🧠 Leetcode AI — Your Smart Coding Coach 🚀

---

🌌 Overview

Leetcode AI is an advanced AI-powered Chrome Extension that analyzes your LeetCode code submissions and provides intelligent feedback, performance insights, and suggestions to improve your problem-solving skills.

It integrates a FastAPI backend, a browser extension frontend, and a machine learning pipeline capable of training and analyzing code data.

---

⚙️ Tech Stack

Layer	Technology
Frontend (Extension)	HTML, CSS, JavaScript (Manifest v3)
Backend API	FastAPI, Python
Machine Learning	HuggingFace Transformers, JSONL datasets, Phi-2 model
Communication	REST (via fetch requests from popup.js)

---

🧩 Features

• 🧠 AI-powered code feedback
• 🔗 Direct integration with LeetCode problem pages
• ⚡ Instant insights via popup interface
• 🧰 Modular structure (backend, extension, ML separated)
• 🧮 ML pipeline for dataset generation & fine-tuning
• 🔒 Local-first design — runs via your backend endpoint

---

🗂 Folder Structure

Leetcode_AI/
├── backend/                     # FastAPI server
│   ├── main.py
│   └── requirements.txt
│
├── extension/                   # Chrome extension (Manifest v3)
│   ├── manifest.json
│   ├── popup.html
│   ├── popup.js
│   ├── content.js
│   ├── styles.css
│   └── icons/
│       ├── icon16.png
│       ├── icon48.png
│       └── icon128.png
│
├── machine_learning/            # ML training setup
│   ├── generate_dataset.py
│   ├── input_problems.jsonl
│   ├── training_dataset.jsonl
│   └── leetcode-ai-coach-phi2/
│       ├── adapter_model.safetensors
│       └── tokenizer_config.json
│
└── test_ollama.py               # Testing and model verification script

---

🚀 Getting Started

1️⃣ Clone the Repository

git clone https://github.com/Orb-20/Leetcode_AI.git
cd Leetcode_AI/backend

2️⃣ Install Backend Dependencies

pip install -r requirements.txt
uvicorn main:app --reload

Your FastAPI server will start at:

http://localhost:8000/analyze

---

3️⃣ Load the Chrome Extension

1. Open Chrome → chrome://extensions/
2. Turn on Developer Mode
3. Click Load Unpacked
4. Select the extension/ folder

Now open any LeetCode problem and click the Leetcode AI popup to analyze your code.

---

💻 Example Code Snippet

🧠 Backend — main.py

from fastapi import FastAPI, Request
from fastapi.middleware.cors import CORSMiddleware

app = FastAPI()

app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_methods=["*"],
    allow_headers=["*"],
)

@app.post("/analyze")
async def analyze_code(request: Request):
    data = await request.json()
    code = data.get("code", "")
    return {"analysis": f"AI Feedback: Great structure! Try optimizing loops."}

---

🌐 Chrome Manifest — manifest.json

{
  "manifest_version": 3,
  "name": "Leetcode AI Coach",
  "version": "1.0.0",
  "description": "Get AI-powered insights on your LeetCode solutions.",
  "permissions": ["activeTab", "scripting"],
  "host_permissions": ["*://leetcode.com/problems/*"],
  "action": { "default_popup": "popup.html" },
  "icons": {
    "16": "icons/icon16.png",
    "48": "icons/icon48.png",
    "128": "icons/icon128.png"
  }
}

---

🧠 Machine Learning

The ML module (machine_learning/) is designed to:

• Generate a training dataset from LeetCode problems
• Fine-tune a lightweight model like Phi-2
• Store model weights and tokenizer configs locally

Example dataset format (training_dataset.jsonl):

{"input": "Two Sum problem", "output": "Use hashmap for O(n) solution."}

---

🧭 Roadmap

• FastAPI backend setup
• Chrome extension integration
• Dataset generation script
• Full model fine-tuning integration
• Cloud deployment
• Advanced UI & performance dashboard

---

🧾 License

This project is licensed under the MIT License — free for personal and commercial use.

---

🖤 Built to make coding smarter, faster, and more human.

```