📚 AI-Powered Study Assistant using RAG

Project Overview

This project is an AI-powered Study Assistant built using Retrieval-Augmented Generation (RAG). It allows users to ask questions from a PDF document and generates accurate answers based on the document's content using Google's Gemini model.

---

Features

• Upload and process PDF documents
• Split document into chunks
• Generate embeddings using Sentence Transformers
• Store embeddings using FAISS
• Retrieve relevant context
• Generate answers using Gemini Flash
• Interactive Streamlit interface

---

Technologies Used

• Python
• Streamlit
• Google Gemini API
• Sentence Transformers
• FAISS
• PyPDF
• LangChain Text Splitter

---

Project Structure

Week_7_Assignment_RAG/
│
├── app.py
├── generator.py
├── retrieval.py
├── embed.py
├── chunk.py
├── ingest.py
├── requirements.txt
├── README.md
├── .env
├── .gitignore
├── data/
│   └── datasciencenotes.pdf

---

Installation

Clone Repository

git clone <repository_link>
cd Week_7_Assignment_RAG

Install Dependencies

pip install -r requirements.txt

---

Create .env File

Create a file named .env in the project folder and add:

GEMINI_API_KEY=YOUR_GEMINI_API_KEY

Replace YOUR_GEMINI_API_KEY with your own Gemini API Key.

---

Run Project

streamlit run app.py

---

How it Works

1. Read PDF
2. Split into chunks
3. Create embeddings
4. Store embeddings in FAISS
5. Retrieve relevant chunks
6. Send context to Gemini
7. Display generated answer

---

Future Improvements

• Multiple PDF support
• Chat history
• Source citation
• Better retrieval ranking
• Voice input

---

Author

Shruti Deshmukh

MCA Student