirements.txt    # Python Dependencies
+└── README.md               # Documentation

api/config.py

@@ -2,7 +2,7 @@ import os
 import sys
 import logging
 from dotenv import load_dotenv
-from vectorstore import VectorStoreManager
+from api.vectorstore import VectorStoreManager
 import google.generativeai as genai
 
 logging.basicConfig(
@@ -38,6 +38,7 @@ try:
     genai.configure(api_key=GOOGLE_API_KEY)  # type: ignore
     flash = genai.GenerativeModel("gemini-2.0-flash")  # type: ignore
 
+    logger.info("✅ System initialized: Pinecone & Gemini ready.")
 except Exception as e:
     logger.critical(f"Startup Failure: {e}")
     sys.exit(1)

api/crawler.py

@@ -1,7 +1,7 @@
 import time
 import trafilatura
 from trafilatura.sitemaps import sitemap_search
-from utils import logger, is_valid_url
+from api.utils import logger, is_valid_url
 
 
 def smart_chunk(text: str, chunk_size=500) -> list[str]:

api/server.py

@@ -1,10 +1,10 @@
 from fastapi import FastAPI, BackgroundTasks, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
 
-from utils import get_namespace_id, logger
-from crawler import crawl_website
-from schemas import ChatRequest, IngestRequest
-from config import vs, flash
+from api.utils import get_namespace_id, logger
+from api.crawler import crawl_website
+from api.schemas import ChatRequest, IngestRequest
+from api.config import vs, flash
 
 app = FastAPI(title="RAG Chatbot API", version="1.0")
 

api/vectorstore.py

@@ -2,7 +2,7 @@ from typing import Any
 import uuid
 from pinecone import Pinecone, ServerlessSpec
 from sentence_transformers import SentenceTransformer
-from utils import logger
+from api.utils import logger
 
 
 class VectorStoreManager:

chrome-extension/manifest.json

@@ -0,0 +1,22 @@
+{
+  "name": "Ragbot",
+  "description": "Chat with any website using RAG.",
+  "version": "1.0",
+  "manifest_version": 3,
+  "action": {
+    "default_popup": "popup.html",
+    "default_icon": {
+      "16": "icons/icon16.png",
+      "48": "icons/icon48.png",
+      "128": "icons/icon128.png"
+    }
+  },
+  "icons": {
+    "16": "icons/icon16.png",
+    "32": "icons/icon32.png",
+    "48": "icons/icon48.png",
+    "128": "icons/icon128.png"
+  },
+  "permissions": ["activeTab", "scripting"],
+  "host_permissions": ["http://localhost:8000/*"]
+}

chrome-extension/popup.css

@@ -0,0 +1,186 @@
+* {
+  box-sizing: border-box;
+}
+
+body {
+  width: 360px;
+  height: 500px;
+  font-family:
+    -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial,
+    sans-serif;
+  margin: 0;
+  padding: 0;
+  background-color: #ffffff;
+  color: #1a1a1a;
+  display: flex;
+  flex-direction: column;
+}
+
+header {
+  padding: 15px;
+  border-bottom: 1px solid #eaeaea;
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  background: #fafafa;
+}
+
+h1 {
+  margin: 0;
+  font-size: 16px;
+  font-weight: 600;
+}
+
+.badge {
+  font-size: 10px;
+  padding: 2px 6px;
+  border-radius: 4px;
+  background: #eee;
+  color: #666;
+}
+
+main {
+  flex: 1;
+  overflow: hidden;
+  display: flex;
+  flex-direction: column;
+}
+
+.view {
+  padding: 20px;
+  flex: 1;
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  justify-content: center;
+  text-align: center;
+}
+
+.hidden {
+  display: none !important;
+}
+
+.icon-large {
+  font-size: 48px;
+  margin-bottom: 15px;
+}
+
+h2 {
+  margin: 0 0 10px 0;
+  font-size: 18px;
+}
+
+p {
+  margin: 0 0 20px 0;
+  font-size: 13px;
+  color: #666;
+  line-height: 1.4;
+}
+
+button {
+  background: #000;
+  color: #fff;
+  border: none;
+  padding: 10px 20px;
+  border-radius: 6px;
+  font-size: 14px;
+  font-weight: 500;
+  cursor: pointer;
+  transition: opacity 0.2s;
+  width: 100%;
+}
+
+button:hover {
+  opacity: 0.8;
+}
+
+button:disabled {
+  background: #ccc;
+  cursor: not-allowed;
+}
+
+#chat-view {
+  justify-content: flex-start;
+  padding: 0;
+}
+
+#messages {
+  flex: 1;
+  width: 100%;
+  overflow-y: auto;
+  padding: 15px;
+  display: flex;
+  flex-direction: column;
+  gap: 10px;
+}
+
+.msg {
+  max-width: 85%;
+  padding: 8px 12px;
+  border-radius: 12px;
+  font-size: 13px;
+  line-height: 1.4;
+  word-wrap: break-word;
+}
+.msg.user {
+  align-self: flex-end;
+  background: #000;
+  color: #fff;
+  border-bottom-right-radius: 2px;
+}
+.msg.bot {
+  align-self: flex-start;
+  background: #f0f0f0;
+  color: #000;
+  border-bottom-left-radius: 2px;
+}
+.msg.error {
+  align-self: center;
+  background: #ffebee;
+  color: #c62828;
+  font-size: 12px;
+}
+
+.input-area {
+  width: 100%;
+  padding: 15px;
+  border-top: 1px solid #eaeaea;
+  display: flex;
+  gap: 10px;
+  background: #fff;
+}
+
+input {
+  flex: 1;
+  padding: 10px;
+  border: 1px solid #ddd;
+  border-radius: 6px;
+  outline: none;
+  font-size: 14px;
+}
+input:focus {
+  border-color: #000;
+}
+.send-btn {
+  width: auto;
+  padding: 0 15px;
+}
+
+.loader {
+  border: 3px solid #f3f3f3;
+  border-top: 3px solid #000;
+  border-radius: 50%;
+  width: 20px;
+  height: 20px;
+  animation: spin 1s linear infinite;
+  display: inline-block;
+}
+
+@keyframes spin {
+  0% {
+    transform: rotate(0deg);
+  }
+  100% {
+    transform: rotate(360deg);
+  }
+}

