# cognee
Deterministic LLMs Outputs for AI Engineers using graphs, LLMs and vector retrieval
Open-source framework for creating self-improving deterministic outputs for LLMs.
Try it in a Google collab notebook or have a look at our documentation
If you have questions, join our Discord community
## 📦 Installation
### With pip
```bash
pip install cognee
```
### With poetry
```bash
poetry add cognee
```
## 💻 Usage
### Setup
```
import os
os.environ["LLM_API_KEY"] = "YOUR OPENAI_API_KEY"
```
or
```
import cognee
cognee.config.llm_api_key = "YOUR_OPENAI_API_KEY"
```
If you are using Networkx, create an account on Graphistry to visualize results:
```
cognee.config.set_graphistry_username = "YOUR_USERNAME"
cognee.config.set_graphistry_password = "YOUR_PASSWORD"
```
To run the UI, run:
```
docker-compose up cognee
```
Then navigate to localhost:3000/wizard
You can also use Ollama or Anyscale as your LLM provider. For more info on local models check our [docs](https://topoteretes.github.io/cognee)
### Run
```
import cognee
text = """Natural language processing (NLP) is an interdisciplinary
subfield of computer science and information retrieval"""
await cognee.add([text], "example_dataset") # Add a new piece of information
await cognee.cognify() # Use LLMs and cognee to create knowledge
await search_results = cognee.search("SIMILARITY", {'query': 'Tell me about NLP'}) # Query cognee for the knowledge
print(search_results)
```
Add alternative data types:
```
cognee.add("file://{absolute_path_to_file}", dataset_name)
```
Or
```
cognee.add("data://{absolute_path_to_directory}", dataset_name)
# This is useful if you have a directory with files organized in subdirectories.
# You can target which directory to add by providing dataset_name.
# Example:
# root
# / \
# reports bills
# / \
# 2024 2023
#
# cognee.add("data://{absolute_path_to_root}", "reports.2024")
# This will add just directory 2024 under reports.
```
Read more [here](docs/index.md#run).
## Vector retrieval, Graphs and LLMs
Cognee supports a variety of tools and services for different operations:
- **Local Setup**: By default, LanceDB runs locally with NetworkX and OpenAI.
- **Vector Stores**: Cognee supports Qdrant and Weaviate for vector storage.
- **Language Models (LLMs)**: You can use either Anyscale or Ollama as your LLM provider.
- **Graph Stores**: In addition to LanceDB, Neo4j is also supported for graph storage.
## Demo
Check out our demo notebook [here](https://github.com/topoteretes/cognee/blob/main/notebooks/cognee%20-%20Get%20Started.ipynb)
[
](https://www.youtube.com/watch?v=BDFt4xVPmro "Learn about cognee: 55")
## How it works
## Star History
[](https://star-history.com/#topoteretes/cognee&Date)