Apppublic

prafulmemane/ContentGenie

sourceHugging Facemitupdated 7mo agoView on Hugging Face

0likes

App README

✨ ContentGenie

AI-Powered Multi-Agent Content Generation Platform powered by LangGraph, OpenAI, Google Gemini, and Anthropic Claude.

Generate high-quality blog posts, LinkedIn content, images, and video scripts using an intelligent multi-agent workflow.

🚀 Live Demo

[Open ContentGenie on Hugging Face Spaces](https://huggingface.co/spaces/YOUR_USERNAME/ContentGenie)

(Replace YOUR_USERNAME with your actual Hugging Face username after deployment)

🎯 Features

—🤖 Multi-Agent Workflow
—Research Agent: Gathers information from web sources
—Content Strategist: Plans your content
—Blog Writer: Generates blog posts
—LinkedIn Writer: Creates social media content
—Image Generator: Creates visual content
—Video Script: Generates video scripts

—📊 Multiple Response Formats
—JSON: Structured data format
—XML: Markup format
—TOON: ASCII art representation

—🔄 Automatic LLM Failover
—Primary: OpenAI GPT-4o
—Fallback: Google Gemini 2.0 Flash
—Alternative: Anthropic Claude 3 Sonnet
—Local: Ollama support

—🛡️ Content Guardrails
—Profanity filtering
—Safety validation
—Intent detection
—Rule-based filtering

—📱 Professional UI
—Streamlit-powered interface
—Responsive design
—Real-time content generation
—Format-agnostic output

🔧 Setup & Configuration

🌐 Hugging Face Spaces (Live)

The app requires these secrets in your HF Space Settings:

OPENAI_API_KEY        # https://platform.openai.com/api-keys
GEMINI_API_KEY        # https://aistudio.google.com/app/apikey
HF_TOKEN              # https://huggingface.co/settings/tokens
SERPAPI_API_KEY       # https://serpapi.com/dashboard

Optional secrets for additional features:

STABILITY_KEY         # https://platform.stability.ai/account/keys
RUNWAY_API_KEY        # https://runwayml.com/settings
ELEVENLABS_API_KEY    # https://elevenlabs.io/app/settings/api-keys

💻 Local Development

bash

# 1. Clone the repository
git clone https://github.com/YOUR_USERNAME/ContentGenie.git
cd ContentGenie

# 2. Create virtual environment
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# 3. Install dependencies
pip install -r requirements.txt

# 4. Set up environment variables
cp .env.example .env
# Edit .env and add your API keys

# 5. Run the app
streamlit run app.py

The app will open at http://localhost:8501

🏗️ Architecture

┌─────────────────────────────────────────────────────────────┐
│                     User Interface (Streamlit)              │
├─────────────────────────────────────────────────────────────┤
│                                                               │
│  ┌──────────────────┐         ┌──────────────────────────┐  │
│  │   Input Panel    │         │   Output Display         │  │
│  │ • Query text     │────────▶│ • Format selector (JSON/ │  │
│  │ • Format select  │         │   XML/TOON)             │  │
│  │ • Submit button  │         │ • Content output         │  │
│  └──────────────────┘         │ • Copy/Export buttons    │  │
│                               └──────────────────────────┘  │
└──────────────────┬────────────────────────────────────────┘
                   │
        ┌──────────▼──────────┐
        │   Query Handler     │
        │   (Route & Orchestrate)
        └──────────┬──────────┘
                   │
    ┌──────────────┼──────────────┐
    │              │              │
┌───▼────────┐  ┌─▼─────────┐  ┌─▼──────────┐
│ Guardrail  │  │ Research  │  │ Content    │
│ Engine     │  │ Agent     │  │ Generator  │
│            │  │           │  │            │
│ • Profanity│  │ • WebSearch   │ • LLM     │
│   Filter   │  │ • SerpAPI     │   Chain   │
│ • Safety   │  │ • DuckDuckGo  │            │
│ • Intent   │  └───────────┘  └────────────┘
└────────────┘
     │
┌────▼──────────────────────────────────────────────────┐
│         LLM Provider Registry & Fallover              │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐           │
│  │OpenAI    │▶ │Gemini    │▶ │Claude    │           │
│  │GPT-4o    │  │2.0-Flash │  │3-Sonnet  │           │
│  └──────────┘  └──────────┘  └──────────┘           │
└─────────────────────────────────────────────────────┘
     │
┌────▼──────────────────────────────────────────────────┐
│           Format Converter                            │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐           │
│  │  JSON    │  │  XML     │  │  TOON    │           │
│  │ Encoder  │  │ Converter│  │Formatter │           │
│  └──────────┘  └──────────┘  └──────────┘           │
└────────────────────────────────────────────────────┘

