Skip to content

Latest commit

 

History

History
66 lines (47 loc) · 2.1 KB

README.md

File metadata and controls

66 lines (47 loc) · 2.1 KB
Raw

Generative AI Idea Validator for Circular Economy

Product Demo

Click Here

Presentation Slides

Click Here

Overview

The Generative AI Idea Validator for Circular Economy is a cutting-edge tool that automates the assessment of circular economy ideas. Leveraging the power of OpenAI GPT-4, the tool generates detailed reports, classifies ideas, and provides insights into sustainability, business viability, impact, and innovation aspect of the ideas.

How does it work

  1. Input Problem and Solution / PDF
  2. Click "Process Input"
  3. Model will be run and a report will be generated featuring the following areas:
    • Overview of the problem and idea
    • Relevant Industries
    • Sustainability Analysis
    • Business Assessment
    • Impact and Innovation Analysis
  4. Within the key featured areas, ratings will be shown with some suggested follow-up questions
  5. Continue with your follow-up questions to understand more about the idea and more

Technical Implementation

  1. Generative AI: Leveraged OpenAI GPT-4 pre-trained model for generating answers. Called OpenAI Assistant API to enable continuous responses to maintain context of previous messages in threads. Prompt engineering instructions and responses to structure the report.
  2. Front-end Management: Utilized Streamlit for an interactive front end.
  3. Data Sources: Used various circular economy ideas with problem and solution for model testing and development.

Getting Started

  1. Clone Repository
git clone git@github.com:brianchanbc/GenAIEarthHack.git
cd GenAIEarthHack
  1. Install Dependencies
python -m venv earthhack
activate earthhack
pip install -r requirements.txt
  1. Insert OpenAI API Key and Specify Model
echo "OPENAI_API_KEY=your_api_key_here" >> .env
echo "OPENAI_MODEL=your_model_here" >> .env
  1. Run App
streamlit run app.py

Contributions

Brian Chan, Samantha Yom, Po-Ju Chen, Ya-Wei Tsai from the University of Chicago

License

This project is licensed under the MIT License.