# cognee Make data processing for LLMs easy
Open-source framework for creating knowledge graphs and data models for LLMs.
)
[//]: # (
)
[//]: # ( )
[//]: # ( )
[//]: # (
)
[//]: # ( )
[//]: # ( )
[//]: # (
)
[//]: # ( )
[//]: # ( )
[//]: # (
)
[//]: # ( )
[//]: # ( )
[//]: # (
)
[//]: # ( )
[//]: # ( )
[//]: # (
)
[//]: # ( )
[//]: # (
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: ```bash pip install cognee ``` With poetry: ```bash 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 [
](https://www.youtube.com/watch?v=yjParvJVgPI "Learn about cognee: 55")
## 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.