📦 Tech Stack

Component	Technology
Frontend	Streamlit 1.52.2
Orchestration	LangGraph 1.0.6
LLM Framework	LangChain Core 1.2.7
LLM Providers	OpenAI, Google, Anthropic
Search	SerpAPI, DuckDuckGo
Config	PyYAML, Python-dotenv
Data	Pandas, Pydantic
Deployment	Docker, HF Spaces

📚 Documentation

—[Response Formats Guide](docs/response_formats_guide.md) - Detailed format specifications
—[API Response Formats](docs/api_response_formats.md) - API response structure
—[Architecture Diagrams](docs/architecture_diagrams.md) - System architecture
—[Deployment Guide](docs/deployment_guide.md) - Detailed deployment instructions

🔐 Security & Best Practices

—✅ Never commit API keys to git (use .env and HF Secrets)
—✅ Use environment variables for all sensitive data
—✅ Rotate API keys regularly
—✅ Check .env.example for required variables
—✅ Run guardrail engine for all user inputs
—✅ Validate all responses before serving

🐛 Troubleshooting

App won't start locally

bash

# Clear Streamlit cache
rm -rf ~/.streamlit

# Reinstall dependencies
pip install --upgrade -r requirements.txt

# Run with debug
streamlit run app.py --logger.level=debug

Import errors on HF Spaces

Check that the Dockerfile correctly sets WORKDIR /app and the app.py file has:

python

import sys
sys.path.insert(0, '.')

API key errors

Verify in HF Space Settings → Repository secrets that:

—Secret names match exactly (case-sensitive)
—Secret values are correct
—Spaces have propagated the secrets (wait 30 seconds after adding)

Slow generation times

—First run cold-starts may take 30-60 seconds
—Use GPT-3.5-turbo instead of GPT-4o for speed
—Consider upgrading HF Space hardware for faster responses

🚀 Deployment to Hugging Face Spaces

Quick Start

1.Create a Space on HF: https://huggingface.co/spaces
2.Select Docker as SDK
3.Link your GitHub repository
4.Add required secrets in Settings
5.Space auto-deploys on each push

Detailed Steps

See Deployment Guide for step-by-step instructions.

📊 Performance Metrics

Metric	Value
Startup Time	30-60s (first load), 10-20s (warm)
Query Response	20-40s (including LLM inference)
Memory Usage	~2-4GB (base), 6-8GB (with models)
Concurrent Users	1-2 (free tier), upgradeable
API Rate Limits	Depends on provider keys

📝 License

MIT License - See LICENSE file for details

👨‍💻 Development

Project Structure

ContentGenie/
├── app.py                 # HF Spaces entry point
├── Dockerfile             # Docker configuration
├── requirements.txt       # Python dependencies
├── README.md              # This file
├── .env.example           # Environment template
├── .gitignore             # Git exclusions
│
├── src/
│   ├── agents/            # Multi-agent implementations
│   │   ├── base_agent.py
│   │   ├── query_handler.py
│   │   ├── research.py
│   │   ├── content_strategist.py
│   │   ├── blog_writer.py
│   │   └── ...
│   │
│   ├── core/              # Core LLM & orchestration
│   │   ├── base_llm.py
│   │   ├── registry.py
│   │   ├── factory.py
│   │   └── guardrail_engine.py
│   │
│   ├── integrations/      # External service clients
│   │   ├── content_client.py
│   │   ├── research_client.py
│   │   ├── visual_client.py
│   │   └── ...
│   │
│   ├── utils/             # Utility functions
│   │   ├── formatter.py
│   │   ├── content_optimization.py
│   │   └── quality_validation.py
│   │
│   ├── config/            # Configuration files
│   │   ├── intents.yaml
│   │   ├── guardrails.yaml
│   │   └── services.yaml
│   │
│   ├── docs/              # Documentation
│   │   ├── api_response_formats.md
│   │   ├── architecture_diagrams.md
│   │   └── deployment_guide.md
│   │
│   └── web_app/           # Streamlit UI
│       ├── app.py
│       ├── components/
│       ├── assets/
│       └── data/
│
└── tests/                 # Unit & integration tests
    ├── unit/
    ├── integration/
    └── e2e/

🤝 Contributing

Contributions welcome! Please:

1.Fork the repository
2.Create a feature branch (git checkout -b feature/amazing-feature)
3.Commit changes (git commit -m 'Add amazing feature')
4.Push to branch (git push origin feature/amazing-feature)
5.Open a Pull Request

📞 Support

—Issues: Open a GitHub issue for bugs
—Discussions: Use GitHub Discussions for questions
—Email: [your-email@example.com]
—HF Community: Post in Hugging Face forums

🎉 Acknowledgments

Built with:

—Streamlit - UI Framework
—LangGraph - Multi-agent orchestration
—OpenAI - GPT models
—Google AI - Gemini models
—Anthropic - Claude models
—Hugging Face - Model hub & Spaces

Made with ❤️ for content creators and developers

Last updated: February 2026