🔬 DeepResearch AI

Your AI-powered research companion that transforms complex queries into comprehensive insights.

Features • Installation • Usage • Architecture • Contributing

🌟 Features

🤖 AI-Powered Research

• Contextual Understanding: Asks clarifying questions to understand your research needs
• Smart Query Generation: Uses Gemini Pro to create targeted search queries
• Deep Web Analysis: Scrapes and analyzes multiple sources for comprehensive insights
• Intelligent Processing: Handles rate limits and large content chunks efficiently

📊 Smart Output

• Executive Summaries: Concise overview of key findings
• Structured Analysis: Categorized insights and detailed breakdowns
• Source Tracking: Complete transparency with cited sources
• Markdown Reports: Clean, formatted reports saved automatically

🛡️ Enterprise-Grade Features

• Rate Limit Protection: Smart retry system with exponential backoff
• Token Management: Efficient handling of API token limits
• Error Resilience: Graceful handling of API and network issues
• Progress Tracking: Real-time updates on research progress

🚀 Installation

# Clone the repository
git clone https://github.com/Shasvinth/DeepResearch-AI.git

# Navigate to project
cd DeepResearch-AI

# Install dependencies
npm install

# Set up environment
cp .env.example .env.local

🔑 API Keys Setup

1. Get your Google AI (Gemini Pro) API key
2. Get your Firecrawl API key
3. Add to .env.local:

   GOOGLE_API_KEY="your_gemini_key"
   FIRECRAWL_KEY="your_firecrawl_key"

🎮 Usage

npm start

📝 Example Research Flow

1. Start Your Research

   What would you like to research?
   > Latest advancements in quantum computing
   

2. Set Parameters

   • Breadth (3-10): How many angles to explore
   • Depth (1-5): How deep to analyze each angle

3. Answer Context Questions

   What specific aspects of quantum computing interest you most?
   > Focus on error correction and scalability
   

4. Get Comprehensive Results

   • Executive Summary
   • Key Findings
   • Detailed Sources

🏗️ Architecture

graph TD
    A[User Query] --> B[Context Questions]
    B --> C[Query Generation]
    C --> D[Web Search]
    D --> E[Content Processing]
    E --> F[AI Analysis]
    F --> G[Report Generation]

Loading

📁 Project Structure

src/
├── core/           # Core business logic
├── models/         # AI model integrations
├── utils/          # Utility functions
└── tests/          # Test suites

🤝 Contributing

Contributions are welcome! Here's how you can help:

1. 🍴 Fork the repository
2. 🌿 Create your feature branch

   git checkout -b feature/AmazingFeature

3. 💾 Commit your changes

   git commit -m 'Add some AmazingFeature'

4. 📤 Push to the branch

   git push origin feature/AmazingFeature

5. 🔄 Open a Pull Request

📈 Future Roadmap

• Multi-model support (Claude, GPT-4)
• Custom search providers
• Interactive research mode
• Citation formats
• Research history tracking
• Export to multiple formats

📄 License

MIT © Shasvinth Srikanth

---

GitHub • Twitter

Made with ❤️ by Shasvinth Srikanth