Skip to content

An AI-powered coding assistant that can solve scientific computational workflows

License

Notifications You must be signed in to change notification settings

UIUC-Chatbot/workflow-agent

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Welcome to the 2024 Ashby Prize in Computational Science Hackathon

Rules and Judging

  1. You can create anything you want but it must involve computatoinal science.
  2. You will be judgged primarially on innovation, inginuity and creativity, as well as the other criteria mentioned here like your final oral presentation.

Workflow Agent

An AI-powered coding assistant designed to streamline and solve complex scientific computational workflows. Leveraging advanced language models and a suite of development tools, it offers an intuitive interface for executing a wide range of tasks, from data analysis to full-stack development.

Features

  • Intelligent Planning: Generates step-by-step plans to achieve specified objectives.
  • Execution Environment: Runs code snippets using shell
  • Integration: Seamlessly interacts web browsers, and other tools for a comprehensive development experience.
  • Customizable Workflows: Tailored to specific scientific domains, enhancing productivity and accuracy.

Getting Started

  1. Clone the repository:

    git clone https://github.com/UIUC-Chatbot/workflow-agent
    
  2. Install dependencies:

    pip install -r requirements.txt
    
  3. Set up your environment variables in a .env file based on the provided .env.example.

  4. Install Playwright dependencies for browser automation:

    playwright install
    
  5. Prepare the issue.json file required for running the agent. This file should contain the issue data in JSON format that the agent will process. For the structure of issue.json, refer to the Issue class definition.

  6. Run the agent:

    python main.py
    

License

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

Contributing

Contributions are welcome! Please read our contributing guidelines for details on how to submit pull requests, report bugs, and suggest enhancements.

Acknowledgments

Special thanks to the Center for AI Innovation for supporting this project.

About

An AI-powered coding assistant that can solve scientific computational workflows

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages