kv-tube/README.md
KV-Tube Deployer f429116ed0
Some checks failed
Docker Build & Push / build (push) Has been cancelled
v3.1: WebLLM summarization, improved translations, copy button, removed mini player
- Added WebLLM service for client-side AI summarization and translation
- Improved summary quality (5 sentences, 600 char limit)
- Added Vietnamese character detection for proper language labels
- Added Copy button for summary content
- Key Points now extract conceptual ideas, not transcript excerpts
- Removed mini player (scroll-to-minimize) feature
- Fixed main.js null container error
- Silent WebLLM loading (no overlay/toasts)
- Added transcript service with yt-dlp
2026-01-19 19:03:09 +07:00

3.1 KiB
Executable file

KV-Tube v3.0

A lightweight, privacy-focused YouTube frontend web application with AI-powered features.

KV-Tube removes distractions, tracking, and ads from the YouTube watching experience. It provides a clean interface to search, watch, and discover related content without needing a Google account.

🚀 Key Features (v3)

  • Privacy First: No tracking, no ads.
  • Clean Interface: Distraction-free watching experience.
  • Efficient Streaming: Direct video stream extraction using yt-dlp.
  • AI Summary (Experimental): Generate concise summaries of videos (Currently disabled due to upstream rate limits).
  • Multi-Language: Support for English and Vietnamese (UI & Content).
  • Auto-Update: Includes update_deps.py to easily keep core fetching tools up-to-date.

🛠️ Architecture Data Flow

Architecture Data Flow

🔧 Installation & Usage

Prerequisites

  • Python 3.10+
  • Git
  • Valid cookies.txt (Optional, for bypassing age-restrictions or rate limits)

Local Setup

  1. Clone the repository:
    git clone https://git.khoavo.myds.me/vndangkhoa/kv-tube.git
    cd kv-tube
    
  2. Install dependencies:
    pip install -r requirements.txt
    
  3. Run the application:
    python wsgi.py
    
  4. Access at http://localhost:5002

Docker Deployment (Linux/AMD64)

Built for stability and ease of use.

docker pull vndangkhoa/kv-tube:latest
docker run -d -p 5002:5002 -v $(pwd)/cookies.txt:/app/cookies.txt vndangkhoa/kv-tube:latest

📦 Updates

  • v3.0: Major release.
    • Full modularization of backend routes.
    • Integrated ytfetcher for specialized fetching.
    • Added manual dependency update script (update_deps.py).
    • Enhanced error handling for upstream rate limits.
    • Docker linux/amd64 support verified.

Developed by Khoa Vo