From 1bd82158fc0b402112861ef25f2d189f3f3c8286 Mon Sep 17 00:00:00 2001
From: enias <enias@yatkv2.local>
Date: Sun, 24 Aug 2025 22:15:38 -0400
Subject: [PATCH] Initial commit: YouTube Summarizer project setup

- Created project structure following new standardized layout
- Added FastAPI-based main application
- Configured requirements with YouTube and AI integrations
- Added comprehensive README documentation
- Set up environment configuration template
---
 .env.example     |  40 +++++++++++
 .gitignore       |  53 +++++++++++++++
 README.md        | 173 +++++++++++++++++++++++++++++++++++++++++++++++
 requirements.txt |  44 ++++++++++++
 src/main.py      | 106 +++++++++++++++++++++++++++++
 5 files changed, 416 insertions(+)
 create mode 100644 .env.example
 create mode 100644 .gitignore
 create mode 100644 README.md
 create mode 100644 requirements.txt
 create mode 100644 src/main.py

diff --git a/.env.example b/.env.example
new file mode 100644
index 0000000..ea8a9b8
--- /dev/null
+++ b/.env.example
@@ -0,0 +1,40 @@
+# YouTube Summarizer Configuration
+
+# Server Configuration
+APP_HOST=0.0.0.0
+APP_PORT=8082
+DEBUG=False
+
+# YouTube API (optional but recommended for metadata)
+YOUTUBE_API_KEY=your_youtube_api_key_here
+
+# AI Service Configuration (choose one or multiple)
+# OpenAI
+OPENAI_API_KEY=your_openai_api_key_here
+OPENAI_MODEL=gpt-4o-mini
+
+# Anthropic Claude
+ANTHROPIC_API_KEY=your_anthropic_api_key_here
+ANTHROPIC_MODEL=claude-3-haiku-20240307
+
+# DeepSeek (cost-effective option)
+DEEPSEEK_API_KEY=your_deepseek_api_key_here
+DEEPSEEK_MODEL=deepseek-chat
+
+# Database
+DATABASE_URL=sqlite:///./data/youtube_summarizer.db
+
+# Session Configuration
+SECRET_KEY=your-secret-key-here-change-in-production
+
+# Rate Limiting
+RATE_LIMIT_PER_MINUTE=30
+MAX_VIDEO_LENGTH_MINUTES=180
+
+# Cache Configuration
+ENABLE_CACHE=True
+CACHE_TTL_HOURS=24
+
+# Logging
+LOG_LEVEL=INFO
+LOG_FILE=logs/app.log
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..235b68f
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,53 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+venv/
+ENV/
+.venv
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+.DS_Store
+
+# Environment
+.env
+.env.local
+.env.*.local
+
+# Testing
+.coverage
+htmlcov/
+.pytest_cache/
+.tox/
+
+# Build
+build/
+dist/
+*.egg-info/
+.eggs/
+
+# Logs
+*.log
+logs/
+
+# Database
+*.db
+*.sqlite
+*.sqlite3
+
+# Media/Data
+data/
+downloads/
+cache/
+
+# Task Master
+.taskmaster/reports/
+.taskmaster/backups/
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..77a8911
--- /dev/null
+++ b/README.md
@@ -0,0 +1,173 @@
+# YouTube Summarizer Web Application
+
+An AI-powered web application that automatically extracts, transcribes, and summarizes YouTube videos, providing intelligent insights and key takeaways.
