🎬 VisionFlow AI

Intelligent Video Understanding Platform — Upload any video and let AI transcribe, analyze, and extract deep intelligence from it.

---

✨ Features

Feature	Description
🎙 AI Transcription	Whisper-powered speech recognition with timestamps
📍 Timeline Intelligence	Auto-divides video into smart chapters with detected tools
🧠 AI Insights	Extracts concepts, tools, actions and questions automatically
🚨 Error Detector	Finds mistakes, bugs and problems — with solutions
📄 Auto Documentation	Generates complete docs + quiz from video content
🔍 AI Video Search	Ask anything about your videos in natural language
📊 Analytics Dashboard	Full stats on all your processed videos

---

🖥 Screenshots

Dashboard

Clean dark UI showing all your videos and AI stats at a glance.

Video Intelligence

5-tab interface: Transcript · Timeline · Insights · Errors · Documentation

AI Search

Chat with your videos — get answers with timestamps and sources.

---

🛠 Tech Stack

Frontend

• Next.js 15 (App Router)
• TypeScript
• Tailwind CSS
• Axios

Backend

• FastAPI (Python)
• SQLAlchemy + SQLite
• JWT Authentication
• FFmpeg (audio extraction)

AI / ML

• Groq Whisper Large V3 (transcription)
• Groq LLaMA 3.3 70B (analysis, insights, docs)

---

🚀 Getting Started

Prerequisites

• Python 3.10+
• Node.js 18+
• FFmpeg installed
• Groq API key (free at console.groq.com)

1. Clone the repo

git clone https://github.com/YOUR_USERNAME/VisionFlow-AI.git
cd VisionFlow-AI

2. Backend setup

cd backend
pip install -r requirements.txt

Create .env file:

GROQ_API_KEY=your_groq_api_key_here
SECRET_KEY=your-secret-key
DATABASE_URL=sqlite:///./visionflow.db
UPLOAD_DIR=uploads
ACCESS_TOKEN_EXPIRE_MINUTES=120

Start backend:

uvicorn app.main:app --host 127.0.0.1 --port 9000

3. Frontend setup

cd frontend
npm install
npm run dev -- --no-turbo

4. Open browser

http://localhost:3000

---

📁 Project Structure

VisionFlow-AI/
├── backend/
│   ├── app/
│   │   └── main.py          # All API routes + AI pipeline
│   ├── uploads/             # Video files (gitignored)
│   ├── requirements.txt
│   └── .env                 # API keys (gitignored)
│
├── frontend/
│   ├── app/
│   │   ├── dashboard/       # Main dashboard
│   │   ├── upload/          # Video upload
│   │   ├── videos/          # Video list + detail
│   │   ├── search/          # AI search chat
│   │   └── analytics/       # Stats
│   ├── lib/
│   │   └── api.ts           # Axios API client
│   └── types/
│       └── index.ts         # TypeScript types
│
├── .gitignore
└── README.md

---

🔄 How It Works

Upload Video
     ↓
Extract Audio (FFmpeg)
     ↓
Speech Recognition (Groq Whisper)
     ↓
┌────────────────────────────┐
│  AI Analysis Pipeline      │
│  ├── Timeline chapters     │
│  ├── Insight extraction    │
│  ├── Error detection       │
│  └── Documentation gen     │
└────────────────────────────┘
     ↓
Video Intelligence Report
     ↓
AI Search & Analytics

---

🌐 API Endpoints

Method	Endpoint	Description
POST	/auth/register	Create account
POST	/auth/login	Login
POST	/videos/upload	Upload video
GET	/videos	List all videos
GET	/videos/{id}	Get video + AI data
POST	/videos/{id}/reprocess	Re-run AI pipeline
POST	/search/query	AI search across videos
GET	/analytics	Usage stats

---

📝 License

MIT License — feel free to use, modify and distribute.

---

👨‍💻 Author

Built with ❤️ using FastAPI + Next.js + Groq AI

---

VisionFlow AI — Give your videos a brain.