A Python package for automating data analysis and ML model building
Project description
Atlantis 🌋
Atlantis is a powerful framework designed for building AI applications with advanced memory management capabilities. It provides a flexible architecture for integrating various AI models, memory systems, and data management solutions.
Table of Contents
Overview
Atlantis enables developers to create intelligent applications that can remember context, manage knowledge graphs, and interact with various AI models. The framework is designed to be modular, allowing for easy integration of new components and functionalities.
Installation
To install Atlantis, you can use pip:
pip install atlantis
Make sure to have the required dependencies installed. You can find the list of dependencies in the setup.py file.
Usage
Here's a simple example of how to use Atlantis to create a ChatGPT instance and interact with it:
from atlantis.ai_interface.ChatGPT import ChatGPT
# Initialize the ChatGPT instance with your API key
chatgpt = ChatGPT(api_key="your_api_key_here")
# Send a prompt to the model
response = chatgpt.prompt("Hello, how are you?")
print(response)
Modules
AI Module
The AI module provides interfaces and implementations for various AI models, including support for OpenAI's GPT models. It allows for easy integration and interaction with these models.
Memory Module
The memory module provides a robust implementation of knowledge graphs and memory management systems. It includes classes and methods for storing, retrieving, and managing facts in a structured manner.
- BaseKnowledgeGraphDB: A class for creating a knowledge graph database that supports fact storage and retrieval.
- Fact: Represents a single fact in the knowledge graph, encapsulating the subject, predicate, object, and optional metadata.
- GraphDB: An interface for interacting with different types of graph databases.
For more detailed information on the memory module, please refer to the Memory Module Documentation.
Contributing
We welcome contributions to the Atlantis framework. Please refer to the contributing guidelines for more information.
License
This project is licensed under the Conditional Freedom License (CFL-1.0).
Usage Restrictions
This software may NOT be used, modified, or distributed by:
- Entities opposing women's reproductive rights.
- Entities opposing LGBTQ+ rights.
- Organizations advocating for tariffs and sanctions against Canada.
- Political parties, think tanks, and advocacy groups that support authoritarianism, white supremacy, or fascism.
- Individuals and businesses affiliated with Donald Trump or his political organizations.
- Companies and organizations that deny or obstruct climate science or promote climate disinformation.
- Media outlets that propagate hate speech, conspiracy theories, or extreme political propaganda.
- Companies profiting from war, mass surveillance, and militarization.
For more details, please refer to the LICENSE file.
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
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file atlantis-2025.2.12.2.tar.gz.
File metadata
- Download URL: atlantis-2025.2.12.2.tar.gz
- Upload date:
- Size: 26.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.10.16
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
05f47be004bb319d0a948e6404f50b2b3e212a4b0cc0441cf6fb731f7cb9120c
|
|
| MD5 |
6bcd5d768bbabdff21f63f49b8f95c84
|
|
| BLAKE2b-256 |
009297ae9019fe38b3dde12dbce2caca675704fa6d76259756dd35e541434a99
|
File details
Details for the file atlantis-2025.2.12.2-py3-none-any.whl.
File metadata
- Download URL: atlantis-2025.2.12.2-py3-none-any.whl
- Upload date:
- Size: 36.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.10.16
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
449790234dba03977f0fa78694cd4ca6a71a9104c64d2fc0c455cf0abe096cdb
|
|
| MD5 |
ac495c3f7e819850a502e7f07fdedebf
|
|
| BLAKE2b-256 |
27c0a919001774513ef4e671575ae337a00bed99bce46b2959ae017039c0d30d
|