5.2 KiB
5.2 KiB
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:
pip install cognee
With poetry:
poetry add cognee
💻 Usage
- Add a new piece of information to storage
import cognee
cognee.add(data_path, file_name)
- Use LLMs and cognee to create graphs
cognee.cognify(file_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.
