A GPT memory management library
Project description
GPT Memory
GPT Memory is a package that stores historical memory of your ChatGPT conversations and uses these memories to improve subsequent interactions. The system automatically classifies the memories and generates abstracts to complement the GPT context limitations.
Features
- Historical Memory Storage: Stores and manages historical chat data.
- Automatic Classification: Automatically classifies chat memories for better organization.
- Abstract Generation: Generates abstracts of past conversations to enhance GPT's context handling.
Installation
To install GPT Memory, use pip:
pip install gpt_memory
Usage
Importing and Using the Memory Class
To start using GPT Memory, import the Memory
class and process a user message:
from gpt_memory import Memory
m = Memory()
status, response = m.process_message('user_message')
Command Line Chat Interface
You can also run the command line chat interface to interact with GPT Memory:
python ui.py
Example
Here’s a simple example of how to use the Memory
class:
from gpt_memory import Memory
# Initialize the memory system
memory_system = Memory()
# Process a user message
status, response = memory_system.process_message('Hello, how are you?')
# Print the status and response
print(f"Status: {status}")
print(f"Response: {response}")
Contributing
If you would like to contribute to GPT Memory, please follow these steps:
- Fork the repository.
- Create a new branch for your feature or bugfix.
- Implement your changes.
- Submit a pull request.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Contact
For any questions or inquiries, please contact your.email@example.com.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file gpt_memory-0.0.7.tar.gz
.
File metadata
- Download URL: gpt_memory-0.0.7.tar.gz
- Upload date:
- Size: 9.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.11.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | f33f820945f7fe1e7a38eda9e0594f7d8b6f7ea91d09be272da1200e7a9230d1 |
|
MD5 | 15361fee88290c505312875968f14627 |
|
BLAKE2b-256 | ca4e750837f44975ead352f2afceefa1ee5cea3b9c1e9e9432807c1a7523024e |
File details
Details for the file gpt_memory-0.0.7-py3-none-any.whl
.
File metadata
- Download URL: gpt_memory-0.0.7-py3-none-any.whl
- Upload date:
- Size: 9.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.11.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5d3f054440ad6644ae915422cf4e412c5f52d3c9f9dbdae086ead97b9442eb0f |
|
MD5 | d352cb06a22a5e9713e69aeef9d0ff59 |
|
BLAKE2b-256 | ac97df194a71f028659573490bcd60f9e9f567fdf641ede76ab1cf07a5f436f0 |