Load your data

Difficulty: Beginner

Overview

cognee let’s you load from 30+ data sources using dlt. You can connect relational, graph and vector stores to cognee.

Let’s create a basic LLM memory with cognee

Adding data to our graph and connecting it to LLM can help LLM reason better. You move from large amounts of text to structured data. See before and after bellow.

Here is what we start with:

Before

And here is how it ends:

After

Step 1: Clone cognee repo


git clone https://github.com/topoteretes/cognee.git

And our getting started repo


git clone https://github.com/topoteretes/cognee-starter.git

Step 2: Install with poetry

Navigate to cognee repo


cd cognee

Install with poetry


poetry install

Step 3: Run simple cognee script

Create a python file called simple_example.py and copy the code from the following link into it

https://github.com/topoteretes/cognee-starter/blob/main/src/pipelines/default.py

Step 4: Run cognee

In order to load the data Run


python simple_example.py

Step 5: Inspect your cognee graph

The script will create an html file in the root folder that you can inspect and check the graph


import webbrowser
import os
from cognee.api.v1.visualize.visualize import visualize_graph
await visualize_graph()
home_dir = os.path.expanduser("~")
html_file = os.path.join(home_dir, "graph-visualization.html")
webbrowser.open(f"file://{html_file}")
# display(html_file) in notebook

If you prefer video tutorial, check this short video that our engineer Igor made

Join the Conversation!

Have questions? Join our community now to connect with professionals, share insights, and get your questions answered!