chrome-extension/popup.html

@@ -0,0 +1,56 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>RAG Bot</title>
+    <link rel="stylesheet" href="popup.css" />
+    <script src="popup.js" defer></script>
+  </head>
+  <body>
+    <header>
+      <h1>RAG Bot</h1>
+      <span id="domain-badge" class="badge">Checking...</span>
+    </header>
+
+    <main>
+      <div id="loading-view" class="view">
+        <div class="loader"></div>
+        <p>Connecting to Brain...</p>
+      </div>
+
+      <!-- Train View -->
+      <div id="train-view" class="view hidden">
+        <div class="icon-large">🧠</div>
+        <h2>New Knowledge</h2>
+        <p>
+          I haven't read this website yet.<br />Train me to answer questions
+          about it.
+        </p>
+        <button id="train-btn">Train on this Page</button>
+        <p id="train-status" class="hidden">
+          <span class="loader"></span>
+          Processing...
+        </p>
+      </div>
+
+      <!-- Chat View -->
+      <div id="chat-view" class="view hidden">
+        <div id="messages">
+          <div class="msg bot">Hello! Ask me anything about this page.</div>
+        </div>
+        <div class="input-area">
+          <input
+            type="text"
+            id="user-input"
+            placeholder="Ask a question..."
+            autocomplete="off"
+          />
+          <button id="send-btn" class="send-btn">↑</button>
+        </div>
+      </div>
+    </main>
+
+    <!-- The Logic -->
+  </body>
+</html>

chrome-extension/popup.js

@@ -0,0 +1,162 @@
+// Config
+const API_BASE = "http://localhost:8000";
+
+// DOM Elements
+const views = {
+  loading: document.getElementById("loading-view"),
+  train: document.getElementById("train-view"),
+  chat: document.getElementById("chat-view"),
+};
+const els = {
+  domainBadge: document.getElementById("domain-badge"),
+  trainBtn: document.getElementById("train-btn"),
+  trainStatus: document.getElementById("train-status"),
+  messages: document.getElementById("messages"),
+  input: document.getElementById("user-input"),
+  sendBtn: document.getElementById("send-btn"),
+};
+
+// State
+let currentUrl = "";
+
+// --- Initialization ---
+
+document.addEventListener("DOMContentLoaded", async () => {
+  try {
+    const tab = await getCurrentTab();
+    currentUrl = tab.url;
+
+    // Update Badge with Domain
+    const urlObj = new URL(currentUrl);
+    els.domainBadge.textContent = urlObj.hostname;
+
+    // Check Backend
+    await checkIndexStatus(currentUrl);
+  } catch (err) {
+    showError("Error: " + err.message);
+  }
+});
+
+// --- Core Logic ---
+
+async function checkIndexStatus(url) {
+  showView("loading");
+
+  try {
+    const res = await fetch(`${API_BASE}/check`, {
+      method: "POST",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({ url: url }),
+    });
+
+    const data = await res.json();
+
+    if (data.exists) {
+      showView("chat");
+    } else {
+      showView("train");
+    }
+  } catch (err) {
+    showError("Backend Offline. Is server.py running?");
+  }
+}
+
+async function startTraining() {
+  els.trainBtn.disabled = true;
+  els.trainStatus.classList.remove("hidden");
+
+  try {
+    const res = await fetch(`${API_BASE}/ingest`, {
+      method: "POST",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({ url: currentUrl }),
+    });
+
+    const data = await res.json();
+
+    // Since ingestion is background, we wait a bit then switch to chat
+    // In a real app, we would poll status. Here we fake a 2s delay.
+    setTimeout(() => {
+      showView("chat");
+      addMessage(
+        "bot",
+        "I've started reading this site! You can ask me questions now. (Note: It might take a minute to finish reading everything).",
+      );
+    }, 2000);
+  } catch (err) {
+    els.trainBtn.disabled = false;
+    els.trainStatus.classList.add("hidden");
+    alert("Training failed: " + err.message);
+  }
+}
+
+async function sendMessage() {
+  const text = els.input.value.trim();
+  if (!text) return;
+
+  // UI Updates
+  addMessage("user", text);
+  els.input.value = "";
+  els.input.disabled = true;
+  els.sendBtn.disabled = true;
+
+  try {
+    const res = await fetch(`${API_BASE}/chat`, {
+      method: "POST",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({
+        message: text,
+        url: currentUrl,
+      }),
+    });
+
+    if (!res.ok) throw new Error("API Error");
+
+    const data = await res.json();
+    addMessage("bot", data.answer);
+  } catch (err) {
+    addMessage("error", "Failed to get response. Try again.");
+  } finally {
+    els.input.disabled = false;
+    els.sendBtn.disabled = false;
+    els.input.focus();
+  }
+}
+
+// --- Utilities ---
+
+function getCurrentTab() {
+  return new Promise((resolve, reject) => {
+    chrome.tabs.query({ active: true, currentWindow: true }, (tabs) => {
+      if (tabs[0]) resolve(tabs[0]);
+      else reject(new Error("No active tab"));
+    });
+  });
+}
+
+function showView(name) {
+  Object.values(views).forEach((el) => el.classList.add("hidden"));
+  views[name].classList.remove("hidden");
+}
+
+function addMessage(type, text) {
+  const div = document.createElement("div");
+  div.className = `msg ${type}`;
+  div.innerText = text; // Safe text insertion
+  els.messages.appendChild(div);
+  els.messages.scrollTop = els.messages.scrollHeight;
+}
+
+function showError(msg) {
+  document.body.innerHTML = `<div style="padding:20px; color:red; text-align:center;">${msg}</div>`;
+}
+
+// --- Event Listeners ---
+
+els.trainBtn.addEventListener("click", startTraining);
+
+els.sendBtn.addEventListener("click", sendMessage);
+
+els.input.addEventListener("keypress", (e) => {
+  if (e.key === "Enter") sendMessage();
+});

