Skip to content

BiswasNehaa/universal-academic-advisor

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Universal Academic Advisor 🎓

An AI-powered academic advisor that works for any college. Tell it your career goal and completed courses — it tells you exactly what to study next.

Built with RAG (Retrieval-Augmented Generation) using LangChain, FAISS, and LLaMA 3.3 70B.


What it does

  • You tell it: your career goal + courses you've completed + credit limit
  • It tells you: exactly which courses to take next semester and why
  • It shows you: a full roadmap from where you are to your career goal
  • It never recommends a course you're not eligible for

Works for any college

The sample data inside Data/sample_courses.json is from VTU (India). But you can use this for your own college by adding your course data. See how to add your college's data.


Tech Stack

Tool Purpose
LangChain RAG pipeline
FAISS Vector search
HuggingFace all-MiniLM-L6-v2 Embeddings
Groq + LLaMA 3.3 70B AI reasoning
Streamlit Web UI

How it works

User Input
│
├── Career Goal (e.g. "I want to be an ML Engineer")
├── Completed Courses (e.g. CS101, CS201)
└── Credit Limit (e.g. 15 credits)
│
▼
RAG Pipeline
│
├── courses.json → FAISS Vector Database
│   └── Embeds all course topics and outcomes
│
├── career.json → Career Requirements Lookup
│   └── Finds required skills for your goal
│
▼
LLaMA 3.3 70B (via Groq)
│
└── Matches your completed courses + career goal
    └── Recommends exactly what to study next
│
▼
Output
│
├── Recommended courses for next semester
├── Why each course is recommended
└── Full roadmap to your career goal

How to run it

1. Clone the repo

git clone https://github.com/BiswasNehaa/universal-academic-advisor.git
cd universal-academic-advisor

2. Install dependencies

pip install -r requirements.txt

3. Add your API key

Create a .env file and add: GROQ_API_KEY=your_key_here

Get a free key at console.groq.com

4. Build the vector database

python app/ingest.py

5. Run the app

streamlit run app/app.py

Want to contribute?

The easiest way to contribute is to add your college's course data.

See the contribution guide to get started. All experience levels welcome.


Made by

Nehaa Biswas — 3rd year CS student

About

An AI-powered academic advisor that works for any college. Just plug in your course data.

Resources

Contributing

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages