StudyGenius is an intelligent, RAG-powered study assistant designed to transform static PDF documents into interactive learning sessions. Unlike standard PDF chat tools, StudyGenius features an active "Exam Simulator" mode that generates quizzes to test user retention.
Chat with your document naturally. The AI uses Retrieval-Augmented Generation (RAG) to pull answers strictly from your uploaded PDF, ensuring accuracy and reducing hallucinations.
Struggling to prepare for a test? Click one button, and the "Professor AI" agent will:
- Analyze your document's key concepts.
- Generate a 3-question Multiple Choice Quiz.
- Provide the correct answers for self-assessment.
Uses high-performance vector embeddings (all-MiniLM-L6-v2) to semantic search through hundreds of pages in milliseconds.
- Frontend: Streamlit (Custom Dark Mode Theme)
- Orchestration: LangChain (LCEL Architecture)
- LLM:
HuggingFaceH4/zephyr-7b-beta(via Hugging Face Inference API) - Vector Database: FAISS (Facebook AI Similarity Search)
- Embeddings: Sentence-Transformers
If you want to run this project on your own machine:
-
Clone the Repository
git clone [https://github.com/Muhammad-Shahan/StudyGenius-AI.git](https://github.com/Muhammad-Shahan/StudyGenius-AI.git) cd StudyGenius-AI -
Install Dependencies
pip install -r requirements.txt
-
Run the App
streamlit run app.py
This app follows a BYOK (Bring Your Own Key) security model.
- Obtain a free API Token from Hugging Face.
- Enter it in the sidebar when prompted.
- Note: Your key is never stored; it is used only for the active session.
Contributions are welcome! Please feel free to submit a Pull Request.
Built by [Muhammad Shahan]