requirements.txt

@@ -1,11 +1,7 @@
-altair==5.5.0
 annotated-doc==0.0.4
 annotated-types==0.7.0
 anyio==4.11.0
-attrs==25.4.0
 babel==2.17.0
-beautifulsoup4==4.14.2
-blinker==1.9.0
 cachetools==6.2.2
 certifi==2025.11.12
 charset-normalizer==3.4.4
@@ -13,10 +9,6 @@ click==8.3.1
 courlan==1.3.2
 dateparser==1.2.2
 fastapi==0.122.0
-filelock==3.20.0
-fsspec==2025.10.0
-gitdb==4.0.12
-GitPython==3.1.45
 google-ai-generativelanguage==0.6.15
 google-api-core==2.28.1
 google-api-python-client==2.187.0
@@ -27,74 +19,37 @@ googleapis-common-protos==1.72.0
 grpcio==1.76.0
 grpcio-status==1.71.2
 h11==0.16.0
-hf-xet==1.2.0
 htmldate==1.9.4
 httplib2==0.31.0
-huggingface-hub==0.36.0
 idna==3.11
-Jinja2==3.1.6
-joblib==1.5.2
-jsonschema==4.25.1
-jsonschema-specifications==2025.9.1
 jusText==3.0.2
 lxml==6.0.2
 lxml_html_clean==0.4.3
-MarkupSafe==3.0.3
-mpmath==1.3.0
-narwhals==2.12.0
-networkx==3.6
-numpy==2.3.5
 orjson==3.11.4
 packaging==24.2
-pandas==2.3.3
-pillow==12.0.0
 pinecone==8.0.0
-pinecone-client==6.0.0
 pinecone-plugin-assistant==3.0.1
 pinecone-plugin-interface==0.0.7
 proto-plus==1.26.1
 protobuf==5.29.5
-pyarrow==21.0.0
 pyasn1==0.6.1
 pyasn1_modules==0.4.2
 pydantic==2.12.4
 pydantic_core==2.41.5
-pydeck==0.9.1
 pyparsing==3.2.5
 python-dateutil==2.9.0.post0
-python-dotenv==1.2.1
 pytz==2025.2
-PyYAML==6.0.3
-referencing==0.37.0
 regex==2025.11.3
 requests==2.32.5
-rpds-py==0.29.0
 rsa==4.9.1
-safetensors==0.7.0
-scikit-learn==1.7.2
-scipy==1.16.3
-sentence-transformers==5.1.2
-setuptools==80.9.0
 six==1.17.0
-smmap==5.0.2
 sniffio==1.3.1
-soupsieve==2.8
 starlette==0.50.0
-streamlit==1.51.0
-sympy==1.14.0
-tenacity==9.1.2
-threadpoolctl==3.6.0
 tld==0.13.1
-tokenizers==0.22.1
-toml==0.10.2
-torch==2.9.1
-tornado==6.5.2
 tqdm==4.67.1
 trafilatura==2.0.0
-transformers==4.57.2
 typing-inspection==0.4.2
 typing_extensions==4.15.0
-tzdata==2025.2
 tzlocal==5.3.1
 uritemplate==4.2.0
 urllib3==2.5.0