No description
| .data | ||
| .github | ||
| assets | ||
| bin | ||
| cognitive_architecture | ||
| docs | ||
| iterations | ||
| .env.template | ||
| .gitignore | ||
| .pylintrc | ||
| __init__.py | ||
| api.py | ||
| CONTRIBUTING.md | ||
| Demo_graph.ipynb | ||
| docker-compose.yml | ||
| Dockerfile | ||
| entrypoint.sh | ||
| LICENSE | ||
| main.py | ||
| mkdocs.yml | ||
| poetry.lock | ||
| pyproject.toml | ||
| README.md | ||
cognee
Semantic AI Memory
Open-source framework for building AI Memory, extending the limits of cognitive architecture, designed for accuracy, transparency, and control.
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.
