README.md

---
title: DeepSearch
emoji: 😻
colorFrom: yellow
colorTo: blue
sdk: gradio
sdk_version: 5.33.1
app_file: app.py
pinned: false
short_description: performs comprehensive research on any query.
tags:
- mcp-server-track
contributors:
- LokeshReddy001
- suchith-koduru
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

demo-link: https://drive.google.com/file/d/1Xrj-5z2tcJYq124wlJndcJbVjHmP_Jos/view?usp=sharing

# Deep Research Assistant

Design of the agent is in the following [tldraw link](https://www.tldraw.com/f/ZCoiik0AvCCeCx2GOlqf6?d=v2200.-4065.1101.733.ADvUOyPQU3xs8HDV8iUjG)

An advanced AI-powered research assistant that performs comprehensive analysis and generates detailed reports on any topic. Built with Gradio and powered by Cerebras AI, Google search engine API.

## 🎥 Demo Video
<div align="center">
  <a href="https://drive.google.com/file/d/1Xrj-5z2tcJYq124wlJndcJbVjHmP_Jos/view?usp=sharing">
    <img src="https://img.shields.io/badge/Watch%20Demo-Video-red?style=for-the-badge&logo=youtube" alt="Watch Demo Video"/>
  </a>
</div>

## 🚀 Try It Live
<div align="center">
  <a href="https://huggingface.co/spaces/suchith-koduru/deepsearch">
    <img src="https://img.shields.io/badge/🤗%20Open%20In%20Spaces-blue?style=for-the-badge" alt="Open in Spaces"/>
  </a>
</div>

## 🌟 Features

- **Comprehensive Research**: Performs deep analysis using multiple research tools and AI models
- **Structured Reports**: Generates well-organized reports with:
  - Executive Summary
  - Main Findings with supporting details
  - In-depth Analysis
  - Clear Conclusions
  - Source Citations
- **Real-time Processing**: Get research results in real-time with live progress updates
- **User-friendly Interface**: Simple, clean Gradio interface for easy interaction
- **Markdown Support**: Results are formatted in clean, readable markdown

## 🛠️ Setup

1. Clone the repository:
   ```bash
   git clone https://github.com/YourUsername/deepsearch.git
   cd deepsearch
   ```

2. Install dependencies:
   ```bash
   pip install -r requirements.txt
   ```

3. Create a `.env` file in the root directory with your API key:
   ```
   GOOGLE_API_KEY="<get api key from https://console.cloud.google.com/apis/credentials>"
   GOOGLE_CSE_ID="<get cse id from https://programmablesearchengine.google.com/controlpanel/all>"
   CEREBRAS_API_KEY="<get api key from https://cloud.cerebras.ai/>"
   FIRECRAWL_API_KEY="<get api key from https://www.firecrawl.dev/app/api-keys>"
   ```

## 🏃‍♂️ Running Locally

1. Start the Gradio web interface:
   ```bash
   python app.py
   ```
2. Open your web browser and navigate to the URL shown in the terminal (typically http://localhost:7860)
3. Enter your research query and click submit

## 📝 Example Queries

The application works best with specific, focused queries. Here are some examples:
- "What are the latest developments in quantum computing?"
- "Explain the current state of climate change and its impacts"
- "What are the emerging trends in artificial intelligence?"

## 🔍 How It Works

1. **Query Refinement**: Your input is analyzed and structured into a comprehensive research query
2. **Research Phase**: Multiple tools are used to gather and analyze information:
   - Web searching for recent information
   - Content scraping for detailed analysis
   - Text summarization for key points
3. **Report Generation**: Results are compiled into a structured report with:
   - Executive Summary
   - Main Findings
   - Detailed Analysis
   - Conclusions
   - Source Citations

## ⚠️ Important Notes

- Requires valid API keys for all services (Google Search, Cerebras AI, Firecrawl)
- Some queries may take a few minutes to process depending on complexity
- Internet connection required for real-time research

## 🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.