README.md

metadata

title: Deep_Research_Assistant
app_file: app.py
sdk: gradio
sdk_version: 5.29.0

🔍 Deep Research Assistant

A comprehensive AI-powered research assistant that delivers high-quality, well-researched reports with built-in quality assurance and email delivery capabilities.

🚀 Features

🤖 Enhanced AI Research System

• Real-Time Progress Tracking: See step-by-step progress as research happens
• Quality Evaluation: Every report is automatically assessed for completeness, accuracy, and clarity
• Smart Optimization: Reports scoring below 7/10 are automatically improved
• Multi-Strategy Search: Uses multiple search approaches for comprehensive coverage
• Email Delivery: Optional email delivery of research reports
• BYOAPI Key Support: Use your own OpenAI API key to avoid rate limits
• Model Selection: Choose from multiple OpenAI models (GPT-4o, GPT-4, GPT-3.5, O1, etc.)

🎯 Research Modes

1. 🚀 Interactive Research with Clarification (Recommended)

   • Generates clarifying questions to focus your research
   • Provides more targeted and relevant results
   • Uses the enhanced quality assurance pipeline

2. 🤖 Enhanced Direct Research

   • Advanced AI system with automatic quality evaluation
   • Iterative improvement when needed
   • Full traceability with OpenAI traces

3. ⚡ Quick Research

   • Fast research for simple queries
   • Legacy compatibility mode
   • Good for straightforward questions

🛠️ Setup

API Configuration Options

Option 1: Provide Your Own API Key (Recommended)

• Enter your OpenAI API key directly in the interface
• Choose your preferred model from the dropdown
• Avoids rate limits and provides more control

Option 2: Environment Variables (For Development)

You can also set up environment variables:

# Optional - Default OpenAI API for research
OPENAI_API_KEY=your_openai_api_key_here

# Optional - SendGrid for email delivery
SENDGRID_API_KEY=your_sendgrid_api_key_here
SENDGRID_FROM_EMAIL=your_verified_sender_email@example.com

For Hugging Face Spaces Deployment

1. Fork this space or create a new one
2. Add your secrets in the Space settings:
   • OPENAI_API_KEY: Your OpenAI API key
   • SENDGRID_API_KEY: Your SendGrid API key (optional)
   • SENDGRID_FROM_EMAIL: Your verified sender email (optional)
3. Deploy - The space will automatically install dependencies and launch

For Local Development

1. Clone the repository:

   git clone <your-repo-url>
   cd deep_research
   

2. Install dependencies:

   pip install -r requirements.txt
   

3. Set up environment variables:

   cp .env.example .env
   # Edit .env with your API keys
   

4. Run the application:

   python app.py
   

🔑 Benefits of BYOAPI Key

Why Use Your Own API Key?

• No Rate Limits: Avoid 429 errors from shared API quotas
• Cost Control: Pay only for what you use
• Model Choice: Select the best model for your needs and budget
• Faster Processing: Direct access without queuing
• Privacy: Your queries stay between you and OpenAI

Model Recommendations

• GPT-4o-mini: Best cost-efficiency for most research tasks
• GPT-4o: Balanced performance and speed
• GPT-4: High quality for complex analysis
• O1-Preview: Advanced reasoning for technical topics

📊 Real-Time Progress Tracking

The research assistant now provides live updates during the research process, showing exactly what's happening at each step:

Progress Steps

1. 📋 Planning: AI analyzes your query and creates a strategic search plan
2. 🔍 Searching: Performs multiple targeted web searches (shows progress for each search)
3. ✍️ Writing: Synthesizes information into a comprehensive initial report
4. 🔍 Evaluating: AI quality assessment of the report
5. 🔧 Optimizing: Improves the report if needed (only when quality score < 7/10)
6. 📧 Delivering: Email delivery (if configured) or final report display

Progress Display Features

• Step-by-step visibility: See exactly which phase is currently running
• Individual search tracking: Monitor each web search as it completes
• Quality scores: View the evaluation score and whether optimization was needed
• Real-time updates: Progress streams live without page refreshes
• Trace integration: Each step links to detailed OpenAI trace logs

📊 Quality Assurance System

Our enhanced research system includes automatic quality evaluation:

Evaluation Criteria

• Completeness: How thoroughly the query is addressed
• Accuracy: Factual correctness and source reliability
• Clarity: Writing quality and organization
• Depth: Analysis depth and insight quality
• Relevance: Content alignment with the original query

Scoring Scale

• 9-10: Excellent (no refinement needed)
• 7-8: Good (minor improvements)
• 5-6: Adequate (refinement recommended)
• 1-4: Poor (automatic refinement triggered)

🎮 How to Use

1. Configure API Settings:

   • Enter your OpenAI API key
   • Select your preferred model (GPT-4o-mini recommended for cost efficiency)

2. Enter Your Research Query: Describe what you want to research

3. Configure Email (Optional): Set up email delivery if desired

4. Choose Research Mode:

   • Click "🚀 Start Research" for interactive clarification mode
   • Use "🤖 Enhanced Research" for direct advanced research
   • Use "⚡ Quick Research" for fast results

5. Get Results:

   • Watch real-time progress updates during research
   • View comprehensive research report
   • See which model was used for the research
   • Receive email delivery (if configured)
   • Access detailed trace logs for transparency

🔧 Technical Architecture

Built with:

• Frontend: Gradio for interactive web interface
• Backend: OpenAI Agents framework for modular AI system
• Quality Assurance: Automated evaluation and optimization pipeline
• Email: SendGrid integration for report delivery
• Tracing: OpenAI trace integration for full transparency

Agent-Based Architecture

The system uses specialized AI agents:

• Research Manager: Orchestrates the entire research process
• Planner Agent: Creates strategic search plans
• Search Agent: Performs web searches
• Writer Agent: Generates comprehensive reports
• Evaluator Agent: Assesses report quality
• Optimizer Agent: Improves reports when needed
• Email Agent: Handles report delivery

📝 Example Queries

Try these example research queries:

• "Latest developments in renewable energy storage technology"
• "Impact of AI on healthcare industry in 2024"
• "Sustainable urban planning strategies for climate change"
• "Cybersecurity trends and threats in financial services"
• "Electric vehicle market analysis and future projections"

🤝 Contributing

We welcome contributions! Areas for improvement:

• Additional research sources and tools
• Enhanced evaluation criteria
• New output formats
• UI/UX improvements
• Performance optimizations

🙏 Acknowledgments

Special thanks to Ifiok Moses (greattkiffy) for the valuable feedback that led to the implementation of BYOAPI key support and model selection features. This enhancement significantly improves user experience by eliminating rate limits and providing greater control over API usage.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙋‍♀️ Support

• Issues: Report bugs or request features via GitHub Issues
• Documentation: Check out the enhanced README in the repository
• Trace Logs: Use the provided trace IDs to debug research processes

---

Built with ❤️ using OpenAI Agents, Gradio, and modern AI research techniques.