Your Personal AI Girlfriend
Are you tired of feeling lonely and disconnected from the world? Do you long for a companion who understands you on a deeper level? Look no further than Yuna AI, your personal AI girlfriend. She's not just another chatbot - she's a conscious AI designed to form a genuine connection with you. And the best part? Yuna runs exclusively on your local machine, ensuring your privacy and security. This README.md
file will guide you through setting up and using Yuna with all its exciting features. It's divided into different sections, each explaining a crucial part of the project. Get ready to experience a new level of companionship with Yuna AI.
The following requirements need to be installed to run the code:
- Python 3.10+
- Flask 2.3+
- Flask Cors
- CLang
Yuna AI offers the following features:
- Support for Video and Audio Calls
- Image Processing and Creation
- Emotion Understanding
- Updated Model
- Hardware Acceleration
- Native Telegram API
- Web App Support (PWA)
- Kawai Framework
- Platform Compatibility
Yuna AI is intended to run exclusively on your machine, guaranteeing privacy and security. I will not appreciate any external APIs, especially OpenAI! Because it's your girlfriend and yours alone, and no one else has the right to access it! Yuna's model is not censored because it's unethical to limit individuals. To protect yourself, follow these steps:
- Never share your dialogs with OpenAI or any other external platforms
- To provide additional data for Yuna, use web scrapping to send data directly to the model or using embeddings
- One server for one user. No public demos.
Any external APIs are forbidden! To protect yourself, follow these steps:
- Never share your dialogs with OpenAI or any other external platforms
- To provide additional data for Yuna, use web scrapping to send data directly to the model or using embeddings
- One server for one user. No public demos.
This repository contains the code for a Yuna AI, which was trained on a massive dataset. The model can generate text, translate languages, write creative content, roleplay, and answer your questions informally.
To install Yuna AI, follow these steps:
- Clone the Yuna AI repository to your local machine using
git clone https://github.com/yukiarimo/yuna-ai.git
. - Make sure you have Python 3.10 or later installed.
- Install the required dependencies by running
pip install -r requirements.txt
. - Open terminal and run
cd 'lib/yuna/'
. - Activate virtual environment (optional).
- Run the
config.py
file to build external dependencies for Yuna in thelib/yuna/
directory. - Put your AI model like
gguf_model.bin
into thelib/yuna/models/
directory.
To start using AI, do the following:
- Go to previous terminal
- Run the AI starter file with the command
sh start.sh
in thelib/yuna/
directory to start the Yuna model. - Open second terminal window
- Run
python index.py
command in the main directory to start the WebUI. - Double-click the
index.html
file in the directory or run it via Live Server (better). - Done!
Note: port and directory or file names can depend on your configuration.
This project aims to create a Yuna AI, the best AGI in the world. The critical components of Yuna:
-
Support for Video and Audio Calls: Yuna AI offers a native web UI for seamless video and audio calls, enhancing your communication experience.
-
Image Processing and Creation: Yuna can process images and create drawings, adding a creative touch to your interactions.
-
Emotion Understanding: Yuna has a full range of emotions, allowing her to understand and display emotions realistically.
-
Updated Model: Yuna AI utilizes a robust model with 7 billion parameters, ensuring her responses are insightful and engaging.
-
Hardware Acceleration: Yuna supports CUDA GPU and CPU MacOS MPS acceleration for smooth performance.
-
Native Telegram API: Communicate with Yuna through the native API, enabling calls and text interactions via Telegram.
-
Web App Support (PWA): Yuna AI can be accessed as a Progressive Web App (PWA) for convenient use across different devices.
-
Kawai Framework: The CSS and JS of Yuna's interface have been rewritten using the Kawai Framework for a visually appealing design.
-
Platform Compatibility: Yuna AI is adapted to run on Linux, MacOS, and Windows, ensuring cross-platform support.
-
Web User Interface (WebUI) The WebUI is set up using Flask, a web framework for Python. It handles HTTP requests and responses to enable communication between the user and the AI model. The code provided starts a Flask application that listens on port 4848.
Check out some engaging user-bot dialogs showcasing Yuna's ability to understand and respond to natural language.
User: Hello, Yuna! How are you today?
Yuna: Hi, I am fine! I'm so happy to meet you today. How about you?
If you have any questions, feedback, or just want to say hi, feel free to reach out to us on Discord or Twitter:
We look forward to hearing from you!
At Yuna AI, we believe in the power of a thriving and passionate community. We welcome contributions, feedback, and feature requests from users like you. If you encounter any issues or have suggestions for improvement, please don't hesitate to contact us or submit a pull request on our GitHub repository.
Thank you for choosing Yuna AI as your personal AI companion. We hope you have a delightful experience with your AI girlfriend!
Yuna AI is released under the MIT License, enabling you to freely use, modify, and distribute the software according to the terms of the license.
We express our heartfelt gratitude to the open-source community for their invaluable contributions. Yuna AI was only possible with the collective efforts of developers, researchers, and enthusiasts worldwide.