Skip to main content

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:

  1. Fork the repository.
  2. Create a new branch for your feature or bugfix.
  3. Implement your changes.
  4. 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


Download files

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

Source Distribution

gpt_memory-0.0.7.tar.gz (9.8 kB view details)

Uploaded Source

Built Distribution

gpt_memory-0.0.7-py3-none-any.whl (9.8 kB view details)

Uploaded Python 3

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

Hashes for gpt_memory-0.0.7.tar.gz
Algorithm Hash digest
SHA256 f33f820945f7fe1e7a38eda9e0594f7d8b6f7ea91d09be272da1200e7a9230d1
MD5 15361fee88290c505312875968f14627
BLAKE2b-256 ca4e750837f44975ead352f2afceefa1ee5cea3b9c1e9e9432807c1a7523024e

See more details on using hashes here.

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

Hashes for gpt_memory-0.0.7-py3-none-any.whl
Algorithm Hash digest
SHA256 5d3f054440ad6644ae915422cf4e412c5f52d3c9f9dbdae086ead97b9442eb0f
MD5 d352cb06a22a5e9713e69aeef9d0ff59
BLAKE2b-256 ac97df194a71f028659573490bcd60f9e9f567fdf641ede76ab1cf07a5f436f0

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