LectureMind AI

LectureMind AI converts your lecture videos into interactive, hierarchical mind maps using Gemini 2.5 Flash and OpenAI Whisper.

Prerequisites

• Python 3.9+
• Node.js 18+
• FFmpeg installed and in your PATH.
• Google Gemini API Key.

Setup & Running

Backend

1. Navigate to the backend directory:

   cd backend

2. Create a virtual environment and install dependencies:

   python -m venv venv
   source venv/bin/activate  # or venv\Scripts\activate on Windows
   pip install -r requirements.txt

3. Create a .env file from .env.example and add your GOOGLE_API_KEY:

   cp .env.example .env

4. Start the FastAPI server:

   python main.py

   The backend will run on http://localhost:8000.

Frontend

1. Navigate to the frontend directory:

   cd frontend

2. Install dependencies:

   npm install

3. Start the Next.js development server:

   npm run dev

   The frontend will run on http://localhost:3000.

Architecture

The project follows a modular AI architecture:

• backend/services/speech: Audio extraction and transcription (Whisper).
• backend/services/summarization: AI analysis and mind map generation (Gemini, placeholder for BART).
• backend/services/embeddings: Future semantic clustering (placeholder for SBERT).
• backend/services/pipeline: Orchestration of the AI workflow.

Tech Stack

• Frontend: Next.js 15, React 19, TypeScript, Tailwind CSS, Framer Motion, React Flow.
• Backend: FastAPI, FFmpeg, Whisper, Gemini 2.5 Flash.