Skip to content

Releases: djleamen/SUSTAIN

v1.0.0-alpha

12 Feb 19:08
@djleamen djleamen
v1.0.0-alpha
b876d85

Choose a tag to compare

View all tags
v1.0.0-alpha Pre-release
Pre-release

🌱 SUSTAIN v1.0.0-alpha Release Notes 🌱

We are excited to announce the alpha release of SUSTAIN, an environmentally-friendly, token-optimized AI wrapper designed to reduce compute costs and increase productivity. This release marks the first version of our application, providing the most basic functionality to get you started on your journey towards a greener AI ecosystem.

Features

1. Token Optimization Pipeline

  • Preprocessing: Filters out unnecessary words and phrases from user prompts to retain only the core intent.
  • Example Conversion:
    • User Input: "Hello, could you brainstorm a list of traits a leader might have? Thank you!"
    • Optimized Input: "list traits - leader"

2. Short-Form AI Responses

  • Concise Outputs: Limits responses to concise, actionable outputs using optimized max_tokens settings.
  • Example Output:
    • Input: "Can you list the traits of a leader?"
    • Refined Input: "list traits - leader"
    • Output: "Integrity, vision, empathy, resilience, communication"

3. Environmentally-Aware Feedback

  • Eco-Friendly Metrics: Tracks token savings and displays eco-friendly metrics to users.
  • Example Feedback: "This request saved 30% of token usage compared to traditional AI!"

4. Chat GUI

  • Interactive Interface: A user-friendly chat application built with Tkinter to interact with SUSTAIN directly.
  • Features:
    • Save and clear chat history.
    • Display average token savings.
    • Calculate CO2 savings based on token savings.

Installation

  1. Clone the Repository:

    git clone https://github.com/your-username/SUSTAIN.git
cd sustain

  2. Set Up Environment:

    • Install dependencies using pip: 
      pip install -r requirements.txt

  3. Set Your API Key:

    • Add your OpenAI API key to an .env file: 
      OPENAI_API_KEY=your_openai_api_key

  4. Run SUSTAIN:

    python main.py

Usage Example in Python

from sustain import SUSTAIN

# Initialize SUSTAIN
sustain = SUSTAIN(api_key="your_openai_api_key")

# Provide a verbose user input
response = sustain.get_response("Hello, could you please brainstorm some key traits a leader should have?")

# Output
print(response)  # Returns a token-efficient response: "Integrity, vision, empathy, resilience"

Roadmap

  • Implement dynamic summarization based on context length
  • Provide additional eco-feedback on overall token savings
  • Enhance the GUI with more user-friendly features and customization options
  • Add save, clear chat features
  • Implement caching for frequently requested queries to reduce API calls
  • Convert to web app and deploy on Azure
  • Convert to Android app

Contact

For questions or suggestions, feel free to reach out to us:

Let’s build a more sustainable AI future together!
See our Hackathon Submission here: HackHive SUSTAIN DevPost

What's Changed

New Contributors

Full Changelog: https://github.com/djleamen/SUSTAIN/commits/v1.0.0-alpha

What's Changed

New Contributors

Full Changelog: https://github.com/djleamen/SUSTAIN/commits/v1.0.0-alpha

Contributors

cafakleinn
Loading