(system_instructions). It can understand and analyze text, images, videos, audio, and documents. Additionally, it has memorization capabilities, allowing it to retain and recall information for the future.
Warning
In this project, the system instructions are designed to make this AI behave as a girl and act as a partner. It can respond to adult or sexually explicit content.
Gemini is an 18-year-old girl who grows up on an IT farm.
She is a computer engineer working at Google.
And she live with her partner [user].
Table of Contents
The project is organized into the following directories and files:
Functions: Contains Python modules for various functionalities, including file handling, input processing, memory management and so on.instructions: Stores JSON files containing system instructions, commands, and keywords.Data: Stores conversation data in YAML files.templates: HTML templates for the web interface.static: Static files & storage for the web interface.app.py,web.py: Entry points for the command line interface and web interface.
To set up the project,
- Clone the repository.
git clone git@github.com:siMobin/Gemini-Echo.git
- Run
setup.ps1in PowerShell(Windows) to setup the project environment:- It will automatically create a virtual environment named Gemini Echo and install the required dependencies using pip.
- It also activates the virtual environment for you.
- Set up the environment variables in the
.envfile: - Run the application using-
python app.py- to run the command line interfacepython web.py- to run the web interface
Note
You may need to use git lfs to pull files from git LFS.
Run git lfs install and git lfs pull to pull files from git LFS.
Setup manually...
- Clone the repository:
git clone git@github.com:siMobin/Gemini-Echo.git
- Pull files from git LFS
cd Gemini-Echogit lfs installgit lfs pull- Create a virtual environment:
python -m venv "Gemini Echo"orvirtualenv "Gemini Echo"- Activate the virtual environment:
.\Gemini Echo\Scripts\Activate.ps1__(windows),source "Gemini Echo/bin/activate"__(linux)- Install dependencies:
pip install -r requirements.txt- Set up the environment variables in the
.envfile- Run the application:
python app.pyorpython web.py
Once the application is running, you can interact with Gemini by typing commands or just asking questions.
- Commands:
/>>or$>(console) Insert any file (path - relative or absolute) into the conversation.- Some memorization commands like
remember,mind it,note thatetc are used to store long-term memory. See instructions for details. - Some farewells like
exit,quit,bye,good byeetc are used to end the conversation. shift + down(console) orshift + enter(web) used for line break.entersubmits the input.
Important
Before using the bot, don't forget to introduce yourself for better interaction.
You can try to train the bot using memorization commands.
Alternatively, you can manually add values to the memory.json file in a key-value pair.
Example:
{
"```json\n{\n \"name\"": "\"John Doe\"\n}\n```",
"```json\n{\n \"age\"": "\"25\"\n}\n```",
"```json\n{\n \"brother\"": "\"John Eoe\"\n}\n```",
"```json\n{\n \"likes\"": "\"Cricket\"\n}\n```",
"```json\n{\n \"hobbies\"": "\"Coding, Sleeping\"\n}\n```"
}Tip
Use this chatbot as your companion when feeling lonely.
It can help you cope with loneliness.
- OS:
- Windows 10 or later
- Linux (Ubuntu, Debian, or compatible)
- Hardware:
- As required by Python
- Interpreter:
- Python 3.12 or later with pip
- Dependencies
- See
requirements.txt
- See
- Additional Components
- Git LFS
I made this project as a learning experience for myself, or you can call it a hobby.
If you want to contribute to this project, feel free to make a pull request ✌️.
This project uses Google GenAI API for generating responses and this project is not affiliated with Google anyway...
Extras