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}

📦 Installation

With pip:

pip install cognee

With poetry:

poetry add cognee

💻 Usage

cognee.add() - Add a new piece of information to storage

cognee.cognify() - Use LLMs to create graphs

cognee.search() - Query the graph for a piece of information

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.