cognee¶
Deterministic LLMs Outputs for AI Engineers¶
Open-source framework for loading and structuring LLM context to create accurate and explainable AI solutions using knowledge graphs and vector stores
Let's learn about cogneeHub!¶
cogneeHub is a free and open-sourced learning platform for those interested in creating deterministic LLM outputs. We help people with using graphs, LLMs and adding vector retrieval to their ML stack.
- Get started — Get started with cognee quickly and try it out for yourself.
- Conceptual Overview — Learn about the core concepts of cognee and how it fits into your projects.
- Data Engineering and LLMOps — Learn about some data engineering and llmops core concepts that will help you build better AI apps.
- RAGs — We provide easy-to-follow learning materials to help you learn about RAGs.
- Research — A list of resources to help you learn more about cognee and LLM memory research
- Blog — A blog where you can read about the latest news and updates about cognee.
- Support — Book time with our team.
Vision¶
Architecture¶
Why use cognee?¶
The question of using cognee is fundamentally a question of why to have deterministic outputs for your llm workflows.
-
Cost-effective — cognee extends the capabilities of your LLMs without the need for expensive data processing tools.
-
Self-contained — cognee runs as a library and is simple to use
-
Interpretable — Navigate graphs instead of embeddings to understand your data.
-
User Guided — cognee lets you control your input and provide your own Pydantic data models
License¶
This project is licensed under the terms of the Apache License 2.0.