acumennations/cognee

Memory management for the AI Applications and AI Agents

cognee

Make data processing for LLMs easy

Open-source framework for creating knowledge graphs and data models for LLMs.

🚀 It's alive

Try it yourself on Whatsapp with one of our partners by typing /save {content you want to save} followed by /query {knowledge you saved previously} For more info here are the docs

📦 Installation

With pip:

pip install cognee

With poetry:

poetry add cognee

💻 Usage

Check out our demo notebook here

• Set OpenAI API Key as an environment variable

import os

# Setting an environment variable
os.environ['OPENAI_API_KEY'] = ''

• Add a new piece of information to storage

import cognee
cognee.add(absolute_data_path, dataset_name)

• Use LLMs and cognee to create graphs

cognee.cognify(dataset_name)

• Render the graph after adding your Graphistry credentials to .env

graph_url = await render_graph(graph, graph_type = "networkx")
print(graph_url)

• Query the graph for a piece of information

query_params = {
    SearchType.SIMILARITY: {'query': 'your search query here'}
}
cognee.search(graph, query_params) 

Demo

Architecture

How Cognee Enhances Your Contextual Memory

Our framework for the OpenAI, Graph (Neo4j) and Vector (Weaviate) databases introduces three key enhancements:

• Query Classifiers: Navigate information graph using Pydantic OpenAI classifiers.
• Document Topology: Structure and store documents in public and private domains.
• Personalized Context: Provide a context object to the LLM for a better response.