An open API service indexing awesome lists of open source software.

https://github.com/bklieger-groq/deep-research-fast

Lightning fast deep research app powered by Compound-beta on Groq!
https://github.com/bklieger-groq/deep-research-fast

Last synced: 5 months ago
JSON representation

Lightning fast deep research app powered by Compound-beta on Groq!

Awesome Lists containing this project

README

          




Deep Research Fast Logo




Deep Research Fast: Generate research reports
in seconds with Compound Beta on Groq










Features
Quickstart
Usage
Contributing


[Demo of Deep Research Fast](https://github.com/user-attachments/assets/068948df-0960-4beb-adea-2a561c69ed9e)
> Imagine deep research, spanning 50+ sources, taking 10 seconds. This is possible, only on Groq. Using multiple compound-beta-mini agents in parallel, Deep Research Fast achieves record speeds while producing comprehensive research reports.

## Features

- **Compound Agent Architecture**: Multiple mini agents working independently, before results are combined
- **Multimodal Results**: Text, links, and images are all returned in the report
- **Lightning Fast**: Research reports generated in seconds, not minutes
- **Comprehensive Coverage**: Access to an average of 40-60 sources for thorough research
- **Modern UI**: Clean and intuitive user interface for seamless research experience

## Quickstart

### Prerequisites

- Node.js
- npm
- A Groq API key (can be obtained for free from console.groq.com)

### Installation

```bash
# Clone the repository
git clone https://github.com/bklieger-groq/deep-research-fast.git

# Navigate to project directory
cd deep-research-fast

# Navigate to the frontend
cd frontend

# Install dependencies
npm install

# Set up environment variables
export GROQ_API_KEY=gsk...

# Run app
npm run dev
```

## Usage

1. Enter your research query in the search box
2. Click "Research" to start the process
3. View your research report in seconds

## Contributing

Contributions are welcome! Please feel free to submit a Pull Request detailing the feature and providing a video demo. Also feel free to open new issues and provide feedback!

## License

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