📚 StudyMate AI — RAG-based PDF Study Assistant

StudyMate AI is an interactive Retrieval-Augmented Generation (RAG) application built with Streamlit.
It allows students and researchers to upload PDFs, ask questions, get summaries, generate quizzes, and explore content interactively using Groq’s Gemma2-9B-IT LLM and ChromaDB.

---

🚀 Features

• 📂 Upload one or multiple PDFs( Magic Fast Uploading with Batch Processing and Parallel File Processing)
• 🔍 Semantic search using embeddings
• 💡 Summarization & quiz generation from PDFs
• 🧠 RAG-based conversational Q&A
• ⚡ Fast response using Groq API
• 🎯 Supports sentence-transformers for embeddings
• 🖥 Clean Streamlit frontend

---

📌 Workflow

1️⃣ Uploading the File

The user uploads one or more documents (PDF/TXT).

---

2️⃣ Successful Upload & Home Screen

After upload, a confirmation is displayed, and the user sees the home interface.

---

3️⃣ Q&A from the Document

Ask any question from the uploaded document, and get AI-generated answers.

---

4️⃣ Summarization with Key Notes

Get a concise summary along with important bullet points.

---

5️⃣ Quiz Generation

Generate quizzes from the uploaded content for self-assessment.

---

🖼 System Flowchart

Below is the complete workflow architecture:

---

🛠 Tech Stack

Component	Technology
Frontend	Streamlit
Language Model	Groq - Gemma2-9B-IT
Vector Database	ChromaDB
Embeddings	Sentence-Transformers (HuggingFace)
PDF Parsing	PyMuPDF
Environment Config	python-dotenv

---

🧩 RAG Concept:

RAG (Retrieval-Augmented Generation) is a technique where the LLM retrieves relevant information from a vector store before generating a response.

Why use RAG here?

• Keeps answers accurate to the uploaded PDFs
• Reduces hallucinations from the LLM
• Allows working with large documents without exceeding token limits

---

📊 Project Flow

---

## 📥 Installation

1. **Clone the repository**

```bash
git clone https://github.com/yourusername/studymate-ai.git
cd studymate-ai

2. Create virtual environment

python -m venv .venv
source .venv/bin/activate  # (Linux/Mac)
.venv\Scripts\activate     # (Windows)

3. Install dependencies

pip install -r requirements.txt

4. Set environment variables Create a .env file:

GROQ_API_KEY=your_groq_api_key
EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2

---

▶️ Usage

Run the Streamlit app:

streamlit run app.py

---