YouTube Channel RAG Tool

A RAG (Retrieval Augmented Generation) tool that scrapes YouTube channel videos, extracts transcripts, and enables AI-powered chat interactions using Google's Gemini API.

Features

• Extract video lists from YouTube channels using Apify
• Automatically fetch transcripts using free YouTube Transcript API
• AI-powered content search with Gemini API
• Interactive terminal chat interface with markdown support
• Local transcript storage

Quick Start

Prerequisites

• Python 3.8+
• Gemini API key
• Apify API token (only for channel scraping)

Installation

# Clone repository
git clone <repo-url>
cd Youtube-comment-RAG

# Install dependencies
pip install -r requirements.txt

# Configure API keys
cp .env.example .env
# Edit .env and add your API keys

Usage

Scrape videos and chat:

python main.py

Chat with existing transcripts:

python chat.py

Test single video (no Apify needed):

python -m tests.test_transcript

Example Questions

• "What are the main topics covered in these videos?"
• "What did the creator say about [topic]?"
• "Which videos mention [keyword]?"
• "Compare approaches discussed in different videos"

Project Structure

├── main.py              # Main orchestration script
├── chat.py              # Standalone chat interface
├── youtube_scraper.py  # Transcript extraction
├── gemini_rag.py       # Gemini API integration
├── tests/              # Test files
├── utils/              # Utility scripts
└── docs/               # Documentation

License

MIT License - see LICENSE file for details.

For complete license and legal information including third-party licenses, see LICENSE_INFO.md.

Contributing

Contributions welcome! See CONTRIBUTING.md for guidelines.

Support

• Documentation
• Report Issues
• Apify Docs
• Gemini API Docs