CourseLink

Intelligent Course Advisory System powered by RAG + LangGraph

中文文档

---

Introduction

CourseLink is an AI-powered personalized course recommendation system designed for university students. By leveraging advanced RAG (Retrieval-Augmented Generation) technology, we transform the tedious manual handbook lookup process into an intelligent, efficient, and data-driven course selection experience.

Our goal is to help every student easily find the courses that best fit their needs — whether aiming for top grades, seeking easier credits, mastering practical skills, or planning an accelerated graduation path.

In short: Smart course selection without the hassle!

---

Key Features

• Real-time Data: Periodically crawls official university websites to ensure course information accuracy and timeliness
• Personalized Recommendations: Deeply understands your course selection intent — high GPA targets, workload preferences, practical skills, or summer term planning
• Intelligent Chatbot: Built with LangGraph agent architecture, providing fast and accurate answers to your course-related questions via SSE streaming
• Secure Account System: JWT authentication + optional third-party OAuth + AES-GCM end-to-end encryption
• Browser Extension Integration: Chrome extension backend APIs for automated course planning and enrollment
• RAG-Enhanced Search: Vector retrieval + optional reranking for precise course matching

---

Tech Stack

Layer	Technologies
Backend	Python 3.11+, Django 5.x, DRF, Uvicorn (ASGI)
Agent	LangGraph, LangChain
Vector Search	ChromaDB / FAISS
LLM	Dashscope (Qwen series, default)
Database	SQLite (dev) / MySQL (production)
Frontend	React, Vite, TypeScript, Tailwind CSS
Crawler	Python, Requests, BeautifulSoup
Extension	Chrome Extension APIs (Manifest V3)

---

System Architecture

The project adopts a modular design ensuring high cohesion and low coupling.

Core Modules:

• backend/chatbot/langgraph_agent/ - LangGraph Agent core logic (routing, RAG invocation, tool execution, answer generation)
• backend/accounts/ - User authentication, license management, and encryption services
• backend/crawler/ - Scripts for crawling course URLs, details, and graduation requirements
• backend/RAG_database/ - Vector database construction and retrieval services
• backend/extension/ - Chrome extension backend interfaces

Data Flow:

User Query → Django API → LangGraph Agent → Tool Router
                                              ↓
                              ┌───────────────┼───────────────┐
                              ↓               ↓               ↓
                         RAG Search    Knowledge Graph   Direct Answer
                              ↓               ↓               ↓
                              └───────────────┴───────────────┘
                                              ↓
                                    Response Generation → SSE Stream → User

---

Quick Start

Prerequisites

• Python 3.11+
• Node.js 18+ (for frontend)
• Chrome browser (for extension)

Option A: Local Development (SQLite, Recommended)

1. Clone the repository

git clone https://github.com/oceanusXXD/CourseLink.git
cd CourseLink

2. Configure environment variables

cp backend/.env.local.example backend/.env
# Edit backend/.env, at minimum set: DJANGO_SECRET_KEY

3. One-click backend startup

# Windows
.\scripts\start_backend.bat

# macOS / Linux
chmod +x scripts/*.sh
./scripts/start_backend.sh

4. Access the API

• API: http://localhost:8000/api/
• Admin: http://localhost:8000/admin/

Option B: Docker Compose (MySQL + Nginx)

cp backend/.env.example backend/.env
# Configure database credentials in backend/.env
docker compose up -d --build

Access: http://localhost/api/

---

Frontend Code

The frontend code is not open-sourced in this repository.

If you need access to the frontend code for academic research, learning purposes, or collaboration, please contact me:

• Email: tao666918@gmail.com | z453676955@qq.com
• GitHub Issues: Feel free to open an issue

---

Documentation

• Environment Variables: document/ENV_CONFIG.md
• API Documentation: document/API.md
• Development Guide: document/DEVELOPMENT.md
• Quick Start: QUICKSTART.md
• Local Dev Guide: LOCAL_DEV_GUIDE.md

---

Roadmap

• Basic data crawling from official handbook
• Structured course database
• Vector database for RAG retrieval
• LangGraph-based chatbot
• RAG integration with self-judging agent
• User authentication system
• SSE streaming output
• Chrome extension (course planning & auto-enrollment)
• React frontend refactoring
• Advanced data crawling (course reviews, social media)
• Semantic clustering for similar courses
• Architecture upgrade (RPC optimization, SaaS/PaaS deployment)

---

Contributing

Contributions are welcome! Whether it's code, documentation, or suggestions.

1. Fork this repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

---

Contact

If you have any questions, suggestions, or collaboration ideas, feel free to reach out:

• Email: tao666918@gmail.com | z453676955@qq.com
• Or open an Issue on GitHub

---

License

This project is licensed under the GNU General Public License v3.0. See the LICENSE file for details.

---

Related Projects

Project	URL
Backend (this repo)	https://github.com/oceanusXXD/CourseLink
Frontend	Not open-sourced yet. Please contact via email if needed.