Update README.md

This commit is contained in:
Vasilije 2025-02-15 05:40:55 +01:00 committed by GitHub
parent 2072c7a081
commit 978f2b640e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -27,6 +27,10 @@ Have you seen cognee's <a href="https://github.com/topoteretes/cognee-starter">s
<img src="assets/cognee_benefits.png" alt="why cognee" width="80%" />
</div>
### Contrbuting
We welcome contributions! To get started, please check our Contribution Guidelines
## 📦 Installation
You can install Cognee using either **pip** or **poetry**.
@ -109,29 +113,6 @@ cognee.config.set_llm_api_key("YOUR_OPENAI_API_KEY")
You can also set the variables by creating .env file, here is our <a href="https://github.com/topoteretes/cognee/blob/main/.env.template">template.</a>
To use different LLM providers, for more info check out our <a href="https://docs.cognee.ai">documentation</a>
If you are using Network, create an account on Graphistry to visualize results:
```
cognee.config.set_graphistry_config({
"username": "YOUR_USERNAME",
"password": "YOUR_PASSWORD"
})
```
(Optional) To run the with an UI, go to cognee-mcp directory and follow the instructions.
You will be able to use cognee as mcp tool and create graphs and query them.
If you want to use Cognee with PostgreSQL, make sure to set the following values in the .env file:
```
DB_PROVIDER=postgres
DB_HOST=postgres
DB_PORT=5432
DB_NAME=cognee_db
DB_USERNAME=cognee
DB_PASSWORD=cognee
```
### Simple example
@ -206,6 +187,7 @@ if __name__ == '__main__':
When you run this script, you will see step-by-step messages in the console that help you trace the execution flow and understand what the script is doing at each stage.
A version of this example is here: `examples/python/simple_example.py`
### Understand our architecture
cognee framework consists of tasks that can be grouped into pipelines.
@ -258,28 +240,8 @@ Please see the cognee [Development Guide](https://docs.cognee.ai/quickstart/) fo
```bash
pip install cognee
```
### Deployment at Scale (Modal)
Scale cognee in 4(+1) simple steps to handle enterprise workloads using [Modal](https://modal.com)'s GPU-powered infrastructure
**1. Install the modal python client**
```bash
pip install modal
```
**2. Create a free account on [Modal](https://modal.com)**
**3. Set Up Modal API Key**
```bash
modal token set --token-id TOKEN_ID --token-secret TOKEN_SECRET --profile=PROFILE
modal profile activate PROFILE
```
**4. Run cognee example**
This simple example will deploy separate cognee instances building their own memory stores and answering a list of questions at scale.
```bash
modal run -d modal_deployment.py
```
**5. Change the modal_deploy script and develop your own AI memory at scale 🚀**
## 💫 Contributors