+
+## 🎯 Features
+
+- **Video Transcript Extraction**: Automatically fetch transcripts from YouTube videos
+- **AI-Powered Summarization**: Generate concise summaries using multiple AI models
+- **Multi-Model Support**: Choose between OpenAI GPT, Anthropic Claude, or DeepSeek
+- **Key Points Extraction**: Identify and highlight main topics and insights
+- **Chapter Generation**: Automatically create timestamped chapters
+- **Export Options**: Save summaries as Markdown, PDF, or plain text
+- **Caching System**: Reduce API calls with intelligent caching
+- **Rate Limiting**: Built-in protection against API overuse
+
+## 🏗️ Architecture
+
+```
+[Web Interface] → [FastAPI Backend] → [YouTube API/Transcript API]
+                         ↓
+[AI Service] ← [Summary Generation] ← [Transcript Processing]
+                         ↓
+[Database Cache] → [Summary Storage] → [Export Service]
+```
+
+## 🚀 Quick Start
+
+### Prerequisites
+
+- Python 3.11+
+- YouTube API Key (optional but recommended)
+- At least one AI service API key (OpenAI, Anthropic, or DeepSeek)
+
+### Installation
+
+1. **Clone the repository**
+```bash
+git clone https://eniasgit.zeabur.app/demo/youtube-summarizer.git
+cd youtube-summarizer
+```
+
+2. **Set up virtual environment**
+```bash
+python3 -m venv venv
+source venv/bin/activate  # On Windows: venv\Scripts\activate
+```
+
+3. **Install dependencies**
+```bash
+pip install -r requirements.txt
+```
+
+4. **Configure environment**
+```bash
+cp .env.example .env
+# Edit .env with your API keys and configuration
+```
+
+5. **Initialize database**
+```bash
+alembic init alembic
+alembic revision --autogenerate -m "Initial migration"
+alembic upgrade head
+```
+
+6. **Run the application**
+```bash
+python src/main.py
+```
+
+The application will be available at `http://localhost:8082`
+
+## 📁 Project Structure
+
+```
+youtube-summarizer/
+├── src/
+│   ├── api/              # API endpoints
+│   │   ├── routes.py     # Main API routes
+│   │   └── websocket.py  # Real-time updates
+│   ├── services/         # Business logic
+│   │   ├── youtube.py    # YouTube integration
+│   │   ├── summarizer.py # AI summarization
+│   │   └── cache.py      # Caching service
+│   ├── utils/            # Utility functions
+│   │   ├── validators.py # Input validation
+│   │   └── formatters.py # Output formatting
+│   └── main.py           # Application entry point
+├── tests/                # Test suite
+├── docs/                 # Documentation
+├── alembic/             # Database migrations
+├── static/              # Frontend assets
+├── templates/           # HTML templates
+├── requirements.txt     # Python dependencies
+├── .env.example        # Environment template
+└── README.md           # This file
+```
+
+## 🔧 Configuration
+
+### Essential Environment Variables
+
+| Variable | Description | Required |
+|----------|-------------|----------|
+| `YOUTUBE_API_KEY` | YouTube Data API v3 key | Optional* |
+| `OPENAI_API_KEY` | OpenAI API key | One of these |
+| `ANTHROPIC_API_KEY` | Anthropic Claude API key | is required |
+| `DEEPSEEK_API_KEY` | DeepSeek API key | for AI |
+| `DATABASE_URL` | Database connection string | Yes |
+| `SECRET_KEY` | Session secret key | Yes |
+
+*YouTube API key improves metadata fetching but transcript extraction works without it.
+
+## 🧪 Testing
+
+Run the test suite:
+```bash
+pytest tests/ -v
+pytest tests/ --cov=src --cov-report=html  # With coverage
+```
+
+## 📝 API Documentation
+
+Once running, visit:
+- Interactive API docs: `http://localhost:8082/docs`
+- Alternative docs: `http://localhost:8082/redoc`
+
+### Key Endpoints
+
+- `POST /api/summarize` - Submit a YouTube URL for summarization
+- `GET /api/summary/{id}` - Retrieve a summary
+- `GET /api/summaries` - List all summaries
+- `POST /api/export/{id}` - Export summary in different formats
+
+## 🚢 Deployment
+
+### Docker
+
+```bash
+docker build -t youtube-summarizer .
+docker run -p 8082:8082 --env-file .env youtube-summarizer
+```
+
+### Production Considerations
+
+1. Use PostgreSQL instead of SQLite for production
+2. Configure proper CORS settings
+3. Set up SSL/TLS certificates
+4. Implement user authentication
+5. Configure rate limiting per user
+6. Set up monitoring and logging
+
+## 🤝 Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Commit your changes
+4. Push to the branch
+5. Create a Pull Request
+
+## 📄 License
+
+This project is part of the Personal AI Assistant ecosystem.
