🤖 RAG Q&A Assistant

A smart AI-powered document assistant for contextual Q&A and challenge-based learning. Upload a document, ask questions, and test your understanding—all with justifications and references.

---

###Main_Page

###ASk_Me

###Challenge_Mode

⚡ Quick Setup

Prerequisites

• Python 3.9+
• Ollama installed and running
• Gemma3:4b model downloaded (ollama pull gemma3:4b)

Installation & Run

1. Clone the repo

   git clone <repository-url>
   cd Rag_1-main

2. Create and activate a virtual environment

   python -m venv rag_env
   source rag_env/bin/activate  # Windows: rag_env\Scripts\activate

3. Install dependencies

   pip install -r requirements.txt

4. Start Ollama

   ollama serve
   ollama pull gemma3:4b

5. Start the backend

   cd backend
   python main.py
   # Backend: http://localhost:8000

6. Start the frontend (new terminal)

   streamlit run streamlit_app.py
   # Frontend: http://localhost:8501

---

🏗️ Architecture & Reasoning Flow

System Overview

• Frontend: Streamlit (Python)
• Backend: FastAPI (Python)
• LLM: Ollama (Gemma3:4b)
• Document Parsing: PyPDF2, LangChain

Reasoning/Data Flow

1. Document Upload:
   • User uploads PDF/TXT via Streamlit UI
   • Backend extracts text, generates summary
2. Q&A Chat:
   • User asks a question
   • Backend retrieves context, sends to LLM
   • LLM generates answer, justification, and highlights source text
   • Frontend displays answer, justification, and highlights
3. Challenge Mode:
   • Backend generates comprehension questions from document
   • User answers; backend evaluates, scores, and provides feedback/reasoning

---

📖 Usage

1. Upload a PDF/TXT on the Document Upload page and process it
2. Q&A Chat: Ask questions, get answers with justifications and source text
3. Challenge Mode: Generate questions, answer, and receive feedback and scores

---

🗂️ Project Structure

Rag_1-main/
├── backend/
│   ├── main.py
│   ├── models.py
│   ├── utils.py
│   └── prompt.py
├── streamlit_app.py
├── requirements.txt
├── activate_env.sh
├── rag_env/  # (virtual environment)
└── README.md

---

🛠️ Troubleshooting

• Ollama not running: ollama serve
• Model not found: ollama pull gemma3:4b
• Virtualenv issues: Delete and recreate rag_env
• Port conflicts: Change ports in main.py/streamlit_app.py
• Import errors: pip install -r requirements.txt --force-reinstall

---

📄 License

MIT License. See LICENSE file.

---

For questions or issues, please open an issue in the repository.