Skip to content

Latest commit

 

History

History
38 lines (24 loc) · 1.73 KB

readme.md

File metadata and controls

38 lines (24 loc) · 1.73 KB
Raw

Introduction

This is a code repository for a multi-modal AI voice assistant that can perform various tasks such as taking screenshots, capturing webcams, extracting clipboard content, and generating images. The code is written in Python and uses various libraries to perform these tasks.

Models Used

  • LLaMA-8B-8192: This is a large language model used to generate text and respond to user prompts.
  • DALL-E-2: This is a text-to-image model used to generate images.
  • Groq: This is a library used to interact with the Groq AI platform.
  • PIL: This is a library used to interact with images.
  • cv2: This is a library used to interact with the webcam.
  • pyperclip: This is a library used to interact with the clipboard.
  • google.generativeai: This is a library used to interact with the Google Generative AI platform.

Code Description

The code is designed to run the multi-modal AI voice assistant. The assistant can perform various tasks such as taking screenshots, capturing webcams, extracting clipboard content, and generating images. The code uses various libraries to perform these tasks.

Usage

  1. Run the code and interact with the AI voice assistant by entering commands. The AI will respond accordingly.
  2. The AI can take screenshots and capture webcams.
  3. The AI can extract clipboard content and generate images.
  4. The AI can respond to user prompts and perform tasks accordingly.

License

The code is licensed under the Apache License 2.0.

Contributing

The code is open-source, and contributions are welcome. If you would like to contribute to the code, please reach out to the author.

Note

This code is for educational purposes only and should not be used for commercial or production purposes.

testing