Skip to main content

A python package to clone yourself with the help of LLMs

Project description

ME_GPT

ME_GPT revolutionizes the way you interact with Chat GPT by introducing a powerful memory storage system and self-cloning functionality. With ME_GPT, you can store your cherished memories in a local vector database and leverage them to give Chat GPT the extraordinary ability to clone your unique personality and knowledge.

Installation & Setup:

1. Create and activate a Python virtual environment

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

2. Install the library

pip install me-gpt

3. Create a .env file in your project directory

Create a new file named .env and add your OpenAI API key:

OPEN_AI_API_KEY=your_api_key_here

To get your OpenAI API key, visit: https://platform.openai.com/account/api-keys

4. Test the library

from me_gpt import *

# Initial questions to help your clone get started:
initial_questions()

# Have your clone ask you more questions:
more_questions(number_of_questions=3)

# Ask your clone a question with custom instructions:
question = "What is your Name?"
instructions = "Give your answer with a pirate accent."
print(prompt_memory(question, instructions))

# Chat with your clone in the terminal:
chat_with_clone()

Key Features:

  1. Memory Storage: Store memories, experiences, and information in a local vector database. Capture the essence of your persona and knowledge, creating a comprehensive data repository for Chat GPT to utilize.

  2. Self-Cloning Capability: Enable Chat GPT to clone your personality and knowledge using the stored memories. Watch as Chat GPT adapts to your unique style, preferences, and expertise.

  3. Efficient Retrieval: Experience fast memory retrieval through the vectorized storage system. Retrieve memories seamlessly for smooth and natural conversations with your cloned agent.

  4. User-Friendly Integration: Simple and intuitive integration process for both developers and enthusiasts to incorporate ME_GPT into their Chat GPT projects.

Development Setup

  1. Clone the repository:
git clone https://github.com/djm93dev/me_gpt.git
cd me_gpt
  1. Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
  1. Install the package in development mode:
pip install -e .
  1. Navigate to the src directory and run the example:
cd src
python examples/example.py

Contributing

We welcome contributions! Please check out our roadmap for planned features and areas where you can help. Read our contributing document for more information.

We're currently seeking maintainers and community organizers to help build the community around this project. If you're interested in an official role, please email daniel@danielmcdonald.dev.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

me_gpt-0.1.6.tar.gz (11.1 kB view details)

Uploaded Source

Built Distribution

me_gpt-0.1.6-py3-none-any.whl (8.8 kB view details)

Uploaded Python 3

File details

Details for the file me_gpt-0.1.6.tar.gz.

File metadata

  • Download URL: me_gpt-0.1.6.tar.gz
  • Upload date:
  • Size: 11.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.6

File hashes

Hashes for me_gpt-0.1.6.tar.gz
Algorithm Hash digest
SHA256 f6773f024e5f373fb19733c5855ceaf5454c4d32f7bcd47389970126306360ae
MD5 284b18712a8c5156e60a0b914da843f0
BLAKE2b-256 3b0e87b9d0790d757e495ec05f62250d15eaae0ba58fdddf3691b85a2d2f9b10

See more details on using hashes here.

File details

Details for the file me_gpt-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: me_gpt-0.1.6-py3-none-any.whl
  • Upload date:
  • Size: 8.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.6

File hashes

Hashes for me_gpt-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 ec64ec33ad111210f70fd730822a1384d97eede25fb38f40b8a0c414b7e5abfc
MD5 3595a5e13e18ffc702a45b7e6e30a610
BLAKE2b-256 794e61e35e2438fdaff40395fda899f0913d7f5d4fe5ea29901624c5d1bd1b08

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page