+
+## 🔗 Related Projects
+
+- [Personal AI Assistant](https://eniasgit.zeabur.app/demo/my-ai-projects)
+- [YouTube Automation Service](https://eniasgit.zeabur.app/demo/youtube-automation)
+- [PDF Translator](https://eniasgit.zeabur.app/demo/pdf-translator)
+
+## 📞 Support
+
+For issues and questions, please create an issue in the repository.
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..6c1c199
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,44 @@
+# YouTube Summarizer Web Application Requirements
+
+# Web framework
+fastapi==0.104.1
+uvicorn[standard]==0.24.0
+python-multipart==0.0.6
+
+# YouTube integration
+youtube-transcript-api==0.6.1
+pytube==15.0.0
+yt-dlp==2024.8.6
+
+# AI and NLP
+openai==1.35.0
+anthropic==0.28.0
+langchain==0.2.5
+tiktoken==0.7.0
+
+# Database
+sqlalchemy==2.0.23
+alembic==1.13.0
+
+# HTTP client
+httpx==0.25.2
+requests==2.31.0
+
+# Environment and configuration
+python-dotenv==1.0.0
+pydantic==2.5.2
+pydantic-settings==2.1.0
+
+# Utilities
+python-dateutil==2.8.2
+pytz==2024.1
+
+# Testing
+pytest==7.4.3
+pytest-asyncio==0.21.1
+pytest-cov==4.1.0
+
+# Development
+black==23.12.0
+ruff==0.1.8
+mypy==1.7.1
\ No newline at end of file
diff --git a/src/main.py b/src/main.py
new file mode 100644
index 0000000..423b00a
--- /dev/null
+++ b/src/main.py
@@ -0,0 +1,106 @@
+#!/usr/bin/env python3
+"""
+YouTube Summarizer Web Application
+Main entry point for the FastAPI application
+"""
+
+import os
+import sys
+from pathlib import Path
+from contextlib import asynccontextmanager
+
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.staticfiles import StaticFiles
+from dotenv import load_dotenv
+
+# Add project root to path
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+# Load environment variables
+load_dotenv()
+
+# Import routers (to be created)
+# from api.routes import api_router
+# from api.websocket import websocket_router
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    """
+    Manage application lifecycle
+    """
+    # Startup
+    print("🚀 Starting YouTube Summarizer Application...")
+    
+    # Initialize services here
+    # await initialize_database()
+    # await initialize_cache()
+    
+    yield
+    
+    # Shutdown
+    print("🛑 Shutting down YouTube Summarizer Application...")
+    # await cleanup_resources()
+
+# Create FastAPI application
+app = FastAPI(
+    title="YouTube Summarizer",
+    description="AI-powered YouTube video summarization service",
+    version="1.0.0",
+    lifespan=lifespan
+)
+
+# Configure CORS
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Configure appropriately for production
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Mount static files (if needed)
+# app.mount("/static", StaticFiles(directory="static"), name="static")
+
+# Include routers
+# app.include_router(api_router, prefix="/api")
+# app.include_router(websocket_router)
+
+@app.get("/")
+async def root():
+    """
+    Root endpoint
+    """
+    return {
+        "message": "YouTube Summarizer API",
+        "version": "1.0.0",
+        "docs": "/docs",
+        "health": "/health"
+    }
+
+@app.get("/health")
+async def health_check():
+    """
+    Health check endpoint
+    """
+    return {
+        "status": "healthy",
+        "service": "youtube-summarizer"
+    }
+
+if __name__ == "__main__":
+    import uvicorn
+    
+    host = os.getenv("APP_HOST", "0.0.0.0")
+    port = int(os.getenv("APP_PORT", 8082))
+    debug = os.getenv("DEBUG", "False").lower() == "true"
+    
+    print(f"🎬 YouTube Summarizer starting on http://{host}:{port}")
+    
+    uvicorn.run(
+        "main:app",
+        host=host,
+        port=port,
+        reload=debug,
+        log_level="debug" if debug else "info"
+    )
\ No newline at end of file