🎓 EduRAG — The AI Teaching Assistant

An AI Teaching Assistant built using Retrieval-Augmented Generation (RAG) to turn long video lectures and recordings into interactive, searchable knowledge bases.

---

The Problem: "Information Overload"

Imagine sitting through hours of lecture or training videos just to find one specific answer. The traditional method of scrubbing through timelines is inefficient, frustrating, and a major barrier to effective learning. Key knowledge remains locked away inside lengthy recordings.

The Solution: Interactive Q&A

EduRAG solves this problem by ingesting video content and transforming it into a smart knowledge base. Users can ask questions in natural language and receive instant, accurate answers with context, eliminating the need for manual searching.

---

✨ Key Features & Outcomes

• 💬 Natural Language Queries: Ask questions in plain English, just like you would talk to a human teaching assistant.
• 🚀 Instant & Accurate Answers: Leverage the power of RAG and Large Language Models (LLMs) to get precise information without delay.
• 🎓 For Students: Instantly find answers and clarify concepts from hours of lecture recordings. Ace your exams without re-watching entire courses.
• 🎥 For Creators & Trainers: Make your educational content highly accessible and searchable, increasing its value and engagement.
• 🔒 Private & Local: Build a secure, private knowledge base from your personal recordings, running entirely on your local machine with Ollama.

---

⚙️ Tech Stack

This project is built with a powerful, open-source stack designed for efficient AI-powered data processing:

• Video/Audio Processing: FFmpeg, Whisper (OpenAI)
• Data Handling & Numerics: Pandas, NumPy
• Machine Learning & Embeddings: Scikit-learn, Joblib, BGE-M3
• Local LLM Inference: Ollama
• Language Models: DeepSeek R1, Llama 3.2

---

🚀 Getting Started

To get a local copy up and running, follow these steps.

Prerequisites

Make sure you have the following installed on your system:

• Python 3.9+
• FFmpeg
• Git
• Ollama

Installation & Setup

1. Clone the Repository:

   git clone [https://github.com/your-username/EduRAG.git](https://github.com/your-username/EduRAG.git)
   cd EduRAG

2. Create a Virtual Environment:

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

3. Install Dependencies:

   pip install -r requirements.txt

4. Set up Ollama & Pull Models:

   • Ensure the Ollama service is running.
   • Pull the required models from the command line:

   ollama pull llama3.2
   ollama pull deepseek-coder-v2
   ollama pull bge-m3 # For embeddings

---

🖥️ How to Use

1. Add Your Video: Place your video file (e.g., lecture.mp4) into the /videos directory.

2. Process the Video: Run the main processing script to transcribe, chunk, and embed the content.

   python process_video.py --file "lecture.mp4"

3. Ask Questions: Launch the interactive Q&A interface.

   python ask.py

   You can now start asking questions about the video content!

---

🤝 Contributing & Collaboration

This project is open for collaboration! If you're curious, have feedback, or want to extend this project, please feel free to connect.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/NewFeature)
3. Commit your Changes (git commit -m 'Add some NewFeature')
4. Push to the Branch (git push origin feature/NewFeature)
5. Open a Pull Request

---

📄 License

Distributed under the MIT License. See LICENSE for more information.